# Research Papers — 2026-08 · bundle page 51 of 240

> Full-text markdown of papers #2501–2550 of 11995 published in 2026-08, newest first. AI-readable mirrors of the full 11995-paper 2026-08 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-08/page/51
[← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/50.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-08/page/52.md)

### Towards Reliable, Generalizable, and Specific In-Context Knowledge Editing via Multi-Objective Reinforcement Learning

Authors: Xuzhong Wang, Maiqi Jiang, Tejal Nair, Girija Bhusal, Yanfu Zhang, Haipeng Chen
Published: 2026-08-25
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2608.25100v2

Large Language Models (LLMs) are powerful but limited by static parametric knowledge that becomes outdated once pretraining ends. Knowledge editing addresses this problem by updating model behavior on target facts without full retraining. In particular, in-context knowledge editing has gained attention because it is training-free and readily applicable to black-box LLMs. Recent reinforcement learning (RL)-based approaches improve over fixed retrieval strategies by adapting prompt construction to the quantity-quality trade-off. Despite initial success, they fail to model the prompt as a structured entity under the distinct and often competing objectives of reliability, generality, and specificity. Previous methods largely optimize a single objective and make decisions over only part of the prompt construction process, thereby overlooking both the balance of different objectives and the global organization of demonstrations. We propose Multi-Objective In-context Knowledge Editing (MO-IKE), a multi-objective RL algorithm that formulates prompt construction for in-context knowledge editing as a Constrained Markov Decision Process. MO-IKE trains a dynamic retriever to optimize competing objectives in knowledge editing, enabling more balanced and globally coherent prompt construction. On Llama-3.2, MO-IKE improves edit success (reliability) from 85.0% to 92.0%, paraphrase consistency (generality) from 77% to 79%, while increasing retention rate (specificity) by 23.0% compared to prior RL-based methods.

---

### PhysElite: How Far Are LLMs from Solving Olympiad-Level Physics Problems?

Authors: Ruoran Xu, Wending Gao, Liyunfeng Chen, Aixin Shi, Haoyu Cheng, Zixiang Fang, Yiqiang Zou, Qiufeng Wang
Published: 2026-08-25
Categories: cs.AI, cs.MM, math-ph
arXiv: https://arxiv.org/abs/2608.25097v2

Understanding how (multimodal) large language models perform on physics problems requires benchmarks that reflect the difficulty and breadth of expert-level physical reasoning. Existing physics benchmarks remain limited in the following two important ways: (1) short of high-difficulty datasets, and (2) lack of comprehensive coverage of visual forms, knowledge points, and step-by-step solution processes. As a result, model performance on current datasets may not be fully representative of their ability to solve complex physics problems. To address these issues, we present PhysElite, a large-scale bilingual multimodal benchmark for Olympiad-level physics reasoning. PhysElite contains 11,586 Olympiad-tier problems. For each problem, we provide corresponding visual diagrams, step-by-step bilingual Chinese-English solution derivations, and the final answer. We benchmark 18 open-source and closed-source MLLMs, and find that even the strongest model reaches only 33.7% answer accuracy. We additionally conduct step-level process evaluation to diagnose where models fail in the reasoning chain. Our datasets are released at https://huggingface.co/datasets/physelite/PhysElite.

---

### Understanding the Energy Scaling of Large Language Model Inference Across Context Lengths and Attention Architectures

Authors: Molka Chkir, Syed Muhammad Danish, Jos Höll, Arghavan Asad
Published: 2026-08-25
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2608.25096v1

The growing adoption of large language models (LLMs) has raised increasing concerns about the energy consumption and environmental impact of inference. This paper presents a systematic empirical study of decode-phase energy consumption across representative open-source LLMs employing Multi-Head Attention (MHA), Grouped Query Attention (GQA), and Grouped Query Attention with Sliding Window Attention (SWA) to characterize how attention architecture influences decode-phase energy consumption under varying inference workloads. We evaluate four models across different context lengths, batch sizes, and generation workloads while measuring GPU energy using NVIDIA hardware counters. We examine the effects of context length, attention mechanism, Key-Value (KV) cache growth, and batching on decode-phase energy consumption. Results show that attention mechanism is the primary factor governing how decode energy scales with context length. MHA models exhibit substantially steeper energy growth than GQA models, whereas GQA with SWA maintains nearly constant energy consumption. We further show that model size primarily determines absolute energy consumption, while batching reduces both energy per generated token and request latency by up to 87%. These findings provide practical guidance for selecting energy-efficient LLM architectures and inference configurations.

---

### Scalable Self-Supervised Learning for Multiphase AC-OPF in Distribution Systems with Topology Reconfiguration

Authors: Hoang T. Nguyen, Shaohui Liu, Reetam Sen Biswas, Varsha Pendyala, Nurali Virani, Deepjyoti Deka, Priya L. Donti
Published: 2026-08-25
Categories: eess.SY, cs.LG, math.OC
arXiv: https://arxiv.org/abs/2608.25095v2

The proliferation of distributed energy resources (DERs) in distribution grids enables the active coordination of these assets to reduce costs and enable cleaner operations. Realizing this potential requires solving multiphase AC optimal power flow (AC-OPF) quickly across varying loads, DER availabilities, and topology reconfigurations, at much greater speed and scale than conventional nonlinear solvers. Learning-based surrogates can offer millisecond inference, yet existing methods target largely balanced transmission systems and do not scale to the multiphase, unbalanced, and reconfigurable nature of distribution feeders at utility scale. We present the Penalty + Sequential Linearized Feasibility Seeking (SLFS) algorithm, a self-supervised learning framework for multiphase distribution AC-OPF under switch-induced topology changes. Penalty+SLFS requires no labeled optimal solutions and trains directly from the AC-OPF objective and constraints through a differentiable fixed-point power flow solver, avoiding expensive label generation and admitting robust training procedures. Topology changes are handled efficiently using Sherman-Morrison-Woodbury updates of the admittance-matrix inverse, while an M-step Jacobian approximation accelerates differentiation through the power flow solver. At inference, SLFS repairs any infeasible predictions, providing feasibility guarantees with low computational overhead. On IEEE feeders ranging from 13 to 8,500 nodes, Penalty+SLFS achieves negligible optimality gaps and near-zero constraint violations, delivers up to three orders of magnitude speedups over IPOPT, and remains robust under large distributional shifts, demonstrating a viable path toward real-time, topology-aware AC-OPF for large-scale distribution grids.

---

### Auto-Policy, not Auto-Skill: Compiled Agent Skills for the Physical World

Authors: Zhonghao Zhan, Hamed Haddadi
Published: 2026-08-25
Categories: cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2608.25091v1

Self-evolving Skill harnesses (AutoSkills, Hermes Agent) generate more advisory orchestration automatically; their reported gains are efficiency, not safety. This misses the actual gap: a Skill describes how an agent should behave; a Policy decides which behavior is allowed to become an action. Today's format covers the first with markdown and scripts; the second is left to the model. Generating more Skills scales the gap, not the safety, especially when a wrong invocation can unlock a door or move money. Two adjacent attacks are documented: malicious skills compromising cloud software, and jailbroken LLM-controlled robots causing physical harm. Their intersection, malicious agent skills causing physical harm, follows directly but has not been reported. We name this class Borrowed Authority: Skills format gives the receiving agent no typed way to reject an inter-agent permission claim, so a malicious or misused Skill can drive actuation by attaching one. We propose Edge Skillguard, a typed authority layer that lives inside the Skill artifact rather than between tools as workflow engines do, with guards over world state and sensor evidence. On a live edge control-plane testbed, the guards reject 60/60 borrowed-authority requests across five attack variants without blocking benign requests, and the result holds at 5x scale and across hosts over a Tailscale mesh. These results suggest that high-risk Skills should co-package typed invocation policy with procedural knowledge, so that physical actions depend on machine-checkable evidence rather than peer-agent claims.

---

### Apples to Apples? Towards Comparable Crosslingual Language Model Evaluation

Authors: Xiulin Yang, Ethan Gotlieb Wilcox, Catherine Arnett
Published: 2026-08-25
Categories: cs.CL
arXiv: https://arxiv.org/abs/2608.25089v2

Crosslingual evaluation of language models that enables fair comparisons remains a fundamental challenge in multilingual NLP. Existing studies adopt a variety of downstream tasks and intrinsic metrics with different theoretical justifications, yet there has been little empirical investigation into whether these approaches yield meaningful crosslingual conclusions. We systematically examine crosslingual evaluation approaches using controlled monolingual language models trained on parallel data with varying tokenizer vocabulary sizes and model sizes, and further validate our findings on multilingual LLMs. We further discuss challenges in achieving comparable downstream evaluation across languages. Our results show that several widely used normalized metrics introduce crosslinguistic biases rooted in tokenization, encoding, and orthographic differences. In contrast, sentence-level negative log-likelihood computed over semantically equivalent sequences provides more meaningful and consistent crosslingual comparisons.

