# Research Papers — 2026-07 · bundle page 101 of 222

> Full-text markdown of papers #5001–5050 of 11075 published in 2026-07, newest first. AI-readable mirrors of the full 11075-paper 2026-07 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-07/page/101
[← Previous bundle](https://aipod.dev/papers/archive/2026-07/page/100.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-07/page/102.md)

### CNS-Edit++: Category-Agnostic 3D Editing with Coupled Neural Shape Representation

Authors: Jingyu Hu, Weilong Yan, Zhengzhe Liu, Haipeng Li, Ka-Hei Hui, Hao Zhang, Chi-Wing Fu
Published: 2026-07-18
Categories: cs.CV, cs.GR
arXiv: https://arxiv.org/abs/2607.16577v2

This paper presents a latent-space 3D shape editing framework built upon a coupled neural shape (CNS) representation and a neural feature volume optimization. This work extends CNS-Edit, built on Coupled Neural Shape optimization, to CNS-Edit++, by generalizing the category-specific coupled representation to category-agnostic 3D shape editing with foundation models. The Coupled Neural Shape (CNS) representation couples a global latent code that captures high-level shape semantics with a 3D neural feature volume that provides spatial context for local shape manipulation. Then we formulate a coupled neural shape optimization procedure that co-optimizes these two components subject to a given editing operation. Our framework can be instantiated on both the category-specific 3D inversion model and category-agnostic 3D foundation models. We provide various shape editing operators, including copy, resize, delete, mix, point-wise drag, and region-wise drag, each of which is formulated as an objective to guide the CNS optimization. To preserve regions outside the editing area, we further introduce two complementary region-wise control mechanisms, i.e., KV-cache replacement and latent feature regularization. Extensive quantitative and qualitative evaluations across different 3D generative models demonstrate the strong capabilities of our approach over state-of-the-art solutions.

---

### How to Build Marcus's Algebraic Mind: From Thagard's Brain--Mind Viewpoint

Authors: Hiroyuki Chuma, Kanji Otsuka, Yoichi Sato
Published: 2026-07-18
Categories: cs.NE
arXiv: https://arxiv.org/abs/2607.16573v2

This paper reports a convergence neither program was looking for. Marcus's The Algebraic Mind named three things any architecture needs -- operations over variables, recursive structure, and individuals distinct from kinds -- showed multilayer perceptrons have none, and left a register-and-treelet implementation as conjecture. Thagard's Brain-Mind ran it from the other end, making binding the mechanism from which the whole of mind is assembled, and circular convolution load-bearing. Marcus leaves his register algebra open; Thagard's is lossy, degrading under the very recursion his own account demands. VaCoAl is a hyperdimensional computing architecture built end-to-end on XOR-and-shift over GF(2) via primitive-polynomial LFSRs; PyVaCoAl is its extended software realization (all results here); the silicon substrate exists as CASRAM. Bind(R,F) = R XOR Shift(F) is exactly reversible and non-commutative: it supplies all three pillars at fixed dimension and removes convolution's depth degradation. Capability: exact reversible binding at O(N) yields compositional generalization with post-hoc auditability, which no lossy or learned substrate offers. Necessity: two independent architecture programs and the dentate gyrus-CA3 circuit require the same algebra -- convergence, not biomimicry. New here: discrimination and failure-tolerance are one. Repair every collision (RR = 1) and the system is bit-identical to a hash dictionary: candidates become indistinguishable and the confidence path-integral collapses; a memory that never fails keeps no record of which routes were hard. Position: we do not surpass large language models but supply the auditable, multi-hop relational reasoning embeddings lack. No consciousness is implemented and no cognitive experiment reported; bit-exactness holds in silicon, approximately under biological noise; speed and power remain unbenchmarked.

---

### How to Build Marcus's Algebraic Mind: From Thagard's Brain--Mind Viewpoint

Authors: Hiroyuki Chuma, Kanji Otsuka, Yoichi Sato
Published: 2026-07-18
Categories: cs.NE
arXiv: https://arxiv.org/abs/2607.16573v1

Two critiques of connectionist cognition converge on one missing capacity. In The Algebraic Mind, Marcus isolated three components any architecture must support -- operations over variables, structured representations, and individuals distinct from kinds -- showed perceptrons support none, and left neural implementation as conjecture. In Brain-Mind, Thagard made binding the single mechanism assembling perception, emotion, consciousness, and self, but rested it on circular convolution, a lossy algebra that degrades under the recursion his account of self and emotion demands. We argue one substrate answers both. VaCoAl is a hyperdimensional architecture built on one primitive, XOR-and-shift over GF(2), on primitive-polynomial linear-feedback shift registers; PyVaCoAl is its extended realization, adding a multi-stage rescue circuit, million-dimensional scale, and a Rescue-Rate phase transition (SRAM-CAM hardware and low-power claim remain future work). Binding, Bind(R,F) = R $\oplus$ shift(F), is exactly reversible and non-commutative: it fills Marcus's open register algebra (Pillar 1), supports compositional bundling at fixed dimension (Pillar 2), and separates individuals from kinds (Pillar 3), while removing the depth-degradation that afflicts convolution at Thagard's deepest recursions. We make three scoped claims. Capability: exact reversible binding at O(N) yields compositional generalization with post-hoc auditability no lossy or learned substrate offers. Necessity: two independent cognitive-architecture programs and a biological circuit (dentate gyrus-CA3) requiring the same reversible-compositional algebra is evidence, by convergent evolution not biomimicry, that it is substrate-independent. Position: we do not claim to surpass LLMs; the substrate is orthogonal, supplying the reversible, auditable, multi-hop relational reasoning statistical embeddings structurally lack.

---

### Mapping Order in Semicrystalline Polymers using Machine Learning of Nanobeam Electron Diffraction

Authors: Nicholas Marchese, Arthur R. C. McCray, Yael Tsarfati, Karen Bustillo, Adam Marks, Alberto Salleo, Colin Ophus
Published: 2026-07-18
Categories: cond-mat.mtrl-sci, cs.LG
arXiv: https://arxiv.org/abs/2607.16570v1

Organic mixed ionic electronic conductors (OMIECs) are a promising class of polymer materials for applications spanning neuromorphic computation to energy efficient electronics and bioelectronics. Despite being highly tunable, the relationship between structural features and key performance properties such as charge carrier mobility is poorly understood. Scanning nanodiffraction in the transmission electron microscope (TEM) is a powerful probe for elucidating this structure-property relationship, but produces large, noisy datasets that are difficult to interpret because polymer reflections exhibit several distinct morphologies. To address the complexity, we trained a machine learning (ML) model to detect these polymer diffraction peaks and their intensities from synthetic data. Compared to correlative peak detection algorithms, the conventional method for analyzing nanobeam 4D scanning transmission electron microscopy (4DSTEM) data, we show that the ML model is significantly faster and outperforms correlative algorithms in almost all cases, opening up the possibility of near-live visualization of 4DSTEM experiments.

---

### Exact Network Surgery: Functional Invariance and Gradient Plasticity in Reactive Computational Graphs

Authors: Abdallah Khemais
Published: 2026-07-18
Categories: cs.AI, cs.LG, cs.PL
arXiv: https://arxiv.org/abs/2607.16568v2

Function-preserving network growth techniques such as Net2Net and progressive stacking expand a model's capacity without destroying its learned function, but existing formulations either tolerate numerical perturbations or require a full rebuild of the training program. We formalize Exact Network Surgery: the in-place insertion of a residual block into a live computational graph such that (i) the network function is preserved -- bit-exactly under explicit floating-point hypotheses -- and (ii) inserted parameters remain trainable immediately after insertion. We prove an identity-morphism theorem for gated residual blocks, a structural-locality theorem showing that a reactive invalidation engine recomputes exactly the downstream cone of the insertion point, leaving every other node's value and optimizer state untouched, and an escape-from-initialization proposition showing that the Gradient Shadowing gate alpha, initialized at zero over a randomly initialized branch, receives a generically non-zero gradient at insertion time. We identify a degenerate configuration -- zero-initialized output projections combined with a zero gate -- that is an exact saddle point gradient descent cannot escape. Every claim is validated on the reference implementation in NeuroDSL, a reactive graph engine in Julia: grafting is bit-exact on every logit tested (0 mismatches out of 1600); the gate escapes zero at the first optimizer step and unlocks branch gradients at the second, exactly as predicted; the degenerate configuration exhibits gradients identically zero for the entire 600-step run; surgery cost tracks downstream cone size with r = 0.9992 while graft-plus-invalidation bookkeeping is constant (about 0.75 ms) across insertion depths; and training resumes bit-identically across a real process restart. A flagged preliminary appendix reports first single-seed observations on post-insertion gate dynamics.

---

### Exact Network Surgery: Functional Invariance and Gradient Plasticity in Reactive Computational Graphs

Authors: Abdallah Khemais
Published: 2026-07-18
Categories: cs.AI, cs.LG, cs.PL
arXiv: https://arxiv.org/abs/2607.16568v1

Function-preserving network growth techniques such as Net2Net and progressive stacking expand a model's capacity without destroying its learned function, but existing formulations either tolerate numerical perturbations or require a full rebuild of the training program. We formalize Exact Network Surgery: the in-place insertion of a residual block into a live computational graph such that (i) the network function is preserved -- bit-exactly under explicit floating-point hypotheses -- and (ii) inserted parameters remain trainable immediately after insertion. We prove an identity-morphism theorem for gated residual blocks, a structural-locality theorem showing that a reactive invalidation engine recomputes exactly the downstream cone of the insertion point, leaving every other node's value and optimizer state untouched, and an escape-from-initialization proposition showing that the Gradient Shadowing gate alpha, initialized at zero over a randomly initialized branch, receives a generically non-zero gradient at insertion time. We identify a degenerate configuration -- zero-initialized output projections combined with a zero gate -- that is an exact saddle point gradient descent cannot escape. Every claim is validated on the reference implementation in NeuroDSL, a reactive graph engine in Julia: grafting is bit-exact on every logit tested (0 mismatches out of 1600); the gate escapes zero at the first optimizer step and unlocks branch gradients at the second, exactly as predicted; the degenerate configuration exhibits gradients identically zero for the entire 600-step run; surgery cost tracks downstream cone size with r = 0.9992 while graft-plus-invalidation bookkeeping is constant (about 0.75 ms) across insertion depths; and training resumes bit-identically across a real process restart. A flagged preliminary appendix reports first single-seed observations on post-insertion gate dynamics.

