# Research Papers — 2026-09 · bundle page 145 of 266 > Full-text markdown of papers #7201–7250 of 13298 published in 2026-09, newest first. AI-readable mirrors of the full 13298-paper 2026-09 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-09/page/145 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/144.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/146.md) ### When Hiring Becomes Agent-Mediated: Evaluating Access and Recurrence in Two-Agent Résumé Screening Authors: Jian Gao, Hang Jiang Published: 2026-09-17 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.19530v1 Hiring is bilateral: employers assess fit, while candidates present and defend evidence of their qualifications. Yet résumé screening, the first gate, is commonly automated as a static, one-call judgment over a résumé-job pair. We study a two-agent alternative in which employer-side and candidate-side agents represent these roles, exchange evidence, and update their judgments before deciding who advances. We compare procedures on 600 constructed résumé-job pairs using GPT-5.5 and Claude Opus 4.7. Two-agent screening advances more applications (33.3% to 39.3% for GPT-5.5; 34.0% to 35.5% for Opus 4.7). Across three runs on the common 191-pair borderline pool, pass-instance rates rise from 4.5% to 26.2% and from 6.5% to 16.1%, respectively. This is not a uniform relaxation: two-agent screening rejects applications one-call advances, changing decisions in both directions. At similar pass volumes, the procedures advance different applications, and no one-call threshold recovers applications consistently selected by two-agent screening. Among discovery-selected cases re-executed in fresh runs, two-agent-only selections recur less often than shared selections, clearly under GPT-5.5 and less certainly under Opus 4.7, while a separate one-call follow-up shows no comparable decline. As hiring becomes agent-mediated on both sides, the screening procedure, not only the model behind it, shapes who reaches human review and how reliably that access recurs. --- ### Next-token functional estimation Authors: Milind Nakul, Vidya Muthukumar, Ashwin Pananjady Published: 2026-09-17 Categories: stat.ML, cs.IT, cs.LG, math.PR, math.ST arXiv: https://arxiv.org/abs/2609.19529v1 Suppose we observe the first $n$ points of a sequence of random variables having length $n+1$, and wish to estimate a functional of the unobserved final point and the empirical measure of the $n$ observed training points. Such next-token functionals include the probability that the next token is novel (also known as the surprise probability), the tail probability of the minimum distance between the next token and training points, and the test error of a classifier trained on the observed points. All of these quantities are classically estimated by the leave-one-out method, which is inconsistent under temporal dependence. We propose a leave-a-window-out estimator, which deletes a window of length $τ$ after each index before forming the empirical measure and reduces to leave-one-out at $τ= 1$. Under natural assumptions, we show that the error of our estimator decays at a parametric rate for any stationary $β$-mixing process that also admits a Marton coupling. Our results thus cover several natural functionals on a large class of stochastic processes. We complement these upper bounds with a sharp minimax lower bound for estimating the surprise probability on mixing Markov chains. Simulations on Markov chains, moving-average processes, and autoregressive processes show that our estimator succeeds in many scenarios where leave-one-out and add-constant baselines fail. --- ### AURORA: A Natural Language-Driven Agentic Framework for Understanding, Reasoning, and Orchestrating Reliable Air-Ground Co-Simulation Authors: Keshu Wu, Hao Zhang, Rui Gan, Xiangbo Gao, Xiaopeng Li, Zhengzhong Tu, Yang Zhou Published: 2026-09-17 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2609.19527v1 Air-ground transportation research increasingly relies on co-simulation, yet constructing scenarios remains labor-intensive and difficult to validate. More importantly, a generated scenario may execute successfully while failing to realize the spatial, temporal, communication, or behavioral relationships requested by the user. This paper presents AURORA, a natural-language-driven agentic framework that treats air-ground scenario generation as a process of compilation with verification. Central to AURORA is the Air-Ground Scenario Graph (AGSG), a typed intermediate representation that explicitly connects agents, aerial missions, events, communication links, success conditions, and their cross-domain dependencies. This shared representation enables simulator-grounded parsing, joint road-airspace grounding, temporal planning, pre-execution feasibility checking, trace-based runtime verification, failure localization, and bounded repair within a unified workflow. We further introduce AURORA-Bench to evaluate not only