---

### The Von-Neumann State-Space Transformer for neural decoding

Authors: Morteza Sarafyazd
Published: 2026-08-25
Categories: cs.LG, cs.AI, q-bio.NC
arXiv: https://arxiv.org/abs/2608.25088v1

Cortical computation is strikingly low-dimensional: a handful of latent variables, carried in a neural population's activity, steer the higher-dimensional responses of individual neurons. Our aim is sample efficiency-models that decode well from limited data and at small parameter budgets. In a standard Transformer layer, the feed-forward block applies the same operator to every token. We suggest a von-Neumann inspired hypothesis of efficient computation as an alternative for neural decoding: a controller decodes an instruction and then executes a token-specific operator; the usual realization-a soft mixture of experts-only blends their outputs, not operators. We introduce a von-Neumann State-Space Transformer (VN-SST), a memory-augmented Transformer whose feed-forward block is a low-rank instruction bank: a shared base operator plus a small set of learned low-rank instructions, from which a per-token code synthesizes the weight matrix actually used at that token. The code is read from a low- dimensional projection of a carried state-space memory, so a slow latent trajectory acts as an instruction pointer-mirroring how low-dimensional dynamics may route cortical computation. On three motor-cortex neural-decoding benchmarks, VN-SST is far more data-efficient than a modern Transformer, each jointly predicting spikes and decoding behavior. This model wins by a wide margin on the scarcest benchmark, leads on the other two, and turns longer context into rising rather than falling accuracy. We evaluated that the network compresses a large instruction bank to a few bits per token, so program capacity acts as a control channel, not an accuracy lever. The same model is also more parameter-efficient on two small text benchmarks used for language modeling (LLMs), suggesting a generic mechanism.

---

### MTDiag: A Multi-Turn Diagnostic Dataset Towards Clinically Meaningful LLM Evaluation

Authors: Pia Chouayfati, Alexander M. Fichtl, Miriam Anschütz, George Doumat, Georg Groh
Published: 2026-08-25
Categories: cs.CL
arXiv: https://arxiv.org/abs/2608.25085v1

Clinical diagnosis is fundamentally interactive and incremental, yet the dominant paradigm for evaluating Large Language Models (LLMs) in medicine remains static QA benchmarks or template-based dialogues. These benchmarks say little about whether a model can serve as a diagnostic agent in a dynamic clinical encounter, with LLMs showing significant accuracy and reliability degradation in multi-turn settings. To address this issue, we present MTDiag, a large multi-turn diagnostic dialogue dataset constructed from three heterogeneous sources: DDXPlus, MIMIC-IV, and published case reports (AJCR), covering common ED presentations as well as long-tail rare and atypical conditions. All cases are normalized into a canonical schema anchored in the most comprehensive and widely-adopted medical knowledge bases (UMLS concept identifiers, with ICD-10 diagnosis codes). We release the schema, a UserLM-8B-based utterance-generation pipeline, and the physician-validated dataset that converts structured clinical evidence into natural-language utterances. Importantly, we introduce and motivate clinical knowledge-grounded metrics for evaluating LLMs as diagnostic agents, beyond diagnostic accuracy, for the task of multi-turn differential diagnosis.

---

### The Frame Kernel Method for Multiscale Operator Learning

Authors: Branden Frieden, Ryan Whitehead, M. Keith Ballard, Robert M. Kirby, Varun Shankar
Published: 2026-08-25
Categories: cs.LG, math.NA
arXiv: https://arxiv.org/abs/2608.25084v2

We present a natively multiscale operator learning method for the surrogate modeling of (numerical solvers for) multiscale partial differential equations (PDEs). The primary novelty of our method lies in a novel multiscale kernel frame function approximation technique. Leveraging this new kernel frame technique, we cast the operator learning problem as one of learning frame coefficients of output functions as a function of frame coefficients of input functions. The generalization step then automatically allows for a multiscale decomposition of the output functions. Our method is applicable to both tensor-product grids and point clouds. We present interpolation proofs, error estimates, and numerical convergence rates for our frame approximation. We the demonstrate the applicability of our method for the surrogate modeling of inherently multiscale PDEs. The new multiscale frame kernel method is significantly more accurate than popular neural operators on challenging problems from the literature, while simultaneously admitting an a posteriori multiscale decomposition upon generalization.

---

### NVExplain: Explaining Time Series Forecasting with Latent Trajectory Analysis and Structure-Preserving Surrogates

Authors: Muyan Anna Li, Manikandan Ravikiran, Aditi Gautam
Published: 2026-08-25
Categories: cs.LG, cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2608.25080v1

Time series forecasting models are widely used in high-stakes settings, yet their predictions remain difficult to interpret because existing post-hoc methods often ignore temporal dependence and fail to provide horizon-specific explanations. We propose a model-agnostic explainability framework that explains forecasting predictions by attributing each forecast horizon to temporally relevant historical lags. The framework models forecasting as a latent trajectory and introduces semantic flow to quantify how information evolves across time in the model's internal representations. By aggregating semantic flow, it constructs a lag-horizon attribution matrix that captures horizon-resolved temporal influence. To improve explainability, we further generate structure-preserving perturbations and fit sparse local surrogate models, producing human-readable and temporally coherent explanations. We evaluate the method using faithfulness and stability diagnostics across multiple benchmark datasets. Results show that the semantic-flow variant achieves competitive or superior faithfulness compared to standard post-hoc baselines, while being substantially more computationally efficient. Stability analysis further demonstrates that the explanations are robust and identifies regimes where interpretation should be applied with caution.

---

### DeMMO: Longitudinal and Cross-Disease Modelling of Digital Mobility Outcomes via Multi-Task Learning

Authors: Menghui Zhou, Zhipeng Yuan, Vitaveska Lanfranchi, Po Yang
Published: 2026-08-25
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2608.25073v3

Digital mobility outcomes (DMOs) derived from wearable sensors characterise mobility in daily life and offer a promising means of monitoring disease progression. However, existing DMO studies have typically focused on either a single disease or a single visit. To the best of our knowledge, we are the first to define and study the practical problem of cross-disease longitudinal DMO modelling. We argue that this problem should satisfy at least two requirements. First, the temporal progression of DMOs should be modelled within each disease, as mobility-limiting diseases evolve over time. Second, multiple mobility-limiting diseases should be modelled jointly, as different diseases affect different aspects of human mobility. To address this problem, we propose DeMMO, an interpretable framework for longitudinal, multi-disease, and multi-outcome learning. Its central technical contribution is an interpretable cross-disease and cross-outcome relation-learning mechanism that infers signed relations directly from learned longitudinal DMO-outcome mappings, thereby enabling selective information sharing across cohorts without requiring paired participants. We evaluate DeMMO on the recently released, large-scale, multicentre Mobilise-D dataset, which presents a challenging modelling setting involving longitudinal observations, multiple clinical outcomes, and four participant-disjoint cohorts representing distinct mobility-limiting diseases. Compared with eight strong structural longitudinal and deep-regression baselines, DeMMO achieves the best overall predictive performance and outperforms the baselines for most individual outcomes. Stability selection further identifies reliable longitudinal DMO patterns that can inform subsequent clinical validation and disease monitoring. The implementation code is available at https://github.com/menghui-zhou/DeMMO.

---

### HealthBench-Psych: A Mental Health Subset of OpenAI's HealthBench

Authors: Matthew Flathers, Phuong Anh Nguyen, Jill Noorily, Julian Herpertz, Meiting Chen, Jasreen Multani, Samuel Powell, Mason Granof, Mark Kalinch, John Torous
Published: 2026-08-25
Categories: cs.CL, cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2608.25071v1

General-purpose health benchmarks increasingly anchor claims about LLM medical performance, but they are not always resolved by clinical specialty, making domain-specific performance hard to isolate. Mental health is of acute public-health concern as millions of people turn to LLMs for psychological support, and most existing evaluations are bespoke academic benchmarks that are difficult to integrate into developer workflows. We introduce HealthBench-Psych and HealthBench-Psych-Hard. We screened HealthBench's 5,000 physician-rubric conversations for mental-health relevance with a transparent LLM-applied rubric, then validated the subset through two rounds of blinded clinician review with concealed known-exclude controls, yielding 610 conversations (12.2% of the corpus). Evaluating 20 frontier and open models under a cross-vendor panel of three LLM judges, we find a statistically tied frontier cluster, measurable refusal behavior in two models, and near-identical rankings across judges ($τ\ge 0.92$). We release the subset, pipeline, model responses, grades, and analysis code as a reusable resource.