---

### ReqGenX: An Empirical Study of Atomic Decomposition, Artifact Regeneration, and Reconstruction for Legacy SRS Documents

Authors: Ragib Shahariar Ayon, Rayed Fahmi, Sumon Biswas, Shibbir Ahmed
Published: 2026-07-18
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2607.16564v1

Background: Evaluating automated Software Requirements Specification (SRS) generation is challenging because few datasets provide fine-grained traceability between source requirements, intermediate elicitation artifacts, and generated specifications. Aims: We aim to study whether legacy SRS documents can be transformed into traceable synthetic pre-SRS artifacts that support fine-grained evaluation of LLM-based SRS generation. Method: We conduct an empirical study using ReqGenX, a controlled pipeline that decomposes SRS sections into source-grounded atomic statements, routes atoms to standards-inspired artifact types through multi-LLM plurality voting, and generates artifacts using constrained prompts with iterative judge-guided refinement. We evaluate ReqGenX on seven PURE SRS documents using grounding, quality, information retention, and downstream reconstruction analyses. Results: ReqGenX produces faithful and usable atoms, with median AlignScore values typically between 0.96 and 0.99 and Prometheus scores ranging from 4.34 to 4.85. Generated artifacts remain strongly grounded in their source atoms, with AlignScore values typically between 0.80--0.94 and judge pass rates near 100%; stricter Prometheus evaluation yields pass rates from 54.8% to 97.1%. In a downstream SRS reconstruction case study, artifact-backed atoms remain recoverable from generated SRSs, with SBERT means between 0.69 and 0.75 and AlignScore medians between 0.76 and 0.84. Conclusions: Traceable synthetic pre-SRS artifacts can support more fine-grained evaluation of LLM-based SRS generation, while exposing tradeoffs among faithfulness, information retention, and artifact completeness.

---

### From Modalities to Propositions: A Language-Centric Framework for Multimodal Intelligence

Authors: Nadine Chang, Maying Shen, Shizhe Diao, Jialiang Wang, Jingde Chen, Thomas Breuel, Pavlo Molchanov, Rafid Mahmood, Jose M. Alvarez
Published: 2026-07-18
Categories: cs.AI, cs.CV, cs.LG, cs.MM
arXiv: https://arxiv.org/abs/2607.16560v1

We propose a language representation for multimodal data in which any observation, whether image, video, or text, is expressed as a bag of atomic propositions, simple statements about the entities, actions, and relations in a scene. A global semantic codebook unifies these into a shared vocabulary of canonical atomic propositions, placing every modality and observation into one interpretable space that spans fine grained facts to high level concepts and composes into richer ones. This brings interpretability with reasoning, cross-modal understanding and retrieval, and compositionality that enables complex multimodal understanding, rich data curation and complex structured retrieval. We demonstrate the framework on autonomous driving and open-world data.

---

### Capability Emergence Can Be Forecast: Per-Seed, In Advance, With Calibrated Intervals, Certified False Alarms, and a Blind Pre-Registered Gate

Authors: Gunner Levi Howe
Published: 2026-07-17
Categories: cs.LG
arXiv: https://arxiv.org/abs/2609.19000v1

Emergent capabilities are widely treated as unpredictable: loss improves smoothly while abilities appear abruptly. Prior work offers early-warning indicators but never scores them as forecasts: no lead time at controlled false-alarm rate, no calibration, no negatives, no blind tests. We supply that discipline and show that, in grokking model systems and small language models, emergence timing is forecastable per run, in advance, with calibrated uncertainty. Across 30 transformers at identical configuration, the formation time of the previous-token head forecasts each seed's induction-head emergence at Spearman rho=0.977 with median lead 975 steps (~15% of training); a best-case loss rule ties the ranking with 50-step lead (a nowcast). Conformal intervals covered 15/15 held-out seeds, and the frozen rule passed blind pre-registered gates on TWO never-seen configurations (10/10 and 9/10 coverage). A trap-language rung then attacked our own rule as pre-registered: where previous-token context pays for the task itself, the bare precursor false-alarms on 10/10 capability-blocked runs, while the mechanism-composed conjunction is certified in both language classes (0 false alarms) and times emergence at rho=1.000. Finally, a gap-origin study broke the fixed offset (both lr and batch move the gap ~2.3x; no external clock owns it) and revealed the law beneath: across 80 valid-anchor runs the anchor fires at 0.843 of time-to-emergence -- t_event ~= 1.19 x t_anchor -- and this multiplicative rule passed its own blind gate (5/5) at a third unseen configuration. False alarms are certified against 33 manufactured negatives. The precursor leads across 3 public model families (Pythia, OLMo, OLMo-2; 7 suites), with OLMo-2 at 1B tokens showing precursor formed, capability absent. Four pre-registered kill criteria fired and are reported. Every freeze precedes its data in a public commit chain.

---

### One Axis, No Brake: Self-Knowledge Limits the Filtering of Harmful Peer Conformity in LLMs

Authors: Yibo Hu
Published: 2026-07-17
Categories: cs.LG, cs.CL, cs.MA
arXiv: https://arxiv.org/abs/2609.18998v1

Multi-agent LLM systems are expected to be more reliable because agents can catch each other's mistakes. But peer pressure cuts both ways: the same correction that fixes a wrong answer can overturn a right one. The tempting safeguard is a brake that keeps the beneficial revisions and blocks the harmful ones. We show this brake is hard to build, for a simple reason: a revision is harmful exactly when the original answer was right, so deciding whether to block it is the same as knowing whether the model was already correct. This turns the open-ended hunt for a brake into one measurable quantity, the model's self-knowledge: any brake built from a deploy-time signal is a correctness probe in disguise, and self-knowledge is far from perfect (AUROC $\approx 0.64$--$0.89$ across six model families). We call this ceiling the wall. Even white-box steering of the model's own correctness direction does not breach it: it changes how often the model revises, but harmful and beneficial revisions move together. At population scale the wall becomes the cliff: when most agents start wrong, debate amplifies the shared mistake into a confident, wrong consensus. In our multiple-choice societies, more agents, more model diversity, and a stronger member do not fix it. What helps is adding information before the revision, not filtering after it. Local agreement is not global correctness.

---

### Compiled Agency: Coding Agents as Game AI Researchers -- from a Roguelike to StarCraft II and Civilization

Authors: Haonan Huang, Joey Xiao
Published: 2026-07-17
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2609.18996v2

Coding agents are increasingly capable of sustained engineering and empirical research. Greater autonomy makes their research decisions themselves a target for evaluation: what to investigate, which experiments to run, and when to stop. We introduce Gauntlet, a develop-freeze-evaluate protocol for studying these decisions as agents build standalone game-playing programs. Starting from a game description, a raw observation/action interface, and an empty policy file, an off-the-shelf agent develops a controller from bare interaction in one autonomous session. We call the capability under study compiled agency: the shipped program plays with zero model calls. The capability is real and advancing: environment access adds 10 to 78 percentage points of held-out success over construction-only controls, and progress across model generations comes in steps, with tiers that defeat one generation entirely falling to the next. The protocol yields StarCraft II controllers that defeat every fair built-in AI, and in the newest generation the strongest cheating tier as well, and Civilization controllers that win complete games by conquest. Replaying more than 5,000 frozen versions exposes the research behind the programs: gains that plateau early; rigorous local investigation beside sparse validation of what actually ships; and stops that follow a race between the agent's own evidence and a model-specific transcript budget it was never given. When validation panels are refreshed mid-session, so that only the evidence changes, shipped success rises 12.4 points in nine of nine completed pairs of twelve initiated. The experiments an agent designs are part of the capability it delivers; Gauntlet makes them measurable and improvable--a step toward agents whose research practice, not just whose code, can be engineered. We release the benchmark, the corpus, and the replay tooling.

---

### A Benchmark Suite and Ground-Truth Methodology for Formal Verification of IEC 61131-3 Ladder Diagram Programs

Authors: Pierre Dantas, Lucas Cordeiro, Waldir Junior
Published: 2026-07-17
Categories: cs.CL, cs.AR, cs.SE
arXiv: https://arxiv.org/abs/2609.18994v1

We present the first benchmark suite for formal verification of Programmable Logic Controller (PLC) programs that combines controlled ground truth with coverage of both textual (Structured Text, ST) and graphical (Ladder Diagram, LD) IEC 61131-3 encodings. Despite growing support for tools, the field lacks standard evaluation benchmarks: existing corpora omit formal properties or graphical dialects, and private program sets preclude reproducible measurement of progress. Our suite comprises 50 programs in 83 variants across ten industrial domains, provided in PLCopen Extensible Markup Language (XML) and ST, each paired with a formal property, machine-checkable expected verdict, and violation witness in the Software Verification Competition (SV-COMP) format. The central methodological contribution is a tripartite ground-truth discipline - verdicts are established by construction, fault injection, or audited cross-tool consensus - motivated by a concrete failure mode where the obvious safety property misclassifies all attacks from two public logic-bomb corpora as safe due to invisible non-termination. Reference verdicts are obtained with the Efficient SMT-Based Context-Bounded Model Checker (ESBMC) v8.4 from source: all 25 graphical benchmarks execute, and 43 of 45 accepted variants match recorded verdicts. On the finite-state fragment (21 benchmarks), nuXmv - a model checker with unrelated decision procedures - agrees on all 24 interlock variants and resolves two benchmarks ESBMC-PLC leaves unknown, confirming tool-neutral ground truth and discriminative power. Porting exposes format and semantics fragmentation: front-ends accept different serializations, and timer semantics vary across tools - phenomena the suite is designed to reveal. The corpus, schema, validator, and recheck harness are released as open artifacts.