whether generated scenarios execute, but whether they faithfully realize the requested interactions. Experiments across multiple language models show that structured execution substantially improves reliability, while runtime verification exposes silent failures that completion-based evaluation overlooks. Localized repair further resolves many violations without regenerating the entire scenario. The results show that reliable scenario generation requires verifying realized behavior, not merely executable code, and demonstrate the value of explicit intermediate representations for verifiable and repairable language-driven co-simulation. --- ### Self Improvement via Fast Tree-search Authors: Xinghong Fu, Aravinth Kulanthaivelu, Yutaro Yamada Published: 2026-09-17 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.19526v1 Coding agents can recursively modify their own implementations, forming a loop of self-improvement. While prior work shows this can boost performance on coding benchmarks, existing approaches are costly and compute-intensive. We introduce a simple, sample-efficient self-improvement framework that significantly improves coding performance under strict budget constraints. We identify evaluation of candidate self-modifications as the main runtime bottleneck since prior approaches estimate their effectiveness by re-running a subset of benchmark tasks with the modified agent, which is time-consuming. We introduce Recursive Self Improvement via Fast Tree-search (SIFT), which augments these downstream task evaluations with an LLM-as-a-judge signal that performs pairwise comparisons between candidate patches, where the win-loss record is aggregated with a regularized Bradley-Terry model, and the resulting strength scores drive rank-based parent sampling inside a lightweight disaggregated tree search. Expensive downstream task evaluations are reserved only for the most promising nodes. Using a fully disaggregated tree search pipeline, the judge scores provide intermediate signal to guide exploration on promising candidate patches without being bottlenecked by slow evaluation runs. SIFT outperforms existing tree-search based self-evolution frameworks on the full Polyglot benchmark with significantly lower resource requirements in terms of CPU hours, wall clock time, and API cost. --- ### Compression Hurts, Pooling Helps: Information Loss in Rayleigh-Scale Estimation from B-Mode Ultrasound Authors: D. Hudson Smith, Ahmer Raza Published: 2026-09-17 Categories: eess.IV, cs.CV, stat.AP arXiv: https://arxiv.org/abs/2609.19525v1 Clinical B-mode images are widely available as potential data sources for quantitative ultrasound (QUS) analysis for tissue characterization. However, standard clinical ultrasound devices apply unknown log-compression to RF envelope data before display and storage. Previous work has demonstrated estimation of the underlying RF envelope statistics in the presence of an unknown compression law. Using Fisher information analysis, we show that finite-offset log compression causes severe information loss when estimating the Rayleigh scale $σ$, which controls diffuse speckle. For a single image window, unknown compression raises the minimum achievable variance for unbiased estimation of $σ$ by a compression-independent factor of approximately $\FisherMinInflation$. When $M$ equal-sized windows share the same unknown compression settings, the excess variance decays as $1/M$; even in the most favorable regime, reducing the variance inflation factor below $1.1$ requires $\FisherBestCaseWindows$ windows. Our analysis treats the contrast parameter $a$ as unknown and the boundary offset $b$ as known; estimating $b$ experimentally shows even larger variance. We validate this theory using synthetic estimation experiments and demonstrate RF-scale recovery on real RF-envelope windows from the OASBUD dataset. Together, these results clarify the limitations of using routine B-mode images for QUS. --- ### A Unified Evaluation Framework for Trustworthy Large Language Models, Agentic AI, and Multimodal Systems Authors: Shaina Raza, Ahmed Y. Radwan, Imran Liaquat, Kathryn Hume Published: 2026-09-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.19524v2 Benchmark scores alone provide an incomplete basis for assessing the trustworthiness of modern artificial intelligence systems. Large language models (LLMs), agentic systems, and multimodal models (MLLMs) require different forms of assessment, yet their evaluation evidence must remain interpretable for development and oversight. We propose a unified framework that connects output-level, trajectory-level, and cross-modal assessment through eight trustworthiness dimensions: capability, robustness, safety, fairness, transparency, governance, oversight, and efficiency. The framework preserves system-specific metrics while mapping native measurements to common performance bands, accompanied by uncertainty estimates and traceable evidence. A meta-evaluation layer