---

### SHIFT-LLM: Distribution Shift Correction in Depth-Pruned LLMs

Authors: Ali Bahri, Hang Li, Hongliang Li, Zhitang Chen
Published: 2026-08-25
Categories: cs.CV
arXiv: https://arxiv.org/abs/2608.25068v1

Depth pruning removes entire Transformer blocks to reduce the inference cost of large language models, but disrupts the hidden-state distributions expected by downstream layers, leading to significant accuracy loss. We introduce SHIFT-LLM, a training-free post-pruning correction framework that inserts a Linear Residual Adapter (LRA) at each pruning site. Each LRA preserves the identity pathway of the original residual block and adds a lightweight affine residual correction. This correction is calibrated via closed-form least-squares regression on a small held-out set, without gradient computation, to approximate the missing residual update produced by the pruned block. Together with the preserved identity pathway, the resulting LRA output approximates the hidden state produced by the original block, thereby mitigating the distributional mismatch introduced by layer removal while avoiding the expensive attention and feed-forward computations of the removed blocks. The resulting LRAs support low-rank factorization and exact merging across consecutive pruned layers for additional compression, and combine naturally with parameter-efficient fine-tuning for further recovery beyond fine-tuning the pruned model alone. Experiments on five model families, six layer-selection criteria, and seven zero-shot benchmarks show that SHIFT-LLM consistently recovers accuracy lost to depth pruning across most configurations, achieving gains up to +15.7 points on Llama-3.1-8B-Instruct while requiring only a few hundred calibration samples and no gradient computation.

---

### SimVerity: When Does Simulated Agent Success Survive Physical Deployment?

Authors: Zhonghao Zhan, Yefan Zhang, Krinos Li, Hamed Haddadi
Published: 2026-08-25
Categories: cs.AI
arXiv: https://arxiv.org/abs/2608.25067v1

Simulated evaluation is widely used to benchmark AI agents, yet how much evidence a simulated pass provides about physical deployment has not been systematically quantified. We present SimVerity, a verdict-transfer assurance framework: it replays matched scenarios on target smart home deployments and cross-validates agent execution against independently qualified physical witnesses. Our evaluation highlights that deployment success is a real-world process, not a static property in simulation: completion, reported state, observable effect, and settled outcome diverged within the same execution. Although an advanced simulator cleared all 240 light trials, a camera caught 42 sub-second failures invisible to settled-state checks. False clearance was predictable: a risk profile learned from measured trials and locked before evaluation predicted failures on a path it never physically measured, beating a property-blind baseline in all eleven held-out sessions across two cohorts. Agent auditability was also measurable: switching one agent loop's model-client/serving configuration raised its scenario-matching share from 52-88% to 100%. Finally, a second qualified simulator added no independent cross-check: it never disagreed on any overlapping case, and only physical measurement exposed their shared blind spots. SimVerity turns verdict transfer into an explicit decision: clear, abstain, or escalate before deployment.

---

### FLINT: Efficiently Leveraging High Bandwidth Flash for Capacity-Scalable LLM Inference Acceleration

Authors: Geraldo F. Oliveira, Arash Tavakkol, Xiangyu Zhu, Ahmet Caner Yüzügüler, Vamanan Arulchelvan, Lukas Cavigelli, Renzo Andri, Mohammad Sadrosadati, Jia Xinglei, Onur Mutlu, Zhou Ke, Shai Bergman et al.
Published: 2026-08-25
Categories: cs.AR, cs.AI, cs.DC
arXiv: https://arxiv.org/abs/2608.25062v1

LLM inference is increasingly constrained by accelerator memory capacity rather than compute throughput. This constraint is especially acute in single-accelerator and small-node inference systems, where limited on-package memory capacity restricts the size of deployable models. HBF is an emerging 3D-stacked NAND flash technology that provides multi-terabyte near-accelerator capacity, making it a promising capacity tier for storing LLM weights. However, existing HBF-based proposals face three adoption challenges: they (1) rely on coarse-grained static prefetching for LLM weights aiming to hide the microsecond-level read latency of the NAND flash device while maximizing HBF's read throughput, (2) expose NAND flash management tasks (e.g., refresh operations) to the accelerator-visible critical inference path, and (3) miss optimization opportunities to specialize and optimize the flash-management mechanisms to the workload behavior. Our goal is to design an efficient HBF substrate that integrates HBF as a memory-capacity tier alongside HBM while addressing these three challenges. To this end, we propose FLINT, a workload-driven HBF substrate for capacity-scalable LLM inference. FLINT introduces three mechanisms: (1) a hardware burst-buffer controller that dynamically coalesces and pipelines HBF reads aiming to utilize existing NAND flash buffers while sustaining high HBF bandwidth, (2) a phantom-plane refresh mechanism, which removes refresh from the critical inference path by moving refresh-related NAND flash operations outside the read foreground back via low-cost resource duplication, and (3) a read-only FTL, which replaces SSD-class support for arbitrary writes with a compact table that translates logical weight bursts to physical HBF locations.

---

### DataKernelBench: Can LLMs Optimize Database Queries on GPUs?

Authors: Gokul Karthik Kumar, Yotam Perlitz, Corey Lammie, Andrea Giovannini, Katja Hose
Published: 2026-08-25
Categories: cs.CL, cs.AI, cs.DB, cs.LG, cs.PL
arXiv: https://arxiv.org/abs/2608.25061v2

GPUs increasingly accelerate database systems, but query-specific peak performance still often relies on hand-written kernels. Existing LLM kernel benchmarks focus on machine learning operators, leaving irregular, heterogeneous, data-movement-heavy database-style operators untested. We introduce DataKernelBench, which translates SQL into validated PyTorch TorchPlan programs and evaluates LLMs that optimize either the core tensor-bounded snippet or the full query in CUDA or Triton through execution-guided repair. Across ten proprietary and open-weight models on TPC-H SF10 with an H100 GPU, the strongest full-query CUDA configuration achieves $2.11\times$ speedup over the TorchPlan baseline at full pass rate. We find that higher-performing implementations commonly use kernel fusion and execution-strategy changes, stronger models benefit most from full-query specialization, and workload context matters more than hardware context. To handle data larger than GPU memory, we extend TorchPlan with Dask-cuDF for on-demand partition loading on TPC-H SF100 with four H100 GPUs, achieving $2.54\times$ speedup. Project page: https://kerneldf.github.io/datakernelbench

---

### SPECTRA: Subspace-Preserving Embedding Calibration, Transport, and Replay for Fully Few-Shot Class-Incremental Audio Classification

Authors: Giries Abu Ayoub, Loay Mualem, Simon Korman
Published: 2026-08-25
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2608.25054v1

Fully few-shot class-incremental audio classification (FFCAC) requires recognizing new sound classes from only a handful of labeled examples per session, without forgetting previously learned classes and without any large base dataset. Existing methods typically freeze a pre-trained audio--language encoder and classify with point prototypes, but they suffer from significant performance degradation throughout the sessions due to generic feature representations. We propose SPECTRA, a framework built on a frozen encoder which adds three components. (i) a lightweight trainable adapter that calibrates the generic embeddings to the task; (ii) subspace feature replay, an exemplar-free anti-forgetting scheme that replays old classes by sampling from the low-rank subspace of their stored features; and (iii) a transductive optimal-transport refinement of prototypes at test time. Our central finding is that the subspace structure of the replay diminishes forgetting and outperforms naive Gaussian replay of equal variance. On three FFCAC benchmarks (NSynth-100, FSC-89, LS-100), SPECTRA improves average accuracy and reduces forgetting over current state-of-the-art methods, and our ablations statistically validate each component.

---

### Hydra: Phase-Aware Workload Characterization of LLM Inference across Edge SoC Generations, Backends, and Quantization Levels

Authors: Amir Taherin, Sana Taghipour Anvari, Charles Amante, Yixiao Chen, Ruben Noroian, Zlatan Feric, Nicolas Bohm Agostini, Pu Zhao, José Cano, Bin Ren, Yanzhi Wang, David Kaeli
Published: 2026-08-25
Categories: cs.AR, cs.AI, cs.DC, cs.PF
arXiv: https://arxiv.org/abs/2608.25053v1

Edge LLM deployment is shaped by more than model size and precision: inference backend, hardware platform, memory traffic, and power management all affect latency and efficiency. We present Hydra, a common-schema, phase-aware workload characterization framework for LLM inference on edge SoCs. Hydra instruments HuggingFace Transformers and llama.cpp with a shared per-prompt timing schema and fuses those records with hardware telemetry, enabling a multi-dimensional characterization of performance, system-resource utilization, and efficiency across prefill and decode phases. Using Hydra, we evaluate three consecutive edge System-on-Chip (SoC) generations (AGX Xavier, AGX Orin, and AGX Thor), 13 instruction-tuned LLMs from seven families, five execution formats, and consider input/output-length sensitivity. The resulting artifact contains roughly 107K per-prompt records and is publicly released with Hydra. Our analysis shows that aggregate latency alone hides key deployment effects: backend structure changes where latency is introduced, quantization reduces memory traffic and energy but does not predict power monotonically, and SoC generation changes how utilization and efficiency should be interpreted. By connecting phase-level timing with system-resource utilization and efficiency metrics, Hydra enables reproducible, phase-aware characterization of edge LLM inference. Hydra's source code and the collected per-prompt trace corpus are available open-source at: https://github.com/amirtaherin/hydra

---

### Improved Analysis for Hessian-free High-resolution Monte Carlo Sampling

Authors: Wujun Lv, Xiaoyu Wang, Yingli Wang, Lingjiong Zhu
Published: 2026-08-25
Categories: stat.ML, cs.LG, math.AP, math.PR
arXiv: https://arxiv.org/abs/2608.25052v1

Hessian-free high-resolution (HFHR) dynamics augments underdamped Langevin dynamics (ULD) with reversible position diffusion for sampling problems that arise in machine learning. We establish an explicit quantitative contraction rate for HFHR dynamics under a position Poincaré inequality, weighted Hessian and Laplacian bounds, and a compact Sobolev embedding, where the potential function is not necessarily convex. An adapted time-augmented Poincaré inequality yields an explicit rate that improves upon the contraction rate of the underdamped Langevin dynamics. We also give a weak-solution construction and a self-contained spectral proof of the divergence lemma underlying the argument. For HFHR Monte Carlo (HFHRMC) algorithm, which is based on a discretization scheme of HFHR dynamics, we use a path-space Girsanov argument to obtain a non-asymptotic convergence bound and an explicit iteration complexity in total variation distance. The bounds hold for every $α\geq0$ and $γ>0$ and remain regular at the ULD endpoint. Optimizing the iteration complexity bound yields a positive, accuracy-dependent position-diffusion parameter at finite accuracy, while its leading high-accuracy order coincides with that of the optimized ULD endpoint. Our iteration complexity bound improves upon the existing work on HFHR algorithms. Numerical experiments including Bayesian learning problems on real data are provided to illustrate the effect of positive $α$ and its benefit.