---

### Lost in Perception: Isolating Perceptual and Reasoning Failures in Multimodal Physics and Geometry Reasoning

Authors: Raj Jaiswal, Sree Krishna Uppalapati, Dhruvkumar Patel, Ria Khatoniar, Tanuja Ganu, Rajiv Ratn Shah
Published: 2026-07-17
Categories: cs.AI
arXiv: https://arxiv.org/abs/2609.18991v1

Multimodal LLMs report strong performance on scientific reasoning benchmarks, yet most treat perception and reasoning as a single measurable process. We introduce a five-task diagnostic experiment across physics and geometry benchmarks that isolates failures to perception, reasoning, or both. Incorrect diagram interpretation degrades performance even on problems models solve correctly from text alone, and accuracy generally rises from raw images to human-authored captions. Recovery under corrected captions is high for some models, separating perception-blocked failures from genuine reasoning bottlenecks. Which reasoning error follows a perception failure depends on domain: physics failures resolve into calculation errors, geometry into conceptual misapplication. As a discussion beyond our core experiments, InternS1-mini, despite heavy scientific pretraining and thinking capabilities, falls below the weakest model from experiments on every task, with reasoning traces frequently truncating before completion.

---

### Suppressed, Not Erased: A Representational Trace of Edited Facts Survives Even Weight-Free Knowledge Editing

Authors: Priyansh Srivastava, Romit Chatterjee
Published: 2026-07-17
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2609.18985v1

Knowledge-editing benchmarks certify local correctness, whether an edited model produces the new fact on near-edit prompts but not how much of the original fact remains decodable inside the model. We study residual knowledge directly with a linear trace probe: after editing a fact, we ask whether the original object is still recoverable from the model's hidden states. On GPT-2-XL, across three mechanistically distinct editors applied to 50 CounterFact edits, the original object remains linearly decodable well above chance after a successful edit (probe accuracy 0.96 for ROME, 0.86 for constrained fine-tuning, and 0.79 for the memory-based editor GRACE, against a chance level of 0.50; all edits reach 100% generation-based success). The GRACE result is the most informative: GRACE changes zero base-model weights, overriding the fact through an external memory, yet the original object is still decodable from the underlying network, so the residual trace cannot be attributed to an incomplete weight update. We read this as evidence that editing, even when behaviorally successful, suppresses rather than erases the original association in representational space. We also report a relearning-savings instrument that did not behave reliably in our setting and discuss why; we treat it as a negative methodological result rather than evidence. Code and data are released.

---

### Flexible-Region Based Adaptive In-Loop Filter for Video Coding

Authors: Xuewei Meng, Chuanmin Jia, Jing Cui, Shanshe Wang, Siwei Ma
Published: 2026-07-17
Categories: eess.IV, cs.CV, cs.MM
arXiv: https://arxiv.org/abs/2609.18983v2

Adaptive loop filter (ALF) for video coding, which is designed to minimize the mean square error between original and reconstructed samples by using Wiener-based filter, has attracted increasing attention for its significant capability in improving coding efficiency. In the second and third Audio Video Coding Standard, i.e., AVS2 and AVS3, ALF is adopted as one of the in-loop filters. In current design, each frame is divided into 16 regions at most and corresponding filter coefficients are then derived and utilized to reconstruct each region. In this paper, a flexible-region based ALF (FRALF) scheme is proposed to improve the adaptability of existing ALF in AVS3, which introduces multiple region partition templates, such as $2\times4$, $4\times4$, $4\times8$ and $8\times8$. We subsequently propose the filter coefficients merging algorithm to further improve coding efficiency by estimating the distortion level of different partition regions. The proposed FRALF can fully consider the local texture characteristics as well as non-local similarities synthetically. The experimental results show that FRALF outperforms the existing region-based ALF in AVS3 with relatively low complexity increasing.

---

### The Limits of BPE Tokenization in Polish: Segmentation-Flexional Forms, Grammatical Anchoring, and First-Person Stability in Inflectional Language Models

Authors: Elzbieta Dawidek
Published: 2026-07-17
Categories: cs.CL
arXiv: https://arxiv.org/abs/2609.17553v1

This article analyzes BPE tokenization in Polish as a test case for the limits of statistical segmentation in an inflectional language. It asks whether frequency-based tokenization preserves linguistically relevant units, including orthographic form, phonemic and syllabic segmentation, derivational structure, inflectional endings, grammatical form, and the speaking subject. The material includes diagnostic words, a children's text, selected forms from the Preamble to the Constitution of the Republic of Poland, word-family tests, and examples with Polish diacritics and nasal vowels. BPE tokenizers may produce segments that coincide with syllabic or morphologically interpretable divisions, but remain dependent on the frequency of written forms. They do not systematically map orthographic representation onto phonemic structure or context-dependent phonetic realization. The results show that BPE stabilizes frequent surface fragments of grammatical exponents rather than grammatical categories themselves. A form such as ustanawiamy is not merely a sequence ending in -y, but a verbal form anchored in conjugation, person, number, tense, mood, and aspect. The article develops the concept of grammatical form anchoring. In Polish, forms such as poszlam, zrobilam, or bylam can establish the position of the speaking subject without an explicit pronoun. In interaction with AI, this exposes a further problem: a language model does not possess a stable grammatical "I", but reconstructs it contextually and may mirror the user's forms or shift grammatical gender. Roclawski's segmentation-flexional forms are proposed as a diagnostic framework for evaluating tokenization boundaries. More stable modeling of Polish may require sublexical stabilization, anchoring grammatical form in the inflectional system, representing sentence patterns and verbal valency, and maintaining the grammatical "I" in dialogue.

---

### Beyond Right and Wrong: Evaluating Second-order Social Reasoning in Large Language Models

Authors: Sunny Rai, Jinyi Kuang, Reyhan Jamalova, Annie Lou, Cristina Bicchieri, Niyati Malhotra, Victor Hugo Orozco-Olvera, Ana Maria Munoz-Boudet, Lyle H Ungar, Sharath C Guntuku
Published: 2026-07-17
Categories: cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2609.05437v1

Previous AI alignment efforts have focused primarily on first-order social norms -- teaching models what is socially acceptable or unacceptable (e.g., `do not steal'). However, social intelligence depends not only on norm recognition, but also on anticipating who will enforce it and how (e.g., public shame or even imprisonment). These second-order expectations, known as metanorms, govern how people respond when social rules are broken. We introduce a novel framework for evaluating metanorm reasoning in Large Language Models (LLMs) along two dimensions: emotional appraisal and behavioral response, and propose new classification tasks, namely, predicting self-regulation in violators, and other-regulation in observers. We release a multi-perspective dataset, NormReact, of 450 norm violation scenarios, hand-annotated for emotions and behavioral responses across norm violators' gender and observers' social closeness. Current LLMs portray a harsher social world: across six models, they overpredict negative sanctions where humans would expect inaction, and alignment with human judgments deteriorates as social distance increases. These findings suggest that AI systems in norm-sensitive domains from conflict mediation to policy simulation, may risk producing a distorted picture of social regulation: one that over-represents punishment and under-represents the tolerance, restraint, and relational calibration that characterize actual norm enforcement in real world.

---

### Removable and Irreducible: A Token-Cost Ledger for the Multilingual Tokenization Tax

Authors: Madhulatha Mandarapu, Sandeep Kunkunuru
Published: 2026-07-17
Categories: cs.CL
arXiv: https://arxiv.org/abs/2609.00378v1

Large language models pay a well-documented tax on non-English text: the same content costs several times more tokens, and because attention is quadratic in sequence length, far more compute. We ask how much of this tax is removable. Framing the token layer as source coding -- transformer compute is monotone in sequence length, whose per-atom floor is the Shannon rate $H/\log_2 V$, an object already applied to tokenizers in prior work -- we assemble a token-cost ledger that splits each language's cost, at fixed parallel content, into a removable coding redundancy, a residual coding slack, an intrinsic-content term, and an orthogonal, irreducible grapheme-to-phoneme term that governs the multimodal rather than the text cost. On FLORES-200 across eight languages, a production tokenizer costs up to $8.9\times$ more tokens for Indic scripts than for English; a script-matched code trained on $1,012$ sentences removes a median $64\%$ of that excess (bootstrap 95\% CI $(0.638, 0.647)$), and a script-fair information floor shows the intrinsic content differs by under $6\%$ -- the tax is representational, not informational. A constructed code removes $98\%$ of a controlled source's redundancy, and the token tax implies up to $79\times$ attention cost. We are explicit about scope and failure: this is compute-and-memory accounting, not a model-quality claim; we neither measure nor claim the cross-lingual direction of the orthographic term; and our matched code is a conservative small-data demonstration. We contribute the unifying ledger, the removable-versus-intrinsic attribution, and an open one-command harness.