examines the validity, reliability, and reproducibility of the evaluation itself. Multidimensional profiles expose strengths and weaknesses, while safety-critical overrides prevent aggregate scores from masking critical failures. Mappings to governance frameworks, international standards, and European Union regulatory requirements connect technical assessment with oversight needs. The framework provides a structured basis for assessing both system performance and the credibility of the evidence supporting it, with empirical validation across deployment contexts remaining an essential next step. --- ### EconSkills: Studying Skill Transfer and Retrieval for Web Agents on Live Economic Data Authors: Yinzhu Quan, Zefang Liu Published: 2026-09-17 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.19523v1 Web agents often revisit the same sites, yet most evaluations discard the procedures learned in earlier successful interactions. We introduce EconSkills, a skill library and evaluation framework that distills verified EconWebArena trajectories into parameterized standard operating procedures for retrieving live economic data. Each skill records its scope, navigation procedure, site-specific guidance, verification checks, and recovery steps while replacing source-instance values with placeholders. EconSkills separates two questions: whether a known relevant procedure transfers to a held-out task, and whether an agent can retain that benefit when selecting from a library. In controlled transfer, matched skills improve success over no-skill prompting and require fewer steps on paired successes, while abstraction is substantially more effective than replaying raw trajectories. At library scale, retrieval is competitive with the no-skill baseline overall and performs best on directly covered tasks; coverage-stratified outcomes show that approximate matches on uncovered tasks offset these gains. Browser trajectories further identify when procedural guidance shortens portal-specific navigation and when semantic verification remains necessary. These results establish that reusable economic web procedures can transfer across task instances and provide a concrete design target for coverage-aware selection and context delivery. --- ### LSTM-UT and Recurrent-Depth Transformers on Cellular Automata Authors: Aras Kavuncu Published: 2026-09-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.19521v1 Recurrent-depth Transformers apply shared computation repeatedly, but differ in how they retain information across steps. We compare a Block Universal Transformer (BUT), which carries only its current hidden state; CoTFormer, which also retains an expanding attention cache; and a new LSTM Universal Transformer (LSTM-UT) with bounded gated memory. On Rule 30 cellular automata, BUT extrapolates to unseen recurrent depths more reliably than CoTFormer, although its accuracy eventually degrades. State and cache interventions show that CoTFormer's failure depends on their interaction: correcting the current state can temporarily restore accuracy, while retained history can undermine that correction. In a delayed-recall task, BUT also outperforms CoTFormer despite lacking direct access to past states; CoTFormer does not reliably select the requested cached representation. LSTM-UT improves both depth extrapolation and delayed recall over these baselines. The results support bounded gated memory as an effective inductive bias for repeated computation and later retrieval in these tasks. --- ### An Architecture for Long-Horizon Agents: Levels, Ticks and Cascaded Intelligence Authors: Erik Nijkamp, Anurag Koul, Egor Pakhomov, Bo Pang Published: 2026-09-17 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.19519v1 Language-model agents are increasingly asked to carry out work spanning days or weeks, such as an operations remediation or a research programme. Such a task outlives any context window, any process and any interval at which a person can attend. In this paper, we argue that a long-horizon agent must run continually without forgetting before it can learn continually. This ability lies in the harness around the model rather than in the model itself. We derive seven bottlenecks from the long-horizon setting and answer them with a hierarchical architecture of three parts: (i) levels indexed by time scale, each keeping a bounded file summarising the level below; (ii) a clocked tick as the unit of autonomous action; and (iii) cascaded intelligence, where work is escalated to a more capable model only after failing review. We report on a ten-day campaign in which an agent built on this architecture reproduced a published reinforcement-learning result with a human attending once a day, and show (1) the agent kept the thread across every context reset and session boundary of the campaign, (2) operating knowledge written early changed later behaviour with no change to model weights, and (3) where learned components would enter such a