---

### ARISMA: Guidelines for AI- and LLM-Assisted Systematic Reviews, Scoping Reviews, and Mapping Studies

Authors: Mahyar Tourchi Moghaddam, Mina Alipour
Published: 2026-08-25
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2608.25050v1

Systematic reviews, scoping reviews, mapping studies, and related evidence syntheses are increasingly difficult to conduct with fully manual workflows as search volumes, update cycles, and synthesis requirements continue to expand. At the same time, artificial intelligence, machine learning, and large language models are rapidly entering review practice across query formulation, screening, extraction, categorization, appraisal support, and reporting. Yet the empirical evidence remains uneven, task-dependent, and insufficient to justify unconstrained automation. Existing standards such as PRISMA 2020, PRISMA-S, PRISMA-ScR, PRISMA-P, PRESS, and SWiM remain essential, but none provides an end-to-end operational standard for when AI use is methodologically appropriate, how it should be validated, which review decisions must remain human-led, and how AI involvement should be reported so that readers can audit it. This paper proposes ARISMA, an AI Reporting and Integration standard for Systematic Methods and Analysis. ARISMA treats AI as an inspected, benchmarked, logged, and reversible assistant rather than an autonomous reviewer. It is built around one governing principle: every consequential scientific decision must remain human-interpretable, human-auditable, and human-accountable. The paper contributes a lifecycle taxonomy, process guidance, stepwise recommendations across the review pipeline, a governance and provenance model, a tool-support framework, an AI-integrated reporting checklist, and a validation matrix. It also addresses legal, privacy, infrastructure, and sustainability considerations. The framework was iteratively refined through structured expert consultation. The result is a practical and auditable guideline for responsible AI-assisted evidence synthesis.

---

### LifePlanner: Evaluating LLM Agents for Geo-spatial Planning with Social Media Data

Authors: Zhen Dong, Yuning Peng, Yutao Shi, Lei Zhong, Yongsen Mao, Yuan Liu, Haiping Wang
Published: 2026-08-25
Categories: cs.AI
arXiv: https://arxiv.org/abs/2608.25039v1

Geo-spatial planning, like trip design, is a realistic testbed for LLM agents because it requires grounded tool use, noisy evidence retrieval, and multi-constraint reasoning. Most benchmarks, however, only provide clean geospatial data and tools, missing the open-ended social signals that people use in daily planning. We introduce LifePlanner, a benchmark that enriches map data with large-scale local social media posts and provides access through an MCP toolset. LifePlanner provides an evaluation suite spanning four task categories and three difficulty levels. Experiments show frontier LLMs perform well on simple retrieval but degrade sharply on complex planning, with the Pass Rate dropping to 40.2%. Results show that failures mainly stem from incomplete evidence acquisition from such a large multimodal database, imprecise tool use, and weak constraint integration rather than model size or reasoning length, suggesting that future progress requires effective grounded planning instead of scaling alone.

---

### Padamitra: Grounded Glossary Generation for Classical Sanskrit

Authors: Manoj Balaji Jagadeeshan, Sai Pragnaan Marala, Pawan Goyal
Published: 2026-08-25
Categories: cs.CL
arXiv: https://arxiv.org/abs/2608.25038v2

We introduce grounded glossary generation, a structured task requiring models to recover semantically meaningful Sanskrit phrases and produce translation-grounded meanings from a sloka-translation pair, formalizing the traditional patha commentary practice as an evaluable NLP objective. We construct a benchmark of 31,316 sloka-translation-glossary triples from the Valmiki Ramayana and Srimad Bhagavatam, paired with two metrics: Jaccard for phrase recovery and Meaning Faithfulness for semantic consistency. Across zero-shot, few-shot, and instruction fine-tuned variants of Gemma-3n-E4B, Gemma-3-12B, Phi-4, and Qwen3.5-9B, instruction fine-tuning substantially outperforms prompting, while explicit segmentation yields gains. Error analysis identifies over-segmentation of sandhi and samasa compounds as the dominant failure mode, pointing to morphological modeling as the key bottleneck for faithful Sanskrit lexical decomposition.

---

### Retrieve, Match, Escalate: Accurate and Scalable Product Linking with VLM-Distilled Cross-Encoders and Agentic VLMs

Authors: Jian Wang, Steven Xu, Sanjyot Thete, Maryam Barouti, Tom Tang, Elaine Wu, Charu Sareen, Kyle MacDonald
Published: 2026-08-25
Categories: cs.AI, cs.CL, cs.DB, cs.IR
arXiv: https://arxiv.org/abs/2608.25037v1

Product linking, the entity-resolution task of mapping merchant product records to canonical catalog products, consolidates fragmented listings so downstream search, recommendation, and advertising see one clean entry per product. At marketplace scale, billions of noisy, multi-category records must be resolved against tens of millions of canonical products, where scoring every candidate with a single model is either too weak for the hard cases or too costly for the easy ones. We present a production retrieve-then-match cascade that spends computation in proportion to difficulty: retrieval surfaces plausible matches, a lightweight text cross-encoder auto-resolves the high-confidence majority, and an agentic multimodal vision-language model settles the ambiguous remainder by inspecting product images and issuing web searches for evidence that is in neither record. The cross-encoder is distilled from millions of dual-VLM-consensus labels, retiring human annotation from the training set, and is calibrated to auto-accept links at a 98% precision bar validated against a smaller operator-certified audit. The agent is a self-hosted open-weight model that reaches a closed frontier VLM's precision at a four-point recall cost (88% versus 92%) for roughly one-seventh the per-pair cost, with no fine-tuning. Per-pair cost spans nearly five orders of magnitude from the cheap cross-encoder to the frontier VLM, so escalating only the hard tail to the agent raises end-to-end link coverage from the cheap stage's 68% to 77%.

---

### On the Representational Geometry of Dynamic Programs

Authors: Richard F. M. Lim, Ruriko Yoshida
Published: 2026-08-25
Categories: cs.LG, cs.DM, math.AG, math.CO
arXiv: https://arxiv.org/abs/2608.25034v1

Standard neural architectures often fail to generalize to longer inputs for dynamic programming (DP) targets. We investigate what makes this hard geometrically. Every finite min-plus DP is a shortest path on a DAG, which is equivalently a tropical polynomial whose extended Newton polyhedron encodes the decision boundary of which path wins. We prove these three descriptions (graph, polynomial, polyhedron) form isomorphic semirings at two levels --- formal polynomials and their computed functions --- connected by operations that characterize all structural redundancies. We then address the length-generalization question geometrically: does the decision boundary at length $T$ decide the boundary at $T+1$? We present two structural negatives. The semiring's two native ways to reduce dimension (setting a variable to each identity) are neither injective nor always closed within the DP. Series and parallel composition fail to construct all DAG topologies from smaller sub-DAGs, and even all terminal-only operations do not capture all DP compositions.

---

### Directed walks shape a universal square-root law of entropy production rate in nonreciprocal systems

Authors: Thiparat Chotibut, Ewa Gudowska-Nowak, Maciej A. Nowak
Published: 2026-08-25
Categories: cond-mat.stat-mech, cond-mat.dis-nn, cs.NE, math-ph, q-bio.NC
arXiv: https://arxiv.org/abs/2608.25030v1

The entropy production rate (EPR) quantifies irreversibility of a nonequilibrium steady state, yet standard formulas obscure how a complex interaction network generates it. For multivariate Ornstein-Uhlenbeck dynamics on such networks, we express the EPR as a quadratic form in antisymmetric matrices measuring the nonreciprocity of aggregate directed walks at every length, and, equivalently, as two weighted-walk quantities: pairs of directed walks sharing both endpoints, and directed closed walks. For diagonalizable interactions, an exact correspondence translates these walk quantities into eigenvalues and biorthogonal eigenvector overlaps. Across dense, sparse, and deep acyclic random interactions satisfying matched-walk conditions, the mean EPR per node universally follows the square-root law $φ_*(g)=1-\sqrt{1-g^2}$, where $g \in (0,1)$ parametrizes the interaction strength. Deep acyclic interaction matrices are nilpotent, with all eigenvalues fixed at zero for every $g$, yet, as their depth increases, their mean EPR per node approaches $φ_*(g)$. Thus, the square-root law arises from directed walk properties, rather than from a shared spectral density or specific network topology.