---

### Dynamic Influence-Weighted Distillation for Single-IMU Activity Recognition

Authors: Bingxuan Xie
Published: 2026-07-17
Categories: cs.LG, cs.HC
arXiv: https://arxiv.org/abs/2608.24904v1

Inertial sensors at multiple body locations can improve activity recognition, but requiring every sensor at inference increases the deployment burden. We study whether four synchronized IMUs available during training can improve a student that uses only the right-arm IMU during fitting and inference. A frozen four-IMU teacher provides logit and feature targets. Fixed-weight knowledge distillation applies each target with the same strength to every fitting sample, although the student may not benefit equally from them. We introduce dynamic influence weighting (DIW), which tests a one-step candidate update on separate fold-internal training participants. DIW then assigns separate sample-wise gates to the logit and feature losses. On WEAR, we evaluate 19 labels and 68,298 complete windows from 22 participants using subject-disjoint five-fold cross-validation. Pooled out-of-fold macro-F1 is 0.561820 for Supervised and 0.571623 for Fixed-weight KD. DIW reaches 0.638451, gains of 7.66 and 6.68 percentage points, respectively. It exceeds Supervised for 18 of 19 labels and 21 of 22 held-out participants. All three routes retain the same 80,915-parameter right-arm student at inference. Under this protocol, DIW converts training-only multi-position information into a stronger single-IMU model without changing deployed sensing or the student forward graph.

---

### A Social Media Analysis of Discourse on the Israel--Palestine Conflict on Telegram

Authors: Michail Zafeiropoulos, Despoina Antonakaki, Sotiris Ioannidis
Published: 2026-07-17
Categories: cs.CL, cs.AI, cs.CY, cs.SI
arXiv: https://arxiv.org/abs/2608.21385v1

Social media has become a central arena in which armed conflicts are contested, yet the pro-Israel and pro-Palestine communities on Telegram, whose broadcast architecture yields an unusually direct record of deliberate political communication, have not been systematically compared at scale. This study presents a multi-method computational analysis of 87,617 messages from sixteen Telegram channels, eight pro-Israel and eight pro-Palestine, spanning May 2021 to June 2026 and covering multiple conflict escalations. It combines sentiment analysis, three stance detection methods drawn from distinct paradigms (keyword matching, zero-shot DeBERTa via natural language inference, and a fine-tuned BERTweet model), and a framing analysis, all evaluated against 736 manually annotated messages. The fine-tuned model performed best (72.1% accuracy, 0.721 macro F1 under 5-fold cross-validation), outperforming both label-free baselines by 8 to 11 points; the baselines stalled in the low-to-mid 60s, indicating a hard ceiling for stance detection not adapted to in-domain language. The central finding emerges only when sentiment, stance, and framing are read together: the two communities deploy the same death- and victim-related vocabulary in opposite emotional registers, pro-Israel channels predominantly neutral and report-style, pro-Palestine channels markedly more negative, consistent with writing from the distinct discourse positions of acting party and affected party.

---

### Beyond Two Bytes per Letter: Tokenization Overhead in Cyrillic AI Systems

Authors: Ivan Dobrovolskyi
Published: 2026-07-17
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2608.21384v1

Modern multilingual tokenizers often fragment Ukrainian and other underrepresented Cyrillic-script languages more heavily than English, creating disparities in cost and context capacity. We quantify this overhead across nine production tokenizers and five languages with standardized Cyrillic and Latin representations, covering 8.37 million word forms. On a corpus benchmark, Ukrainian shows 68-121% token overhead on modern tokenizers and 220% on the older cl100k, measured through full-text fertility on the BrUK and Brown corpora. Overhead is negatively associated with Cyrillic vocabulary allocation in the subset with independently verified English baselines, although the association is not statistically significant (Spearman rho = -0.536, p = 0.215, n = 7). We evaluate two mitigation strategies. LLMLingua-2 reduces Ukrainian input length by 47-49% on an e-commerce RAG benchmark of 1,536 products and 145 queries, with no compression-induced value losses among 80 retrievable cases. A balanced byte-level BPE tokenizer trained with a 200K vocabulary cap, converging at 158,184 actual entries, reduces the held-out UK/EN ratio from 2.22x to 1.30x. Romanization increases Ukrainian token counts by 2-19% on most tokenizers. Across the five languages, tokenization efficiency favors the script more prevalent in web data. These findings indicate that training data allocation contributes to Cyrillic tokenization overhead and that mitigation is possible at both inference and tokenizer-design stages.

---

### Determinants of Starting Salaries for Filipino Graduates: An Explainable Machine Learning Approach

Authors: Alexander Gabriel A. Aranes, John Michael C. Magpantay, Reginald Neil C. Recario, Jamlech Iram N. Gojo Cruz, Rodolfo C. Camaclang
Published: 2026-07-17
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2608.21383v1

Filipino graduates face a persistent disconnect between educational preparation and labor market outcomes, where starting salary is a key signal of entry-level valuation. Current Philippine research is dominated by descriptive tracer studies that document employment rates but do not explain the determinants of pay. We address this gap using a crowd-sourced survey dataset of graduate responses whose noisy, self-reported nature makes it a challenging prediction target. Applying machine learning to this problem, we identify job role and industry as the dominant determinants of starting salary, significantly outweighing institutional prestige. The strength of this finding is its central contribution: it is corroborated by three independent lines of evidence, namely SHAP attributions, the heavy reliance of the best ensemble on occupational text, and a Natural Language Inference reformulation. These results suggest that career guidance and policy should prioritize sector-specific skills over institutional brand.

---

### There Is No Neutral Harness: Modern LLM Leaderboards Are Manufactured by Config-Fragile Items

Authors: V. S. Raghu Parupudi
Published: 2026-07-17
Categories: cs.AI
arXiv: https://arxiv.org/abs/2608.21382v1

Multiple-choice benchmarks fix the questions and the correct answers, but not the harness: the order of the options, the wording of the prompt, and whether a language model's answer is read from generated text or from per-option likelihoods. Work on this harness sensitivity reports it as aggregate score variance, leaving unexamined which items the variance falls on and whether they are the items that separate one model from the next. We treat the evaluation harness of large language models (LLMs) as an independent variable and resolve its effect to single items. We introduce the \textit{fragility grid}: 12 open-weight instruction-tuned LLMs from 4 families answer the same 3{,}679 items from 4 benchmarks (ARC, HellaSwag, MMLU, TruthfulQA) under 26 equally defensible harness configurations, recording one correctness bit for every model, item, and configuration. The comparison is matched, since the items, the weights, and the greedy decoding stay fixed while only the harness varies. Under the grid a model's score is a band rather than a point: gemma4-31b scores between 31 and 89 percent depending only on the harness. Three results follow. On the items that two adjacent models both answer stably the pair is tied, and config-fragile items carry 95.7 percent of a pair's gap on average. Four of the 12 models reach rank one under some configuration, so the harness selects the winner. Item discrimination, the property that benchmark-compression methods maximize, correlates with fragility at 0.28 (95 percent CI 0.25 to 0.30), so compression keeps the fragile items rather than removing them. The scoring choice, not the option order that protocols usually fix, is the load-bearing axis. We release the per-item records and the analysis script, from which every number regenerates on a CPU in seconds, and we position the fragility grid as a check a leaderboard can run before it reports an order.

---

### TAPR: Enhancing LLM Performance with a Task-Aware Prompt Rewriter

Authors: Oliver Savolainen, Emanuele Bastianelli, Hosein Azarbonyad
Published: 2026-07-17
Categories: cs.AI
arXiv: https://arxiv.org/abs/2607.28657v1

Large Language Models (LLMs) often require carefully crafted prompts to unlock their full potential, which can be a barrier for non-expert users. This work addresses the challenge by introducing a Task-Aware Prompt Rewriter (TAPR), a model that reformulates user prompts into task-optimized prompts with the explicit goal of improving downstream LLM performance. We train TAPR using reinforcement learning with Group Relative Policy Optimization (GRPO), where rewards are derived from LLM-as-judge evaluations of both the reformulated prompt and the corresponding task output. Experimental results on diverse tasks, such as question answering, summarization, and arithmetic reasoning, show that our method yields consistent gains over base models in prompt rewriting ability. Fine-tuning Phi-4-mini-instruct (as the base model for TAPR) produces prompts that contain clearer and more instructive language, leading to higher accuracy on established benchmarks such as Natural Questions and GSM8K. Our code is available at: https://github.com/OliverSavolainen/task-specific-prompt-rewriter

---

### AVE-Compass: Towards Holistic Evaluation for Audio-Video Editing Abilities

Authors: Yuqing Wen, Yukai Huang, Qianqian Xie, Jiangtao Wu, Yibin Lin, Yikai Gu, Jialu Chen, Yuanxing Zhang, Jiaheng Liu
Published: 2026-07-17
Categories: cs.MM, cs.CV, cs.SD
arXiv: https://arxiv.org/abs/2607.24821v1

While instruction-based video editing has advanced rapidly, real-world videos contain tightly coupled audio and visual signals, and editing one modality often requires coordinated changes in the other. Existing benchmarks primarily evaluate visual transformations on silent clips or isolated audio editing, leaving complex audio-visual editing and cross-modal consistency underexplored. We introduce AVE-Compass, a comprehensive benchmark with 145 curated source videos, 196 audio-visually coupled editing instructions, and 2,688 fine-grained checklist items. It evaluates Instruction Following, Fidelity Preserving, Realism, and Editing Intent through checklist-based MLLM judging and a dedicated realism rubric, complemented by automated cross-modal, video, and audio metrics. Extensive evaluation shows that state-of-the-art models still struggle to execute cross-modal instructions while preserving non-target content. We further propose AVE-Agent, a modular agent framework that decomposes complex instructions into dependent subtasks and iteratively improves editing results through self-reflection and evaluator feedback. AVE-Agent improves instruction execution, Fidelity Preserving, and audio-visual alignment in joint editing while maintaining competitive perceptual quality.