system. Overall, our experience suggests continual learning for these agents needs a substrate outliving every context and process, and the checks the harness already runs are where a learner belongs. --- ### AMB3R-SLAM: Kilometer-scale SLAM with Hierarchical Backend Authors: Hengyi Wang, Lourdes Agapito Published: 2026-09-17 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2609.19518v1 We present AMB3R-SLAM, a real-time monocular SLAM system capable of reconstructing kilometer-scale trajectories over 10k frames on a single consumer-grade GPU. Our model couples a lightweight front-end for low-latency online tracking with a hierarchical backend that progressively enforces local, mid-level, and global consistency. By avoiding bundle adjustment that relies on the static world assumption, our system naturally handles complex dynamic scenes out of the box. Furthermore, we demonstrate that our method can be extended to leverage stereo, RGB-D, and LiDAR as additional inputs. AMB3R-SLAM achieves strong camera tracking performance across 9 datasets, reducing the absolute trajectory error (ATE) of previous state-of-the-art methods on VBR and Oxford Spires by over 70%. With additional LiDAR input, our model further reduces ATE to sub-meter level on KITTI and VBR datasets. --- ### LLM-as-an-Improver: Turning Verification into Better Candidates Authors: Akiyoshi Tomihari, Yuma Ichikawa Published: 2026-09-17 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.19515v1 Verifier-based selection improves LLM performance by generating multiple candidate solutions and using a verifier to select the most promising one. However, existing methods typically treat verification only as a ranking step and discard its feedback once a fixed candidate pool has been evaluated. In this paper, we ask whether verification can also improve the candidate set itself. To this end, we introduce LLM-as-an-Improver and propose Verify--Repair--Reselect (VRR), which uses verification feedback to generate and reselect improved candidates. VRR retains the initial winner while conditionally generating three complementary alternatives: repaired versions of the winner and runner-up, and a solution based on a new approach. It filters invalid and duplicate candidates using only inference-time information and then reselects the final answer under the original evaluation criteria. Across diverse models and code-generation and reasoning benchmarks, VRR improves over fixed-pool verifier-based selection in many settings and can recover correct solutions even when all candidates in the initial pool are incorrect. These results highlight a broader role for LLMs as improvers: verification feedback can not only select among existing solutions but also construct stronger candidates beyond the initial pool. --- ### QVAC Genesis III: A Large-Scale, High-Quality Open Synthetic STEM Corpus for Efficient Language Model Pre-Training Authors: Davide Vitabile, N. Ranjan, Akshay Nambiar, Kamal K. Gupta, Amril Nazir Published: 2026-09-17 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.19513v2 High-quality pre-training data is a critical bottleneck for educational and STEM-specific language models targeting edge AI and on-device deployment where token budgets are tightly constrained. While major organizations train ever-larger models on private corpora, the open ecosystem lacks STEM-focused synthetic datasets that deliver high per-token learning value efficiently for small models. To address this gap, we introduce QVAC Genesis III, a 191.43B-token, STEM-focused multi-domain synthetic corpus covering 19 domains across several difficulty levels and different educational styles. QVAC Genesis III is built via a dual generation strategy that performs targeted teacher distillation using a weak edge-scale student model as signal: the student's failures are converted into corrective explanations, while its successes are expanded into contrastive option-level reasoning over all answer choices. We further introduce an LLM-as-a-parser evaluation protocol that extracts final answers from free-form outputs and tracks both accuracy and answer validity. To validate the effectiveness of our QVAC Genesis III data, we conduct controlled from-scratch ablations with 1.7B-parameter models, showing that models trained with QVAC Genesis III consistently outperform both models trained with the open-source synthetic corpus Cosmopedia-v2 and the publicly released Cosmo-1B model across ARC, GPQA Diamond, and MMLU STEM benchmarks, achieving up to +28.57% on ARC-E and +21.35% on ARC-C, while reaching a Valid Answer Rate of up to 99.45%. --- ### CoreSense: Traceable Failure Recall and Conflict-Aware Belief Gating for Auditable Robot Decisions Authors: Zoe Li Published: 2026-09-17 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2609.19512v1 Robots can recall prior failures without knowing whether recalled evidence remains valid, conflicts with current observations, or is sufficient to guide a decision. We