---

### Behind the (MASK): Disentangling Representation and Faithfulness in DAPF-Based Dementia Detection

Authors: Pardis Ranjbar-Noiey, Natalie Parde
Published: 2026-08-25
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2608.25028v1

Spoken-language analysis via prompt-based domain-adaptive models is a promising direction for low-resource, non-invasive dementia screening, but such models remain internally opaque. We study the interpretability of the Domain-Adapted models via Prompt-based Fine-tuning (DAPF) framework, which casts dementia detection as diagnosis-related masked-token prediction. We interpret DAPF and strong baselines using a variety of probing and analysis techniques, finding that DAPF achieved the best overall performance (accuracy=0.83 and macro-F1=0.83) with diagnosis most recoverable from its (MASK) representation. However, this representational advantage did not extend to token-level explanation faithfulness. DAPF attributions primarily reflected language task vocabulary, discourse markers, and transcription artifacts, with perturbation tests showing weak or negative effects. This suggests that its masked-token interface determines diagnosis information without producing faithful token-level explanations.

---

### CVE-SAI: Counterfactual Visual Evidence-Guided Selective Attribute Indexing for Risk-Controlled E-commerce Search

Authors: Xiaolong Sun, Qichao Wang, Hangyu Li, Liang Chen
Published: 2026-08-25
Categories: cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2608.25023v1

Multimodal product models can complete missing e-commerce attributes, yet current methods still optimize attribute-answer accuracy without verifying visual support, conflate transient prediction with persistent index admission, and lack explicit risk control over factually incorrect or visually unsupported values. We address these gaps with Counterfactual Visual Evidence-Guided Selective Attribute Indexing (CVE-SAI), which first infers and freezes an ontology-constrained candidate from the primary image and attribute question without catalog text, and then decides whether that candidate should enter the index. Focus-Zone Distortion (FZD) constructs an attribute-specific visual-dependence proxy through a controlled counterfactual intervention, and Evidence-Guided Attention Redistribution (EGAR) uses the proxy to refine ontology-constrained scoring. The canonical candidate is frozen before evidence necessity, evidence retention, nuisance-transformation stability, and candidate-specific catalog-text conflict audits; catalog text can only tighten admission and cannot revise the candidate. Independent family-level calibration selects one policy with a simultaneous one-sided finite-sample bound under a 5% unsafe-admission budget. Experiments on five visual attributes derived from Amazon Berkeley Objects show that CVE-SAI improves attribute inference and evidence localization, achieves the highest certified admission coverage under the shared risk protocol, and yields the strongest controlled retrieval performance with the lowest unsafe auto-induced exposure among automatic-admission systems. Separating inference from admission therefore enables visually supported attribute completion to improve retrieval while limiting persistent index contamination.

---

### A Primer on Computational Semantics for Artificial Intelligence Systems

Authors: Casey Kennington
Published: 2026-08-25
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2608.25022v1

As people adopt transformer-based language models (e.g., ChatGPT and Gemini) for an increasing number of use-cases, it is important to know how such models learn and represent the meaning of the language, and to be more informed about what language is. This document is an attempt to help the reader understand how linguistic meaning (i.e., semantics) is approached from different fields of scientific and philosophical examination. I also explain three primary semantic theories: formal semantics, grounded semantics, and distributional semantics then compare how transformer-based language models differ from how humans learn language.

---

### EncoTESS: Age-Sensitive Encodings from Raw TESS Light Curves

Authors: Phil R. Van-Lane, Joshua S. Speagle, Ryan Cloutier, Christopher A. Theissen, Gwendolyn M. Eadie, Ilay Kamai
Published: 2026-08-25
Categories: astro-ph.SR, astro-ph.GA, astro-ph.IM, cs.LG
arXiv: https://arxiv.org/abs/2608.25019v1

Main sequence stars of spectral types late F through M exhibit systematic variability in photometric light curves, particularly when they are young. Rotational modulation of starspots manifests as quasi-sinusoidal variability, which enables the measurement of rotation periods. Variability can also be stochastic, as in stellar flaring. However, since measurements of stochastic processes depend on the time of observation, they are typically noisier. Considering that different manifestations of variability have unique observational nuances, models that naturally unify these are incredibly useful for stellar characterization. Towards this goal, we have developed EncoTESS: a Time Series Foundation Model (TSFM) trained on a subset of TESS 2-min light curves. EncoTESS is specifically designed to handle the observational noise, heteroskedastic measurements, irregular sampling, and large data gaps common to TESS data. It is also ~1% of the size of a typical literature TSFM, so can be run easily on a modern laptop. EncoTESS encodes light curves into a fixed-size latent parameter space, which can be used to infer physical stellar properties and recovers light curve summary statistics well. EncoTESS outperforms rotation period and variability amplitude as age indicators for stars that have not converged onto the slow rotator sequence yet; broadly these include K and M stars less than ~100 Myr, and M stars less than ~1 Gyr. We focus on age inference as an application of EncoTESS in this work, but other downstream tasks such as stellar classification could also be explored. The architecture of EncoTESS enables its future extension to TESS light curves of all cadences, and additional surveys such as Kepler and the upcoming PLATO mission. The core EncoTESS framework and library of encodings produced for the stars used in this work are publicly available at https://github.com/philvanlane/encotess.

---

### Rollout-Decoded Reconstruction for Long-Horizon Prediction in Latent World Models

Authors: Rishi Shah, Rishav Shrestha
Published: 2026-08-25
Categories: cs.LG
arXiv: https://arxiv.org/abs/2608.25017v1

A latent world model trains its decoder on latents anchored to observations, then deploys it on the model's own free-running rollout, hundreds of steps past the last observation. Rollout-Decoded Reconstruction (RDR) closes this gap with a single loss term that free-runs the model during training exactly as evaluation will, decodes every rollout latent, and penalizes reconstruction error against ground truth. The term adds no parameters, costs training-time compute only, and reduces to the standard objective at weight zero, so every comparison in this paper is a one-flag A/B. On the chaotic Kuramoto-Sivashinsky equation, RDR raises valid prediction time (the time to first crossing of normalized error 0.5) from $3.87 \pm 0.23$ to $6.97 \pm 0.42$ time units at an identical 193,568 parameters, a $1.80\times$ improvement confirmed on seeds never used in selection and holding in 10 of 10 preregistered configurations at ratios of 1.71-2.50$\times$. The results come from a single system; a sweep in which the advantage grows with latent width is descriptive, and control experiments on two classic tasks are preliminary.

---

### The Imperfective Paradox Is Not Necessarily in Large Language Models: A Benchmark Failure Before a Model Failure

Authors: Kaiqiao Han, Yizhou Sun
Published: 2026-08-25
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2608.25005v1

The imperfective paradox provides a useful test of compositional semantic analysis. Recent work constructs an NLI benchmark and reports that models frequently infer completed telic events from progressive descriptions, attributing this behavior to a Teleological Bias. It further argues that prompting interventions cause a Calibration Crisis. We reexamine the benchmark and conclusions and show that it is substantially affected by conceptual and evaluation mis-specifications. We identify three conceptual mis-specifications. In particular, Aspectual Reduction affects the benchmark construction, analysis, experiments, and conclusions. Under a strict NLI standard, 76% of Group A instances do not explicitly rule out culmination. In our native-speaker annotation, 38% of Group A examples and 29% of the Group C examples were judged to permit an alternative interpretation. To control these issues and lexical variation, we construct Lexically Matched Minimal Pairs. At the evaluation level, we formulate event-semantic NLI as a Multi-step Reasoning Problem and assess both intermediate semantic decisions and final predictions. Our results show that models often do not affirm culmination but nevertheless accept the corresponding simple-past hypothesis, a pattern we characterize as Sufficiency Bias. We further show that prompting interventions produce a Decision Shift among labels without reliably improving the underlying semantic understanding and reasoning. Intermediate and oracle-guided analyses identify two additional failure modes: errors in compositional aspectual classification and Surface-form Attraction toward surface-associated answers. Our experiments on Qwen-7B with suitable prompts, GPT-5.4, and Qwen-72B provide initial evidence for the context sensitivity of aspectual classification and suggest that these models can achieve performance comparable to that of human annotators.