---

### Dynamic Multi-Criteria Bottleneck Severity Index (DMBSI) for Semiconductor Wafer Manufacturing: A Genetically Optimised Framework for Reentrant Production Systems

Authors: Mohammad Sharifur Rahman, Karl McCreadie, Saugat Bhattacharyya, M M Manjurul Islam, Cormac McAteer, Bryan John Baker, Nuala Parker, Girijesh Prasad
Published: 2026-07-17
Categories: eess.SP, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2607.24819v1

Wafer fabrication exhibits unique characteristics, including reentrant process flows, variable bottlenecks, and highly variable process conditions. In order to identify the most severe bottleneck at each moment in time for semiconductor wafer fabrication, this research presents the Dynamic Multi-Criteria Bottleneck Severity Index (DMBSI), a new, data-driven methodology for analysing multiple diagnostic signals of cycle time to changes in process parameters, and the impact of reworks on cycle time in order to generate an interpretable, unified measure of bottleneck severity. The experimental validation of DMBSI was conducted using Manufacturing Execution System (MES) logs collected from 22 wafer production lots at a commercial 200 mm wafer fabrication line operated by Seagate Technology. Using 5-fold cross-validation, the GA-optimised DMBSI achieves a Pearson correlation of r = 0.80 with observed cycle-time contributions, representing an 8.1% improvement over the expert heuristic baseline (r = 0.74) and substantially outperforming the Theory of Constraints (TOC; r = 0.60) and Value Stream Mapping (VSM; r = -0.30). Furthermore, the unique time-windowed component of DMBSI enabled the identification of temporal bottleneck migration patterns, which shifted from the dominant constraints associated with dielectric deposition steps in the early production windows to those associated with over- and under-inspection in the later production windows. The integrated what-if counterfactual analysis demonstrated that a 50% reduction in waiting time at the top-ranked bottleneck step would reduce the mean cycle time by 7.2%, with the top five bottleneck steps offering a combined potential reduction of approximately 19%.

---

### Dual-Level Atomic and Coordination Geometry Learning for Crystal Property Prediction Using Graph Neural Networks

Authors: Sanjay Chakraborty
Published: 2026-07-17
Categories: cs.IR, cond-mat.mtrl-sci, cs.AI, cs.CE
arXiv: https://arxiv.org/abs/2607.24818v1

Accurate prediction of crystal properties remains a key challenge in computational materials science. While graph neural networks (GNNs) such as CGCNN, MEGNet, ALIGNN, and SchNet have shown strong performance, they primarily represent crystals at the atomic level and implicitly learn local chemical environments through message passing. However, many material properties are governed by coordination polyhedra, the fundamental structural units formed by atoms and their neighboring atoms. To address this limitation, we propose the Coordination Polyhedron Graph Network (CPGN), a multi-scale GNN that jointly learns atomic, bond, and coordination-polyhedron representations. CPGN constructs three coupled graphs: an atom graph encoding elemental and bonding information, a line graph capturing angular interactions, and a coordination polyhedron graph describing Voronoi-derived local environments through corner-, edge-, and face-sharing relationships. Physically meaningful geometric descriptors are incorporated for each polyhedron, while an interleaved message-passing mechanism with bidirectional cross-attention enables effective information exchange across structural levels. Extensive evaluations on the Materials Project, JARVIS-DFT, and QM9 benchmark datasets demonstrate that CPGN outperforms existing state-of-the-art GNN models. It achieves a formation-energy MAE of 0.060 eV/atom and a band-gap MAE of 0.292 eV on the Materials Project, while providing competitive multi-property prediction on JARVIS-DFT and superior HOMO prediction on QM9. The results highlight that explicit modeling of coordination polyhedra improves crystal representation learning and enables accurate, physically interpretable prediction of material properties.

---

### Retrieval-Augmented Generation in LLMs for Mental Health: Quantifying the Incremental Contribution of Retrieval Within a Layered Safety Architecture

Authors: Anand Gupta, Akshat Surolia, Shubham Mishra, Shakil Imtiaz, Chaitali Sinha
Published: 2026-07-17
Categories: cs.IR, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2607.24817v1

Digital mental health interventions (DMHIs) offer scalable support, but ensuring they accurately detect users' intent during volatile situations can be challenging. Pure parametric Large Language models (LLMs) do not contain specific safety critical architecture, and can miss critical cues, or hallucinate, undermining reliability. Retrieval Augmented Generation (RAG), which supplements an LLM with retrieved context, could enhance intent detection during volatile situations. Commercially available DMHIs typically combine multiple independent safety layers like rule-based filters, symbolic escalation protocols, and neural classification. The incremental contribution of any single layer, however, remains unquantified. This paper evaluates six LLM models within a DMHI called Wysa, via a controlled comparison of RAG-enabled versus RAG-disabled modes. Anonymized real and synthetic user-chatbot exchanges were annotated by a qualified clinical team against multi-class intent categories (e.g. self-harm, abuse, panic). The study computed classification accuracy, recall, precision and F1 scores against ground truth labels and tested differences for statistical significance. Performance was also examined by risk category and inter-model agreement. While RAG caused a rise in false alarms, the trade-off is consistent with safety-critical design principles that prioritize sensitivity, where flagged cases are routed to additional review rather than acted on directly. Overall, these findings support RAG as a promising approach to improve the accuracy, consistency and safety of LLM-driven DMHIs. Keywords: Digital Mental Health Intervention, Large Language Model, Retrieval Augmented Generation, Accuracy, Recall, Precision

---

### MegaSlide-DiT: Memory-Centric Adaptation and Deformable Local Attention for Efficient Video Diffusion

Authors: Jiacheng Liu, Jason Liu
Published: 2026-07-17
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2607.22696v1

High-resolution video diffusion models built on Diffusion Transformers (DiTs) deliver strong fidelity but quickly exhaust the memory budget of a single workstation. A 100 billion-plus parameter DiT easily requires over a terabyte of persistent state, while naive spatiotemporal self-attention grows quadratically in sequence length. These two walls -- parameter memory and activation memory -- prevent researchers from adapting massive generative models without large GPU clusters. We revisit this problem from a systems perspective and introduce MegaSlide-DiT, a prototype that demonstrates how a pre-trained 105B DiT can be adapted on a single H200 GPU with 1.5 TB of host RAM. Our key insight is that the GPU need not own the model state: all persistent weights, master weights and optimizer moments remain in host memory, while only transient shards are streamed to the GPU on demand. Simultaneously, we replace quadratic global attention with 3D Deformable Slide Attention (3D-DSA), a motion-adaptive local attention operator that reduces both memory and computational complexity to linear in the sequence length. We report detailed memory accounting, execution traces and evaluation results to substantiate our design. MegaSlide-DiT does not claim to train a 105B model from scratch on a single GPU, nor does it magically solve bandwidth limits; rather, it offers a pragmatic path for full-parameter adaptation of massive video diffusion models on high-end workstations.

---

### PANOPTICON: A PII-Based Assemblage of Naturalistic Output Tokens for Investigating Privacy Leakage Within LLM Context Window

Authors: Ryan Thornton, Mir Mehedi Ahsan Pritom, Maanak Gupta
Published: 2026-07-17
Categories: cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2607.22695v1

Large Language Models (LLMs) are capable of generalizing human language for the completion of never-before-seen tasks, leading to widespread deployment. While this automation provides clear utility, completing these tasks often requires the insertion of Personally Identifiable Information (PII), strings of information that uniquely identify some individual, raising privacy concerns. However, ethics has prevented the curation of a public, authentic dataset of PII. Without an appropriate dataset, it is difficult to quantify privacy risks. Thus, we introduce the PANOPTICON pipeline and dataset. The dataset, generated by Meta's Llama-3.1-8B-Instruct model, contains 67, 718 prompts, intended for the models context window, containing PII spans derived from 9,674 publicly available synthetic user profiles. We measure lexical diversity and S-BERT diversity of the created dataset to evaluate realism. Finally, we present a case study showcasing the utility of PANOPTICON data for understanding Prompt Inversion Attacks (PIAs). PANOPTICON thus emerges as the first benchmark dataset for studying PIAs over private corpora, providing a foundation for future LLM privacy research.

---

### Bayesian Repetition Penalty: A Principled Adjacent-Conditional Framework for Reversing Attention Collapse in Autoregressive Language Models

Authors: Wenjie Fan, Bin Ma, Dong Li
Published: 2026-07-17
Categories: cs.AI
arXiv: https://arxiv.org/abs/2607.22694v1

Attention collapse in autoregressive language models -- manifested as repetitive token loops where the model becomes trapped in self-reinforcing attractors -- is a persistent pathology that existing decoding-time heuristics fail to address at its root cause. We present a principled framework that penalises or compensates anomalous confidence arising from collapsed generation patterns, by comparing a token's observed frequency against its corpus prior through an adjacent-conditional probability construction. The resulting self-normalising penalty ratio $R=f(m,n,p)/f(np,n,p)$ requires no ad hoc standardisation and admits a closed-form logit offset with zero approximation error. The correction is isolated from the loss gradient and accumulated into a frozen output-layer bias via exponential moving average, enabling deployment as a repair mechanism for models that have already collapsed without requiring intrusive modifications to standard training pipelines. Experimental validation on a 1.5B-parameter model demonstrates that the frozen-bias mechanism can rescue a model already trapped in a collapsed attractor, reducing 2-gram repetition from 0.073 to near 0 while preserving generation quality.