present CoreSense, a robot-system integration architecture that combines traceable episodic evidence with a conflict-aware belief gate and bounded, auditable recommendations. The gate checks scope, provenance, time, contradiction, and support before it permits PROCEED, requests re-observation, abstains, or escalates. Evaluation follows three complementary layers without commanding a physical robot: offline public real-robot data, a frozen signal-level simulation, and a live cloud deployment path. On CableTrace-120 and BotFails-200, belief gating reduces protocol-defined unsafe proceeds from 20% and 40% to 0%. A disjointly calibrated raw-video policy also reaches 0% unsafe proceed, but overblocks every nominal episode. On public data, a ViFailback-BotFails visual detector reaches 0.778 AUROC yet remains all-blocking, whereas cycle-disjoint UR3 telemetry for protective stops yields 0% unsafe proceed, 36.1% overblocking, and 61.9% coverage; grip-loss transfer remains a negative result. Controlled physical corroboration yields 3.3%, 0%, and 42.0%, while conflict-aware fusion yields 4.7%, 0%, and 42.8%. Finally, 20/20 cloud recalls validate a CockroachDB Cloud-Amazon Bedrock deployment path. The evidence supports an auditable integration pattern, not autonomous recovery or certified safety. --- ### FD-VAD: Semantic Endpoint Detection for Streaming Full-Duplex Speech Authors: Puneet Mathur, Dinesh Manocha Published: 2026-09-16 Categories: cs.CL, eess.AS arXiv: https://arxiv.org/abs/2609.35791v1 Natural turn-taking in full-duplex voice interaction requires determining from partial speech whether a pause reflects hesitation or a completed conversational intent. Acoustic voice activity detection lacks this semantic information, while cascaded ASR-based endpointing introduces transcription dependence and additional processing stages. We formulate semantic endpoint detection as a causal audio-language reasoning task and introduce FD-VAD, an ASR-free streaming endpointer that maps bounded causal audio windows directly to Continue/Stop decisions. FD-VAD combines a frozen speech encoder with a lightweight modality adapter and a parameter-efficiently adapted language model, using a last-chunk training objective for streaming inference. We further introduce confidence-gated endpoint commitment to control interruption versus delay and boundary-focused hard-negative sampling to improve decisions around ambiguous turn boundaries. Across in-domain and conversational evaluations, FD-VAD outperforms strong streaming and non-streaming semantic turn classifiers, and achieves the highest EOT recall among qualifying systems on TurnBench dev set $0.853$ (at FP<=0.10) in a zero-shot setting. These results show that semantic endpointing can be performed directly from streaming audio without intermediate ASR or dialogue state tracking. --- ### Sage: Formalization with Semantic Correction Authors: Thomas Hirtz, Farzad Jafarrahmani, Abdelmouksit Sagueni, Xiang Zhou, Wengping Deng, Liang Zhang Published: 2026-09-16 Categories: cs.LG, cs.AI, cs.CL, cs.LO arXiv: https://arxiv.org/abs/2609.35790v1 While neural theorem provers have achieved impressive milestones in formal mathematics, they largely operate on the assumption that faithful Lean 4 formal statements are already provided. Translating informal natural language into a formal language is a critical data bottleneck plagued by an "illusion of rigor": standard type-checkers accept statements that compile but drop hypotheses, introduce vacuous truths, or subtly alter mathematical bounds. To resolve this, we introduce Sage (Semantic Agent-Guided Formalization Engine), an agentic framework that replaces monolithic translation with a four-stage decomposed generation pipeline coupled with a dual-signal semantic correction loop. By pairing Lean 4 compiler diagnostics with multi-dimensional semantic feedback, our correction loop enforces mathematical fidelity alongside syntactic validity. By explicitly accounting for the gap between open-ended queries and declarative formal targets, our pipeline prevents models from achieving high formalization rates by guessing unverified answers (exhibiting a 70.9% answer leakage rate). Consequently, Sage suppresses leakage to 2.7% while achieving 73.3% pass@4 joint compilation and semantic fidelity on the Omni-MATH without proofs (compared to 42.0% for a fine-tuned Goedel-Formalizer-V2 baseline). Finally, on IMO-Unformalized, a novel frontier of 175 unformalized International Mathematical Olympiad problems, Sage demonstrates effective zero-shot generalization with 87.4% pass@4 verified fidelity compared to just 19.4% for the baseline, winning over 79% of blind pairwise evaluations. --- ### Don't Repeat Yourself: Self-Supervised Fine-Tuning for Coverage Authors: Eric Fithian, Kirill Skobelev, X. Y. Han Published: 2026-09-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.31688v1 In verifiable domains such as math and coding, finding one correct solution among many