---

### Does Fine-Tuning Undo Activation Steering? Behavioural Recovery Without Weight-Edit Reversal

Authors: Philipp E. Glass, Allan Tucker, Yongmin Li, Alina Miron
Published: 2026-08-25
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2608.24988v1

Activation steering can be embedded directly into a language model's weights, shaping behaviour without inference-time intervention and offering a way to encode alignment prior to release. However, models are routinely fine-tuned after deployment, and it is unknown whether embedded interventions survive this. We study the stability of embedded steering for refusal suppression and brevity induction across five instruction-tuned models (3B-14B) under non-adversarial SFT and RLHF. Behaviourally, preservation tracks the training data: steering degrades when optimisation pressure contradicts the targeted behaviour and persists otherwise, with refusal ablation losing 64% of its effect on average under SFT. Mechanistically, however, the weight edit survives almost untouched even where behaviour reverts: mean vector recovery is $ρ= 0.004$, and the fine-tuning update along the steering direction is near-orthogonal to its pre-edit weight pattern (mean $\cosθ= 0.074$). When steered behaviour degrades, fine-tuning does not achieve it by dismantling or reversing the steering mechanism itself. Embedded steering is therefore mechanistically durable but functionally vulnerable, and requires behavioural re-validation after downstream training.

---

### D$^3$-MOPD: Dynamic Domain ScheDuling for Efficient Multi-Teacher Distillation

Authors: Zechen Sun, Zhiwei Zhang, Fei Zhao, Juntao Li, Mu Chuan, Huayu Deng, Guojian Zhan, Wenliang Chen, Yao Hu, Min Zhang
Published: 2026-08-25
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2608.24987v2

Multi-teacher on-policy distillation (MOPD) distills several domain-expert teachers into a single student by minimizing per-domain reverse-KL divergence on the student's own rollouts. Existing approaches typically fix the per-domain data mixture before training, overlooking the fact that different domains converge at substantially different rates: some plateau early while others continue to improve throughout the training budget. A fixed mixture therefore wastes compute on fast-converging domains and undertrains slower-converging ones. To address this, we propose D$^3$-MOPD (Dynamic Domain ScheDuling for MOPD), a zero-overhead scheduler that repurposes the per-domain reverse-KL signal already produced during training to adapt the domain mixture online. Running asynchronously outside the training process, an off-process watcher periodically tracks each domain's KL trajectory, estimates remaining headroom and current improvement rate, and accordingly adjusts the domain sampling ratios without altering the core training loop. Our D$^3$-MOPD scales naturally to arbitrary numbers of domains, and the expected benefit grows as more domains introduce more diverse convergence patterns for the scheduler to exploit. On a Qwen3.6-35B-A3B student distilled from four domain-expert teachers, D$^3$-MOPD closes 97% of the average student-to-teacher performance gap, compared with 63% for vanilla MOPD, reaches the same peak performance with an approximately 3$\times$ reduction in rollout steps, and surpasses the specialist teachers on three of seven benchmarks.

---

### Solving Robust POMDPs with Omega-regular Objectives via Partially Observable Stochastic Games

Authors: Durgam Latha, Dion Reji, S. Akshay, Đorđe Žikelić, Shankaranarayanan Krishna
Published: 2026-08-25
Categories: cs.AI
arXiv: https://arxiv.org/abs/2608.24986v2

Robust POMDPs (RPOMDPs) generalize classical POMDPs to the setting where exact transition probabilities are not known -- rather, they are only known to belong to some uncertainty set of values. In this work, we study the problem of solving RPOMDPs with general omega-regular objectives, which subsume a broad class of objectives such as reachability, safety, and linear temporal logic (LTL) objectives. We show that, for (s,a)-rectangular RPOMDPs with polytopic uncertainty sets, the problem of solving RPOMDPs under omega-regular objectives can be reduced to solving partially observable stochastic games (POSGs) under omega-regular objectives. Moreover, we show for the first time that reductions can be constructed in both directions, establishing the semantic equivalence between (s,a)-rectangular RPOMDPs with polytopic uncertainty sets and POSGs. This allows us to derive a range of new computational complexity results, including both upper and lower complexity bounds, on solving RPOMDPs with different omega-regular objectives. As a corollary, we also derive new computational complexity results for RMDPs.

---

### Unsupervised Post-Training of Foundation Models: A Survey

Authors: Yijie Xu, Qianyi Cai, Huizai Yao, Yili Wang, Tianfu Wang, Cehao Yang, Xingbo Yao, Zhiyu Guo, Aiwei Liu, Xuming Hu, Weiyu Guo, Hui Xiong
Published: 2026-08-25
Categories: cs.CL, cs.AI, cs.CV, cs.LG, cs.MM
arXiv: https://arxiv.org/abs/2608.24982v2

Foundation-model post-training usually relies on human labels, preference data, stronger teachers, or executable verifiers. We study Unsupervised Post-Training (UPT): update-bearing adaptation on unlabeled inputs whose learning signal is derived from same-lineage model artifacts rather than an external oracle. We catalog 80 strict UPT methods and organize them by the object that supplies the update signal: a prediction statistic, a sample relation, a self-generated target, or an internal evaluator. Beyond inventory, we show how the choice of internal signal and task structure determines whether post-training improves the model or recursively amplifies error. An orthogonal Input Visibility $\times$ Update Persistence view maps deployment regimes and defines a unified framework for UPT selection and evaluation.

---

### FrontierChallenge: Evaluating Scientific Workflow Completion

Authors: Liangcai Su, Zhaopeng Feng, Zhuo Chen, Zhen Zhang, Xiang Lin, Ruilin Li, Handuo Zhang, Ning Wang, Kailong Wen, Yueqi Guo, Feng Xing, Yiling Guo et al.
Published: 2026-08-25
Categories: cs.AI, cs.CL, cs.SE
arXiv: https://arxiv.org/abs/2608.24979v2

Scientific agents increasingly analyze data, execute code, and produce research artifacts, yet most benchmarks emphasize final answers, isolated programs, or a single domain. We introduce FrontierChallenge, a cross-domain benchmark comprising 300 end-to-end scientific workflows. In this paper, we release and evaluate 97 of these tasks, spanning quantum chemistry, molecular dynamics, materials characterization, analytical chemistry, life science, and electrochemistry/environment. Each task provides fixed inputs and specifies a bundle of required scientific deliverables. We evaluate twelve frontier models with three agent scaffolds. Pass Rate measures the fraction of tasks satisfying the full-completion criterion, while Avg. Score captures partial progress. Each of the best-performing configurations completed only 20 of the 97 released tasks, yielding a Pass Rate of 20.6%. Partial progress translated especially poorly into complete delivery in analytical chemistry and electrochemistry/environment: Avg. Scores reached 87.6 and 94.9, but the highest Pass Rates were only 4% and 0%. Among non-passing Claude Code trajectories, 75.5% still ended with language claiming completion. Complementary HDS6 process scores correlate strongly with task outcomes, supporting FrontierChallenge as a benchmark of Heavy Duty Solver capabilities. These findings show that neither high partial scores nor confident claims of completion reliably indicate that a scientific task has been fully delivered, highlighting the need to evaluate end-to-end workflow execution and the completeness of scientific deliverables together.

---

### MSR-IVA: Masked Structural Residual Independent Vector Analysis for State-Aware Fusion of Structural MRI and Dynamic Functional Network Connectivity

Authors: Victor Solomon, Zening Fu, Rafal Angryk, Vince D. Calhoun, Jingyu Liu
Published: 2026-08-25
Categories: cs.LG
arXiv: https://arxiv.org/abs/2608.24978v1

Multimodal fusion of structural MRI (sMRI) and dynamic functional network connectivity (dFNC) can reveal how brain structure relates to changing functional states. When the same structural latent representation is coupled with multiple states, applying independent vector analysis (IVA) separately to each state can produce unrelated structural decompositions, while forcing identical decompositions may suppress state-specific relationships. In addition, not every subject expresses every dynamic state. We propose masked structural residual IVA (MSR-IVA), a state-aware framework that combines a shared structural representation with state-specific residual adaptations and masks for incomplete state expression. On an Alzheimer's Disease Neuroimaging Initiative cohort, MSR-IVA improved matched source coupling by 6.5% and reduced unmatched dependence by 15.7% relative to the independent pairwise IVA baseline. Among subjects expressing both states, mean absolute cross-state structural source correlation was 0.9177 for MSR-IVA versus 0.2978 for no sharing, demonstrating controlled structural sharing that preserves source correspondence while allowing state-specific adaptation.

---

### Retrieved But Not Reliable: A Survey on Attacks, and Defenses in Retrieval-Augmented Generation

Authors: Minh Tran, Cuong Dang, Tuc Nguyen, Khanh-Tung Tran, Minh Huynh Nguyen, Trinh Chau, Kien Le, Do Xuan Long, Jiahao Zhang, Fali Wang, Hoang D. Nguyen, Thanh Le et al.
Published: 2026-08-25
Categories: cs.CR, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2608.24977v2

Retrieval-Augmented Generation (RAG) enhances large language models by grounding outputs in external knowledge, improving factuality and reducing hallucinations. At the same time, the retrieval-augmented pipeline introduces new robustness and security risks, including corpus poisoning, backdoor attacks, privacy leakage, and fairness violations. Despite rapid progress in this area, existing surveys remain limited in their treatment of attacker objectives, threat models, and stage-specific defenses across the full RAG pipeline. This survey presents a unified and pipeline-aware overview of RAG robustness. We formalize threat models over the corpus, retriever, and generator, and organize attacks into three main objectives: accuracy, privacy, and fairness. We further review defenses from a pipeline-aware perspective, covering the retrieval, rerank, generation, and traceback stages. In addition, we summarize robustness benchmarks and explainability methods for more deeply evaluating and explaining RAG robustness.