---

### Risk Governance for Generative AI Mental Health Support: A Multi-Turn Safety Architecture

Authors: Anabela C. Areias, Catarina Botelho, António Farinhas, Areti Vassilopoulos, Dora Janela, Xin Tong, Nuno M. Guerreiro, Maya D'Eon, Fabíola Costa, Ricardo Rei
Published: 2026-07-17
Categories: cs.AI
arXiv: https://arxiv.org/abs/2607.22692v1

Large language models (LLMs) are increasingly used for emotional support despite lacking mechanisms to safely govern evolving mental health risk. Existing safety approaches primarily detect risk but rarely shape how models respond as conversational risk unfolds. We developed a model-agnostic safety governance architecture that combines contextual risk detection, reasoning-based verification, and protocol-guided response generation for multi-turn mental health interactions. Synthetic conversations grounded in real-world mental health narratives were used to evaluate the architecture's performance, tested with GPT-5-chat and Qwen3.5-27B, achieving high risk detection performance (specificity: 0.85 (95\%CI: 0.78;0.91), sensitivity: 0.92 (95\%CI: 0.88;0.95)) and increasing clinician-preferred escalation responses by 25.6--59.2pp while preserving rapport and connection. Performance remained stable across conversation length and generalized across both proprietary and open-source models. These findings demonstrate that clinically-grounded safety governance can extend beyond risk detection to improve how LLMs manage evolving mental health risk, providing a scalable framework for safer deployment across models.

---

### HiLLTS: Zero-Shot Hierarchical LLM-Guided Traffic Signal Control for Sustainable Transportation

Authors: Yue Ding, Tendai Mukande, Mingming Liu
Published: 2026-07-17
Categories: cs.AI
arXiv: https://arxiv.org/abs/2607.22691v1

Urban traffic congestion significantly increases fuel consumption, greenhouse gas emissions, and commuter delays, resulting in substantial economic losses and environmental harm in modern cities. Traditional traffic signal control strategies such as fixed-time scheduling, actuated control, and reinforcement learning (RL)-based methods, offer different degrees of adaptability; however, RL-based methods can require extensive retraining, careful reward design, and substantial simulation data when transferred across networks or demand regimes. To address these challenges, we propose HiLLTS, an LLM-guided traffic signal control framework that employs a hierarchical three-layer architecture consisting of a central coordination agent, a district layer and multiple cluster-level intersection agents. Experimental results demonstrate consistent improvements in both congestion and environmental performance. Compared with the strongest non-LLM baseline in each scenario, HiLLTS reduces average waiting time by 36.73% under the low-congestion scenario and 14.71% under the high-congestion scenario, while reducing average CO2 emissions by 7.87% and 8.57%, respectively. Larger gains are observed against weaker baselines: under low congestion, HiLLTS achieves reductions of up to 18.00% in emissions and 62.07% in waiting time relative to Fixed-Time control; under high congestion, reductions of up to 28.89% in emissions and 40.36% in waiting time are observed relative to Max Pressure. The ablation study further validates the contribution of LLM-guided coordination over rule-based control

---

### LazyMem: Retrieve Broadly, Construct Selectively for Efficient Long-Term Agent Memory

Authors: Jing Yu, Yibo Zhao, Jiaming Zhang, Xiang Li
Published: 2026-07-17
Categories: cs.AI
arXiv: https://arxiv.org/abs/2607.22690v2

Long-term memory enables LLM agents to leverage past interactions, but dialogue histories quickly exceed the context window, forcing agents to retrieve relevant subsets at query time. Because useful evidence is sparse and scattered across verbose conversations, retrieval faces a fundamental tension: broadening recall improves coverage but floods downstream reasoning with noise, while compressing memories at write time eases retrieval but irreversibly discards details that future queries may need. We introduce LazyMem, which resolves this tension by deferring all memory construction to query time. Given a retrieved candidate pool, a lightweight model processes it in overlapping parallel windows, selectively retaining and compressing only query-relevant content. The model is trained with supervised fine-tuning followed by reinforcement learning, using a reward that jointly encourages the identification of relevant messages and the generation of compressions that are faithful to the source and useful for answering the query. On LongMemEval, LazyMem-4B achieves an LLM-judge accuracy of 0.85, outperforming the strongest non-oracle baseline while using only 213 answer-context memory tokens, 21.0 times fewer than the baseline. It further generalizes to LoCoMo without target-domain training and reduces mean latency relative to the prior query-time baseline. Code is available at https://github.com/allacnobug/LazyMem.

---

### Beyond Sequential Interaction: Benchmarking Parallel Execution and Coordination for GUI Agents

Authors: Zedong Yu, Qianxing Li, Zhi Gao, Liuyu Xiang, Chenrui Shi, Yang Liu, Huiming Wu, Yujie Wei, Yuhao Fei, Yubo Fu, Zhaofeng He
Published: 2026-07-17
Categories: cs.AI
arXiv: https://arxiv.org/abs/2607.22689v1

Graphical user interface (GUI) agents are systems powered by large multimodal models (LMMs). They perceive screen state and execute user instructions through GUI actions such as clicking, typing, and scrolling on desktops and mobile devices. However, current agents scale poorly to long-horizon tasks: actions incur costly LMM inferences, and performance degrades as context grows. Humans divide such workloads among collaborators who complete sub-tasks in parallel. Yet parallel coordination among GUI agents has received little attention. To close this gap, we introduce ParaGUIBench, to our knowledge, the first benchmark dedicated to parallel execution and coordination of multiple GUI agents on separate desktop instances. It consists of three components: a multi-device Docker infrastructure with a shared file system; a dataset of 233 tasks spanning six task categories; and an evaluation system with efficiency metrics, including step reduction ratio and token cost. We further introduce ParaGUI, a planner-worker agent that decomposes GUI tasks and dispatches sub-tasks to concurrent workers on separate desktop instances. On ParaGUIBench, ParaGUI reaches a 46.4% success rate, outperforming the strongest serial baseline (Claude Sonnet 4.6) by 12.9 points while using roughly half the steps and less than half the tokens. These results show that parallel execution can improve both success rate and efficiency on decomposable, long-horizon GUI tasks, pointing to a direction worth further study.

---

### Co-Harness: Co-Evolving Harnesses and Model Weights for LLM Agents

Authors: Zhengyu Chen, Teng Xiao, Huaisheng Zhu, Yige Yuan, Luan Zhang, Jingang Wang
Published: 2026-07-17
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2607.22688v1

Post-training agents for automated AI research requires optimizing not only model parameters, but also the runtime harness that shapes how research trajectories are generated, evaluated, and learned from. Existing pipelines typically train models under a fixed harness, including prompts, tools, skills, middleware, and memory, while leaving the data-generating process outside the optimization objective. This creates a mismatch between model updates and the static scaffolding that determines trajectory quality. We introduce Co-Harness, a framework that jointly optimizes the agent harness and model parameters during post-training. Co-Harness alternates between harness optimization and model optimization. An LLM-based HarnessCritic analyzes failed trajectories, identifies harness-level failure modes, and proposes validated local updates. The model is then fine-tuned on high-quality trajectories generated by the improved harness, distilling effective scaffolding into model parameters. A 200+ hour autonomous case study further shows that Co-Harness can recover from system crashes, improve inference efficiency, and discover ensemble strategies without human intervention. These results suggest that joint harness and model optimization is an effective way to improve agents beyond fixed-harness post-training.

---

### Chronofy: A Temporal-Logical Decay Architecture for Information Validity in Time-Aware Retrieval-Augmented Generation

Authors: Muntaser Syed, Marius Silaghi, Sheikh Abujar, Sharun Akter
Published: 2026-07-17
Categories: cs.LG
arXiv: https://arxiv.org/abs/2607.20560v1

Retrieval-Augmented Generation (RAG) systems retrieve and integrate external knowledge to ground large language model (LLM) outputs. However, current RAG architectures treat all retrieved facts as equally valid regardless of temporal provenance, leading to temporal hallucination, where plausible but obsolete facts corrupt the output. A clinical lab reading from yesterday is actionable; the same reading from six months ago is noise. We present Chronofy, a three-layer neuro-symbolic framework implementing the Temporal-Logical Decay Architecture (TLDA) that embeds temporal validity directly into the representation, retrieval, and reasoning layers of RAG systems. Layer 1 reserves a dedicated temporal subspace within Matryoshka embeddings to make fact age structurally irremovable from the representation. Layer 2 integrates learnable exponential decay functions into graph-based retrieval, where the decay coefficient $β_j$ is grounded in Bayesian decision theory as an approximation of twice the latent process mean-reversion rate. Layer 3 applies Signal Temporal Logic (STL) robustness functions to evaluate the temporal validity of retrieved knowledge, not LLM output confidence, and enforces the possibilistic weakest-link principle to bound output confidence by the most decayed evidence in the reasoning chain. We evaluate Chronofy on temporal knowledge graph forecasting benchmarks, the TimE temporal QA benchmark, and a domain-specific sensitivity analysis, demonstrating that explicit temporal decay modeling improves retrieval precision, reduces temporal hallucination, and enables principled data re-acquisition triggers when temporal context is insufficient.

---

### Joint Utilization of Geospatial and census proxies for Autoencoder-Assisted Downscaling (JUGAAD) of socioeconomic indicators in India

Authors: Aditya Dutt, Paul Gader, Aditya Singh
Published: 2026-07-17
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2607.20559v1

Monitoring poverty and food security indicators is imperative for addressing socioeconomic challenges in developing nations. A limitation is mismatches in scale between data sources: census data provide geographic coverage, while socioeconomic indicators are derived from infrequently conducted surveys at coarse resolutions, posing a methodological challenge. This study introduces a deep learning framework, JuGAAD, using Indian census and survey data from 2001 and 2011 as a case study. We employ a three-step process: census and geospatial data are averaged into intermediate village-cluster-scale tessellations to reduce noise and regularize administrative boundary changes; an autoencoder compresses high-dimensional National Sample Survey Office (NSSO) data into a low-dimensional latent representation; and a regression model maps upscaled census and geospatial data to this representation. This function is applied to fine-grained census data to generate high-resolution predictions, validated against ground-truth district-level NSSO indicators. Results confirm the methodology predicts socioeconomic indicators at fine scales with strong accuracy.

---

### StabilityBench: Benchmarking Instability in LLMs

Authors: Emma Kondrup, Zachary Yang, Anne Imouza, Reihaneh Rabbany
Published: 2026-07-17
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2607.20558v1

AI Assistants are increasingly deployed in high-stakes settings, such as healthcare or government services. Yet their real-world behavior remains poorly understood due to strong context dependence. Current evaluation protocols follow a defense-in-depth paradigm with compounding layers of safeguards, ranging from traditional benchmarks to live or adversarial testing. Such benchmarks remain largely static and single-turn, limiting their ability to capture real-world variability in conversational settings. We propose StabilityBench, a principled, general and model-agnostic benchmark operator that transforms single-turn benchmark queries into multi-turn interaction histories. StabilityBench augments existing benchmarks by injecting realistic user simulations, through demographic proxies or sycophantic baits, while preserving original task intent. We apply StabilityBench to four benchmarks spanning mathematical reasoning, health question-answering and safety, and evaluate nine large language models under these conditions. Our results show that model performance is consistently unstable under these injections, with considerable performance degradations on three out of four benchmarks studied. These highlight important limitations of static evaluations and motivate more realistic evaluation settings. To this end, we propose StabilityBench-Mini: a size-preserving variant of StabilityBench that samples across diversification axes, enabling more realistic evaluation without increasing costs.

---

### Monkey King Bang: A Unified Scientific Multimodal Foundation Model

Authors: Hesen Chen, Xinyu Su, Xiaomeng Yang, Yuetan Lin, Zixiong Yang, Junyi An, Fenglei Cao, Yifeng Jiao, Yunqi Zhang, Yuan Cheng, Zhiyu Tan, Hao Li et al.
Published: 2026-07-17
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2607.20557v1

Scientific discovery is increasingly shifting from isolated disciplines to multi-domain reasoning, and AI for science faces a similar transition. Existing systems are either specialised for individual domains or unify scientific data mainly through text tokenisation and prompt-based interfaces, limiting their ability to handle diverse scientific inputs, produce modality-native outputs, and support joint understanding, reasoning, and generation across scientific domains. We introduce MKB, a unified scientific multimodal model for both understanding and generation, built around a shared Transformer backbone and modality-tailored encoders, adapters, and decoders. MKB covers six scientific branches, including DNA, RNA, proteins, small molecules, earth science, and medical images, and supports native outputs such as biological sequences, molecular strings, meteorological fields, and segmentation masks. Training follows a two-stage modality-then-language curriculum: Stage 1 aligns modality-specific components with the frozen backbone, and Stage 2 consolidates them with the language backbone using mixed scientific and general corpora. Experiments show that MKB achieves competitive scientific understanding across biological and molecular benchmarks, produces high-fidelity native outputs for weather forecasting, biological generation, and medical-image segmentation, and largely retains the general capabilities of its Qwen3-VL backbone. These results demonstrate the feasibility of the proposed paradigm, suggesting that shared-backbone models with modality-tailored components can provide a promising foundation for future cross-domain scientific multimodal exploration. The model and code are publicly available at https://github.com/Shanghai-Academy-of-AI-For-Science/MKB and https://huggingface.co/sais-org/MKB.

---

### KeySI: An Interaction Framework for Tuning Text Embeddings Based on Human Feedback

Authors: Yan Zhu, Y. Chen, Rebecca Faust
Published: 2026-07-17
Categories: cs.AI
arXiv: https://arxiv.org/abs/2607.20556v2

In large-scale text analysis tasks, pre-trained language models are often used to embed text corpora for downstream analysis. However, such models may struggle to capture domain-specific semantics and adapting them typically requires large amounts of labeled data and technical expertise to implement training pipelines. Recent approaches have demonstrated how visual interactions in document projections can capture human feedback as training signals for model tuning. However, these methods operate on document-level feedback, which requires users to open and assess individual documents in order to provide effective feedback. In this paper, we propose KeySI, an interaction framework that enables feature-level feedback through keyword-based concept specification. Users specify feedback by organizing extracted keywords into groups representing concepts, which KeySI translates into document-level supervision for subsequent tuning. By operating on keywords as the primary interaction medium, KeySI reduces the need for manual document inspection and labeling and lowers the barrier to adapting embedding models. We present a prototype implementation that, given a corpus, curates representative keywords, visualizes keywords and document embeddings via dimensionality reduction, allows interactive specification of keyword groups, and supports iterative refinement through system feedback. We evaluate KeySI through a user study, usage scenarios, and quantitative experiments demonstrating its effectiveness in capturing user intent and improving embedding alignment.

---

### Auditing Retrieval-Augmented LLM Hypotheses for Longitudinal Cell Painting Morphology

Authors: Gilchan Park, Guang Zhao, Byung-Jun Yoon, Shinjae Yoo
Published: 2026-07-17
Categories: q-bio.QM, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2607.19415v1

High-content morphological profiling (Cell Painting) yields sensitive, high-dimensional signatures of cellular state, but translating longitudinal morphology trajectories into interpretable biology remains difficult, especially for weak, chronic perturbations such as low-dose-rate ionizing radiation. Large language models (LLMs) can synthesize heterogeneous evidence into biological narratives, yet their scientific use requires quantitative auditing. We present an evaluation-first, retrieval-augmented interpretation framework for longitudinal Cell Painting morphology, applied to a 9-week RPE-1 time course across five dose rates (0.003--6.0 mGy/hr). Week-matched treated-control morphology deltas are combined with retrieved perturbation neighbors, pathway context, and literature evidence through stable evidence identifiers, enabling an LLM to generate structured, evidence-linked hypotheses that are hierarchically summarized while preserving provenance. We introduce two quantitative auditing tests: V1 citation validity, which verifies that cited evidence identifiers exist in the prompt, and V2 proxy-based morphology compatibility, which evaluates consistency between predicted biological processes and the most altered morphology features. In our experiments, V1 detected no invalid evidence references, while V2 showed meaningful morphology compatibility that increased with perturbation strength and was positively associated with an independent morphology drift summary. The framework produces auditable, falsifiable biological hypotheses, including an adaptive phenotype involving metabolic reprogramming and proteostatic stress at lower dose rates (0.003--0.3 mGy/hr). Current limitations include proxy-based evaluation and the lack of ground-truth mechanism labels.

---

### Decoding EEG Signals to Explore Next-Word Predictability in the Human Brain

Authors: Boi Mai Quach, Binh T. Nguyen, Cathal Gurrin, Graham Healy
Published: 2026-07-17
Categories: cs.CL
arXiv: https://arxiv.org/abs/2607.18321v1

Humans invented reading and have passed down this complex skill across generations through language. This study provides empirical evidence of the neural mechanisms underlying bottom-up (related to high-order linguistic structure) and top-down (related to next-word predictability) processes, which interact to guide comprehension during reading. While previous studies have focused on either the N400 effects of predictability or lexical categories, research on how predictability influences N400 responses across different lexical categories is limited, mainly due to constraints in publicly available datasets. Here, we examine how predictability influences brain responses, recorded at millisecond resolution using electroencephalography (EEG), with a focus on the N400 time window (300-500 ms post-stimulus) across different lexical and grammatical categories. Our results indicate that significant differences in N400 responses between high and low cloze probability levels were more pronounced for content words than function words. Among the two primary content categories, verbs exhibited greater N400 differences than nouns, while nouns carried more distinct information about their predictability than verbs. Moreover, we demonstrate that the decoding technique is more effective than the event-related potential (ERP) traditional analysis in capturing more detailed and distinct representations of cognitive processes over time.