---

### Clearing the Underbrush: AI-Enhanced RF Interference Suppression

Authors: Rahul Jain, Pierre Trepagnier, Rick Gentile, Joey Botero, Alexia Schulz
Published: 2026-08-25
Categories: cs.LG, cs.AI, eess.SP
arXiv: https://arxiv.org/abs/2608.24974v1

AI-based structured interference rejection has grown more popular because deep learning approaches can outperform traditional methods by jointly considering the signal of interest (SOI) and the signal mixture (SOI plus interference). This work builds on a previous AI-enabled approach utilizing autoregressive transformer-based models by adding a Finite Scalar Quantization (FSQ) tokenizer layer which aims to improve the interference rejection performance while keeping overall latency to a minimum. Additionally, we experiment with other inference optimization techniques with the goal of speeding up inference without much accuracy loss. We explore this space with an experiment where the SOI is a digitally modulated radio frequency (RF) signal and the structured interference is a digital television signal, an extremely common type of Orthogonal Frequency-Division Multiplexing (OFDM) transmission. Our results achieve low latency and increased interference rejection over traditional techniques and prior work with other AI-enabled methods. We demonstrate the benefits of the AI-enabled approaches via audio metrics such as Perceptual Evaluation of Speech Quality (PESQ). Additionally, we explore a variety of applications and detail how our interference rejection algorithm may be used in operationally-relevant scenarios.

---

### Resource-Efficient Pruning for Transformer via Low-Rank Importance Estimation

Authors: Peng Liu, Huibing Zeng, Yiqun Zhang, Yang Yi, Jigang Wu
Published: 2026-08-25
Categories: cs.LG, cs.AI, cs.ET
arXiv: https://arxiv.org/abs/2608.24973v1

With the rapid development of large-scale pre-trained language models based on Transformer architectures, their high computational and memory costs have become a major obstacle to deployment, especially in resource-constrained environments. Traditional pruning methods typically depend on full gradient-based importance estimation, and they necessitate prior finetuning of the model to achieve satisfactory performance. This process often results in intolerable resource consumption. This paper proposes REP-LIE, a new approach to enable resource-efficient pruning during the process of finetuning. REP-LIE leverages the gradients of LoRA low-rank matrices to estimate the importance of weights without requiring full gradient computation. To address the inherent randomness in importance estimation, a stability score is introduced, serving as the basis for iterative pruning of unimportant model parameters. The pruned model is further finetuned through lightweight updates, eliminating the need for full-parameter optimization in the process of finetuning. Extensive experiments on both medium-scale encoder models and large-scale generative models (LLaMA-7B and Mistral-7B) demonstrate that REP-LIE still achieves competitive performance compared to existing approaches.

---

### HCC+: Hyperbolic Guarding for Certified Attention Retrieval

Authors: Liangchen Ge
Published: 2026-08-25
Categories: cs.DS, cs.LG
arXiv: https://arxiv.org/abs/2608.24971v1

We study the Lipschitz stability of attention retrieval in hyperbolic spaces. Existing methods lack deterministic guarantees on attention-weight preservation under finite-precision representations. We introduce HCC+, a theoretical framework exploiting three properties of the Poincaré ball: exponential volume growth enabling query-independent boundary truncation; logarithmic covering radius of hyperbolic 1-centers enabling dimension-independent critical-key identification; and a packing bound with constants independent of the embedding dimension. We prove two deterministic guarantees: for exact retrieval, the per-layer attention deviation is bounded by 10\% of its ideal value; for soft attention, the total variation distance decays as $O(1/\sqrt{n})$, the rate of finite-sample variance. As a consequence of the guarding mechanism, the framework achieves a storage reduction factor of $6.1\times$ relative to FP16. We provide the first deterministic, query-independent retrieval certificate in non-Euclidean geometry.

---

### Physics-Informed Error Field Learning: A Post-Training Optimization Framework for Physics-Informed Neural Networks

Authors: Jiuyun Sun, Yong Zhang
Published: 2026-08-25
Categories: cs.LG
arXiv: https://arxiv.org/abs/2608.24970v1

Physics-Informed Neural Networks (PINNs) have emerged as an important class of numerical methods for solving partial differential equations (PDEs). However, during the late-stage optimization process, further parameter updates often yield diminishing accuracy improvements while increasing computational costs. To address this issue, this paper proposes a Physics-Informed Error Field Learning (PIEFL) framework for PINNs. Unlike conventional approaches that continuously approximate the solution field using a single network, PIEFL introduces an auxiliary error network after the primary network achieves satisfactory accuracy and shifts the learning objective from the solution field to the error field. By deriving error control equations under physical constraints, the error network learns the discrepancy between the current approximation and the exact solution, and the learned error correction is combined with the primary prediction to improve solution accuracy. The proposed framework avoids continuous optimization of the entire solution space and focuses computational resources on correcting existing prediction errors. Moreover, PIEFL requires no modification to the primary network architecture, making it compatible with existing PINN models and applicable as a general post-training optimization strategy. Numerical experiments on representative PDEs demonstrate that PIEFL achieves higher solution accuracy under the same computational budget, validating its effectiveness in improving the performance of PINNs.

---

### Targeting the Attention Heads Behind Object Hallucination in LLaVA

Authors: Armaan Sandhu, Abhilasha Senapati, Hima Kammachi
Published: 2026-08-25
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2608.24966v1

Vision-language models such as LLaVA-1.5-7B often hallucinate objects absent from the image when generating captions. We ask whether an interpretability diagnosis of this failure can guide a targeted fix, and we measure what that fix actually changes. We rank attention heads by how much their image attention drops around hallucinated object words, then screen the shortlist by ablating candidate heads and measuring the change in hallucination-token log probability, yielding a 32-head set. We restrict two interventions to these heads: a head-sliced LoRA adapter and an inference-time grounding controller. On 400 held-out COCO images, the combined method lowers CHAIRs (the fraction of captions with a hallucinated object) from 0.370 to 0.230 and CHAIRi (the fraction of hallucinated object mentions) from 0.156 to 0.096 (p < 0.001, paired sign-flip tests). Two controls sharpen attribution. A random-head LoRA control, matched layer-for-layer and trained identically, performs no better than the matched baseline on a separate 200-image control split, supporting the role of head selection rather than LoRA capacity. Under fixed decoding budgets, the CHAIR reduction persists and grows with budget (23% at 64 tokens to 58% at 128), arguing against a pure max-token or truncation artifact, although the method remains shorter and more conservative. The resulting behavior reduces unsupported object mentions while also lowering object recall (0.78 to 0.70). We present a diagnosis-to-intervention pipeline for object hallucination, and, more importantly, a controlled account of what acting on the diagnostic signal actually does: it localizes intervention sites with real, non-random leverage, reported as a behavioral profile rather than a single score.

---

### Common-Center Geometry and Certified Radial Reconstruction for Energy-Form Full Conformal Regions

Authors: Yiheng Feng
Published: 2026-08-25
Categories: stat.ML, cs.LG, stat.ME
arXiv: https://arxiv.org/abs/2608.24964v2

This note studies the geometry of full conformal prediction (FullCP) regions generated by an empirical energy-form pairwise score. Candidate-score convexity alone does not guarantee connected FullCP regions, even for empirical averages of losses convex in the candidate argument. For the energy-form score, each leave-one-out training comparison reduces exactly to a pairwise-dissimilarity sublevel condition. Under symmetry, a constant diagonal, a diagonal lower bound, and attainment of the associated Fréchet-type objective, all comparison regions share a minimizer; if they are convex, every nontrivial exact conformal region is star-shaped about that point. For power distances $ρ_β(x,y)=\|x-y\|^β$, this geometry holds for $β\ge1$, while the conventional energy score is strictly proper for $0<β<2$. For $d=1,β=1$, every nontrivial empirical-CRPS FullCP region is a nonempty closed interval (possibly $\mathbb R$ when $m=1$). For $1<β<2$ and $m\ge2$, explicit data-checkable derivative bounds give Lipschitz control of the radial exits and exact conformal radial function. Combined with directional root search and classical Lipschitz extensions, they yield certified inner and outer radial envelopes of width at most $δ+2\widetilde Lh_{\mathcal U}$ and same-ray Hausdorff guarantees. An analytic two-dimensional example shows why preserving star-shaped but nonconvex geometry can matter. A staged two-dimensional study finds modest but systematic tightening of the generic certificate and frequent robust nonconvexity witnesses, with detected normalized radial departures typically small. The method is intended for low-dimensional multivariate outputs rather than high-dimensional scaling or runtime improvement.