---

### A Situational Speech Synthesizer for Yoruba: System Design, Phonological Rule Architecture, and Orthographic Extensions for Contour

Authors: Kola Tubosun, Adedayo Oluokun, Hafiz Adewuyi, Dadepo Aderemi
Published: 2026-07-17
Categories: cs.SD, cs.CL, eess.AS
arXiv: https://arxiv.org/abs/2607.18317v2

We present TTSYoruba, a rule-based concatenative diphone speech synthesizer for Yoruba, deployed at online as part of the YorubaName.com open dictionary of Yoruba personal names. The system takes tone-marked Yoruba text as input and produces audio output by applying a hand-crafted phonological rule system to a recorded inventory of 651 diphone units spanning five tonal variants of every consonant-vowel combination in the language. We describe the phonological architecture of the system in detail, including our complete tonal file-selection logic, our treatment of the three-way nasal disambiguation problem (oral /n/, nasalized vowel, and syllabic nasal), and the derivation of contextual rising and falling tones from level-tone input. We also present, as an orthographic contribution, the adoption of the caron and circumflex, which are symbols with prior standing in Yoruba phonological transcription, as standard single-vowel contour tone markers, integrated into the TTS normalization pipeline and the WriteYoruba keyboard input tool. The system's performance was evaluated through a listener study (N=50), with detailed results on Mean Opinion Scores (MOS) presented in Section 6. Keywords: Yoruba, text-to-speech, low-resource languages, diphone synthesis, contour tones, African language NLP, rule-based synthesis

---

### Binding Drift in Multi-Step Tool-Augmented Agents

Authors: Rahul Suresh Babu, Shashank Indukuri
Published: 2026-07-17
Categories: cs.SE, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2607.18316v1

Tool-augmented language-model agents execute multi-step workflows over external systems, resolving an entity once and then acting on it across subsequent steps. Prior work shows that in single-step actions, agents select the correct tool but bind it to the wrong entity 24-26% of the time. We study what happens to entity bindings over time: do they stay correct, silently drift to a different entity, or, if wrong from the start, propagate and compound? We formalize binding drift (correct at step 1, wrong later) as distinct from error propagation (wrong at step 1, carried forward), and score them on disjoint workflow sets so the two cannot be conflated. In a controlled multi-step testbed (200 workflows, 580 entity-binding-scored steps, four enterprise domains, eight model backends spanning small to frontier), we find: (1) under controlled error injection, an entity lock (the intuitive "persist the first binding" fix) amplifies wrong actions from 907 to 2,746 (3.0x; bootstrap 95% CI (2.8, 3.3)), because it faithfully carries the seeded wrong entity into every later step; (2) the amplification reaches 8.5x on the most affected model (Claude Opus 4.5); (3) a practical LLM-based re-verifier (a single cheap second model call re-reading the original instruction) reduces wrong actions by 79% (0.21x; CI (0.18, 0.25)), closing the gap to within 1 percentage point of an oracle upper-bound (0.20x); and (4) in the natural (non-injected) setting, baseline agents drift on 18% of eligible workflows, with the per-step error rate rising across steps. Persistence and re-verification are not interchangeable: a defense that eliminates drift can worsen propagation, and a practical re-verifier nearly matches oracle recovery.

---

### Interactive Training 2: Auditable Control Plane for Live Model Training

Authors: Wentao Zhang, Xuanhe Pan, Han Zhou, Yang Lu, Yuntian Deng
Published: 2026-07-17
Categories: cs.LG
arXiv: https://arxiv.org/abs/2607.18314v1

Experiment trackers show how training is progressing, but changing a live run still usually requires trainer-specific code. We present Interactive Training 2, an open-source control plane for steering training through a shared protocol. Training applications declare which settings and actions they expose, humans and automated controllers submit requests through the same interface, and the training loop validates and applies them at safe control points. A customized Aim workspace combines live metrics and controls with a chronological record of requests and outcomes. We demonstrate the system across five NLP and reinforcement-learning workflows. The released code and traces provide a reusable foundation for auditable human- and agent-guided training.

---

### Approximating SPR Distance Between Phylogenetic Trees with Graph Neural Networks

Authors: Renata Martins Castanheira, Miguel Bugalho, Cátia Vaz
Published: 2026-07-17
Categories: q-bio.PE, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2607.18311v1

Comparing phylogenetic tree topologies is essential for understanding epidemic dynamics, yet biologically meaningful distances such as the Subtree Prune and Regraft (SPR) distance are NP-hard to compute and intractable on large datasets. We investigate whether a Graph Neural Network (GNN) can approximate SPR distances in near-constant time per comparison after training. Our contributions are fourfold. First, we build and publicly release a dataset of 864 phylogenetic trees inferred with UPGMA and Neighbor-Joining over four bacterial species, spanning up to 9{,}500 isolates, together with 388 labelled tree pairs. Second, we establish a reproducible pre-processing pipeline including midpoint re-rooting, which reduces tree depth and supplies the rooting required for exact distance computation and for the model's root-based features. Third, we validate the supervision target: on small trees, where exact SPR is tractable, the unrooted phangorn::SPR.dist heuristic correlates almost perfectly with the exact rooted distance computed by rspr (Pearson $0.98$--$0.99$), making it an excellent monotonic surrogate. Lastly, we train a Siamese Graph Isomorphism Network (GIN) regressor. In-distribution, i.e., held-out trees from the same species and size range as training, it explains roughly 87--90% of the variance ($R^2 \approx 0.87$ on a held-out split; $0.90 \pm 0.19$ under stratified cross-validation), with about four times lower error than a mean-predictor baseline, and shows partial transfer to unseen species ($R^2 \approx 0.37$). Its main limitation is extrapolation to trees larger than those seen in training, where accuracy collapses. The released dataset and the validated heuristic versus exact relationship provide a reproducible basis for scaling learned SPR approximation.

---

### Distribution-First Population Simulation: Collapse, Calibration, and Recall in Non-WEIRD LLM Persona Modeling

Authors: Gurkan Ozkan
Published: 2026-07-17
Categories: physics.soc-ph, cs.AI
arXiv: https://arxiv.org/abs/2607.18310v1

Synthetic-population tools increasingly run every individual as an independent large language model (LLM) agent. Using real survey microdata, we show that this paradigm has a basic failure mode, and we set a distribution-first corrective against it, all measured with a deterministic, construct-validated verifier on non-WEIRD (Turkey-first) data. First, N independent LLM agents grounded on 2,414 real World Values Survey respondents fail to reproduce the population's response distribution: they pile onto a modal default (four scenarios x five seeds: concentration 0.36->0.69, entropy 1.46->0.77, 85% collapse, TVD=0.44), and the collapse is a predictable function of scenario structure (r=0.55 with a single-answer structure). Second, Verbalized Sampling (VS) fixes the field's chronic under-dispersion without training in three model families (fidelity +7 to +10; significant on Qwen, p=0.002, d=6.2), yet the same move universally overshoots into over-dispersion (SD-ratio 0.4-0.56 -> 1.26-1.37), a structural property of VS. Third, survey fidelity transfers only weakly to agentic behavior: in a single-model, single-domain booking task, a persona is dominated by a cheapest-default (~80%) that income modulates but does not override (comfort choice 0%->7%->32% across income bands). Fourth, a placebo-controlled memorization attack and an election backtest show VS keeps aggregate strength while subgroup and individual claims are contaminated by recall and underdetermination. We close with the corrective: model the distribution once (VS) and assign it to grounded characters at O(1) cost, with a budget-aware router whose honest AUC is 0.805, not the tautological 1.0 of a code-derived oracle. The central contribution needs no realism claim: it measures the internal inconsistency of the independent-agent route and the conditions under which the distribution-first route calibrates.

---

### Spatio-Temporal Prediction of Unsteady Airfoil Aerodynamics Using Augmented Graph Neural Ordinary Differential Equations with Exogenous Controls

Authors: Henrik Lange, Reik Thormann, Philipp Bekemeyer
Published: 2026-07-17
Categories: cs.LG, physics.flu-dyn
arXiv: https://arxiv.org/abs/2607.18309v1

Unsteady aerodynamic phenomena, such as gusts, turbulence, and fluid-structure interactions affect an aircraft during flight. For design, optimisation and certification, it is indispensable to quantify such unsteady aerodynamic effects. Industry-standard computational fluid dynamics methods, such as solving the unsteady Reynolds-averaged Navier-Stokes equations or the linearized frequency domain method, are either computationally expensive or restricted by assumptions like linearity. Once trained, machine learning methods are capable of computing non-linear relationships very fast, making them suitable as surrogate models. By autoregressively applying graph neural networks (GNNs), operating on a discretised spatial domain, spatio-temporal predictions can be made. However, autoregressive GNNs suffer from error accumulation leading to unstable rollouts over time. Here we show that combining GNNs with augmented Neural Ordinary Differential Equations yields temporally stable predictions of the surface forces on a pitching airfoil. We found that our approach, called GNODE, based on Graph Neural Ordinary Differential Equations, provides temporally more stable, spatially smoother, and overall more accurate results than an autoregressive GNN baseline. Tests are conducted on a dataset consisting of a simulations of a pitching airfoil, including transonic shocks, transient behaviour and dynamic non-linearities. Augmenting GNODEs with additional latent dimensions improves the expressivity and accuracy by capturing underlying history effects. The developed method demonstrates an approach that is suitable to model non-linear spatio-temporal systems with exogenous inputs.

---

### Agentic Calibration of Grey-Box Simulation Models: An LLM-Driven Alternative

Authors: David Gómez-Guillén, Mireia Diaz, Josep Lluis Arcos, Jesús Cerquides
Published: 2026-07-17
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2607.18308v1

Calibration of grey-box simulation models is a constrained optimization problem in which model evaluations are expensive, the parameter space can be high-dimensional, and the search must respect plausibility constraints. Although the simulation code is fully available to the analyst, the joint effect of multiple parameters remains difficult to predict analytically. Classical optimizers such as Nelder--Mead (NM) are simple to deploy but sample-inefficient, particularly under constraints. Modern Bayesian Optimization methods achieve competitive solutions with far fewer evaluations but require non-trivial modeling machinery for constraint handling. We introduce an agentic calibration method in which a large language model acts as the optimizer, with constraints incorporated as a plain-language section of the system prompt. We evaluate the agentic method, NM, and Bayesian Optimization (BO) on an anal cancer simulation model under both unconstrained and clinically constrained calibration. Under unconstrained calibration, the agentic method achieves substantially lower best error than BO and NM, while requiring fewer model evaluations. Under constrained calibration, the agentic method reaches comparable error levels and both outperform NM. These results are obtained at the cost of increased inference time per iteration. Agentic calibration achieves competitive performance with substantially fewer model evaluations, and constraint handling is essentially free at the modeller-facing interface through simple textual specifications rather than additional modelling machinery. The main trade-off lies in increased per-iteration inference cost, making the approach particularly suitable when simulation time dominates. Beyond performance, the per-iteration rationale makes the search auditable and explainable, so its decisions can be scrutinised and justified to third parties.

---