---

### Why and When Neural Networks Improve Local Approximation in Optimization

Authors: Chengkuo Bian, Pengcheng Xie
Published: 2026-08-25
Categories: cs.LG, math.OC
arXiv: https://arxiv.org/abs/2608.24963v1

Published experience with neural surrogates in derivative-free optimisation is contradictory: the same family of models that cuts the evaluation count of one solver leaves another unchanged, or makes it worse. We show that the contradiction dissolves once three factors are stated, and that these, rather than the fit accuracy a training curve reports, are what delimit when a learned local model pays. Role: a surrogate that proposes candidates the true objective must still approve helps, while one that replaces a gradient the solver depends on hurts. Radius: a model fitted to an optimisation path is reliable only inside a bounded neighbourhood, and its error neither vanishes as that neighbourhood shrinks nor survives its growth. Room: a surrogate can only accelerate progress the base method is still able to make. We formalise radius-aware local generalisation, relate it to the classical fully linear condition, and test each factor with the surrogate class, training pipeline and base method held fixed. Over 117 benchmark instances safeguarded assistance raises the instances solved to high accuracy from 67 to 84 while gradient replacement lowers them to 65; removing the gradient term from the training loss cuts surrogate acceptance from 0.703 to 0.148; and 1000 paired comparisons over ten noise levels show no noise threshold, only a base method that stops early. The same factors bound the gain: a model-based trust-region solver, which leaves little room, drops from 88 to 86 when the identical surrogate is attached, and released interpolation software stays ahead at 103, and on a Monte-Carlo inventory model repairing the acceptance interface is worth 10.40 cost units against 0.00 for the surrogate.

---

### Evaluating and Preventing Security Smells in AI-Generated Ansible Code

Authors: Pandu Ranga Reddy Konala, Vimal Kumar, David Bainbridge, Junaid Haseeb
Published: 2026-08-25
Categories: cs.SE, cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2608.24962v1

AI coding assistants generate Infrastructure as Code, yet no work has examined whether this code meets security requirements. This matters because security smells in infrastructure code propagate to deployed systems, producing infrastructure that is insecure and untrustworthy. We evaluate 16 AI models generating Ansible roles for Apache Tomcat v10 and MongoDB v7, analysing 278 Ansible roles against CIS benchmarks. Without security guidance, all 16 AI models produced code containing security smells, resulting in vulnerable infrastructure that fails compliance verification and underperforms code written by human developers. We introduce an approach integrating Ansible best practices and CIS benchmarks into prompts through an extended CO-STAR framework, enabling security smell prevention during synthesis rather than detection after deployment. When this approach is applied, 4 out of 16 models generate compliant code, with the leading model achieving 95%-100% CIS compliance, a fourfold improvement over humans at 23%-43%, with overall code quality improving by 19%-49%. The remaining 12 models fail not because they cannot generate code but because they cannot follow instructions with multiple constraints. For capable models, the approach requires no retraining and can be adopted through system prompts.

---

### GaussVLA: Geometry-Aware Spatial Reasoning for Vision-Language-Action Model

Authors: Md Selim Sarowar, Md Tanvir Islam, Sungho Kim, Sangtae Ahn
Published: 2026-08-25
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2608.24959v1

Vision-Language-Action (VLA) models encode visual observations as flat 2D patch tokens that carry no intrinsic geometric structure, and augmenting them with dense monocular depth injects per-pixel scalar values that encode neither surface orientation nor geometric confidence. This leaves the policy with limited structured spatial reasoning for action prediction. We propose GaussVLA, a Mamba-based VLA that incorporates two custom modules: Gaussian Spatial Tokenizer (GST) to lift frozen semantic and depth features into compact 3D Gaussian tokens, pools geometrically salient regions with learned queries, and \emph{Depth-Aware Chain-of-Thought (DA-CoT)} that performs structured, non-autoregressive geometric reasoning under language and flow-time conditioning. Across both simulation and real-world evaluations, GaussVLA demonstrates strong spatial-manipulation performance while remaining parameter-efficient. On LIBERO, it achieves 93.5% average success and 100.0% success on the Spatial suite with only 200M parameters, improving over SpatialVLA by 19.7% relative average success while remaining significantly more parameter-efficient.

---

### Can We Read the Mind of an Audio LLM? A Verbalizable, Multilingual Middle-Layer Workspace

Authors: Jiajun Fan, Jingyuan Li, Prashanth Gurunath Shivakumar, Qi Luo, Jia-Hong Huang, M. Maruf, Roger Ren, Yile Gu, Rahul Pandey, Ge Liu, Ivan Bulyko
Published: 2026-08-25
Categories: cs.SD, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2608.24958v1

An audio language model is a black box in a specific way: we see what it says, never what it works out on the way there, and chain-of-thought monitoring helps only if the model writes its reasoning down. Reading a base Qwen3-Omni with a logit lens at the audio-token positions, we find that the answer to a spoken question becomes legible - in words - in the model's middle layers, before it emits any token. Five findings follow. (1) The readout carries concepts in neither the question, the options, nor the model's own transcription: on a clip whose verbatim transcription is empty garbling, it reconstructs Watergate and scandal, passes through the role president, and resolves to Nixon - a hidden multi-hop chain, read with no chain-of-thought. (2) The content is language-agnostic: one audio-inferred concept surfaces in several scripts at once, and 38% of top-1 readouts are Chinese on English inputs. (3) It is paralinguistic: given the same clip as audio and as the model's own emotion-free caption, the audio mind forms the sound source, speaker role, or affect that the caption discards, and answers correctly more often. (4) The audio-driven signal is absent at the input, turns on about a tenth of the way into the network, separates most cleanly from the text prior in the middle band (35-80% of depth), and activation patching shows it is causally used and committed before the last fifth of the layers. (5) Deleting single layers maps the pipeline: reading the sound in is localized to the entry layers and answer delivery to the output layer, while retrieval is distributed across the interior. Throughout, a waveform-swap control - identical text, only the sound changed - isolates the audio-driven signal from a prior over the printed options. This is a qualitative account of what an audio model works out before it speaks: the quantities are controls, not benchmark scores.

---

### Synergising Local Geo-Environmental Characteristics with Spatial Context for Enhancing Landslide Susceptibility Mapping

Authors: Yusen Cheng, Lei Fan, Qinfeng Zhu, Cheng Zhang, Yangyang Li, Ron Mahabir
Published: 2026-08-25
Categories: cs.CV
arXiv: https://arxiv.org/abs/2608.24956v2

Data-driven methods are widely used in landslide susceptibility mapping (LSM) because they can effectively model the complex relationships between landslides and geo-environmental conditions. Existing data-driven approaches generally follow two types of data representations. Pixel-based models focus solely on the geo-environmental characteristics of a specific landslide but neglect the influence of its surrounding environment. Patch-based models incorporate surrounding spatial context but may include pixels with weak or no spatial relevance to the target landslide location. To address this limitation, this study proposes a Local-Geo and Spatial Context Fusion (LGSCF) strategy, which synergises the geo-environmental characteristics of landslide points with their corresponding spatial context through a feature-wise modulation mechanism. We tested the LGSCF strategy by integrating it into several representative convolutional neural network (CNN) architectures, creating nine different LGSCF-based models. The primary study area covers approximately 2644 km2 across Jenai and Sinyi Townships in Nantou County, Taiwan, and the dataset comprises 5332 landslide samples and an equal number of non-landslide samples. The results show that LGSCF-based models consistently outperform their corresponding baselines, achieving F1-scores up to 87.09% and AUC values up to 0.9472. Furthermore, the susceptibility maps produced by LGSCF-based models show that known landslides are more accurately concentrated in "very high" susceptibility zones with fewer misclassifications. These findings demonstrate that our fusion strategy can significantly improve the accuracy of landslide susceptibility mapping.

---

### AFDBench: A Reasoning-First AI Scientist for NationalWeather Service Forecast Discussions

Authors: Manmeet Singh, Somnath Luitel, Prabhjot Singh, Manraaj Banga, Naveen Sudharsan, Josh Durkee
Published: 2026-08-25
Categories: cs.LG, physics.ao-ph
arXiv: https://arxiv.org/abs/2608.24954v1

Large language models (LLMs) hallucinate numerical values when generating high-stakes meteorological text, posing risks for weather communication. We present AFDBench, an AI meteorologist that generates professional Area Forecast Discussions (AFDs) by reasoning through structured AI weather forecast data from Google's WeatherNext 2. We introduce AFDBench, the first benchmark for evaluating generative meteorological reasoning, comprising 7,732 expert written discussions from 13 National Weather Service (NWS) offices paired with real AI weather forecast inputs, and three complementary metrics: Met-Align (numerical accuracy), Style-Align (professional dialect adherence), and Input-Grounding (fidelity to source weather data). Zero-shot evaluations reveal that open-source LLMs achieve low Style-Align (~0.33) and moderate Input-Grounding (~0.88), failing to write in the professional NWS register or faithfully use their input data. We apply Group Relative Policy Optimization (GRPO) with domain-specific rewards targeting temperature accuracy, synoptic correctness, and format compliance. On 1,033 held-out samples from two unseen NWS offices, GRPO nearly doubles Style-Align from 0.318 to 0.619 and improves Input-Grounding from 0.881 to 0.940, demonstrating that reinforcement learning teaches a 7B-parameter model to write like a professional meteorologist and faithfully interpret AI weather data.

---