attempts can matter more than the pass rate of each attempt. Post-training can concentrate large language model outputs around a few modes, while increasing sampling temperature has limited effectiveness. We introduce Don't Repeat Yourself Supervised Fine-Tuning (DRY-SFT), a post-training method that increases output diversity and coverage: the probability of at least one correct solution among many attempts. DRY-SFT has two stages. First, for each problem, sequentially generate K solutions, showing the model all prior attempts and asking for a different solution. Second, fine-tune on each attempt independently, removing prior attempts from the context. The process uses no reward, verifier, or correctness filter. On HumanEval+, MBPP+, and DS-1000, DRY-SFT raises pass@100 by 10.8, 12.5, and 12.4 percentage points, respectively, at a small cost to pass@1. Structural diversity, measured by abstract syntax tree edit distance among passing solutions, rises significantly on all three benchmarks. DRY-SFT also solves 244 of 600 problems that the base model did not solve in the same 200 attempts. Across nine open-weight models, lower structural diversity of the base model significantly predicts larger DRY-SFT gains, indicating that the method is especially effective on more mode-collapsed models. --- ### Verification of PETSc with CIVL using LLM-generated ACSL contracts and deterministic driver generation Authors: Hansol Suh, Jan Hückelheim, Stephen Siegel Published: 2026-09-16 Categories: cs.CL, cs.MS, cs.PL, cs.SE arXiv: https://arxiv.org/abs/2609.31687v1 Parallel numerical libraries such as PETSc are widely used in science and engineering applications where wrong results can have costly consequences. Despite this, numerical libraries are rarely formally verified. One of the challenges is the need for an expert to hand-write a specification and manually apply a verification tool, often requiring the development of a harness or driver, all of which can contain additional bugs that lead to false positives or false negatives during verification. With recent advancements in large language models (LLMs), it is tempting to generate such drivers and reference models automatically, but one-shot generation based on a simple prompt is brittle and leads to additional unverified code that needs to be audited. In this paper, we present an approach to use LLMs in a limited setting to generate a small, human-certifiable ACSL contract from the function's documentation, combined with a deterministic toolchain that supports a restricted ACSL profile and generates a driver that uses the CIVL verifier to check the implementation against the contract and, when available, an existing reference model. We demonstrate the pipeline end-to-end on three PETSc functions: MatAXPY (reference model already exists), MatAYPX (no reference model, so the certified contract is the sole oracle), and the non-compressing mode of MatFilter (no reference model, with more complex, conditional behavior). With this pipeline, we were able to discover a bug in PETSc's MatAYPX function that was previously undiscovered and had been present in the code since 1997. --- ### 3-D Emissions Mapping and Social Cost Estimation for US Domestic Aviation at West Coast Hubs Authors: Hesam Shafiei Nia, Don MacKenzie Published: 2026-09-16 Categories: cs.LG, physics.data-an arXiv: https://arxiv.org/abs/2609.31686v1 Existing aviation emissions inventories lack accurate trajectory data for high-resolution social cost and health impact assessment. This paper develops a 3-D emissions map by reconstructing flight trajectories for US west coast hubs to estimate regional environmental and near-airport health impacts. A physics-informed autoencoder (AE) is applied to ADS-B trajectory records for January 2025 covering US west coast hubs. The encoder combines a Convolutional Neural Network (CNN), a Bi-GRU, and a 3-D CNN with skip connection; the decoder is a Temporal Convolutional Network (TCN). It is benchmarked against a baseline-AE and cubic spline interpolation. Emissions are mapped via EUROCONTROL Base of Aircraft Data (BADA) performance tables and ICAO Engine Emissions Databank (EEDB) emission indices, with altitude corrections via Boeing Fuel Flow Method 2 (BFFM2). Social costs are quantified for all flight phases, with health impacts assessed for Landing and Takeoff cycles within 50 km of each hub. The proposed AE model outperforms both a TCN-AE and cubic spline interpolation across 5% to 50% missing rates. Monetizing the emissions inventory shows NOx produces a small net cooling effect in direct climate forcing, while accounting for 99.7% of monetized air-quality and health cost despite being under 0.4% of CO2 by mass, making it the dominant health-cost driver. To our knowledge, this is among the first studies combining AE-based trajectory reconstruction with separate spatial-temporal feature encoding and altitude-based emissions modeling to produce a regional aviation emissions inventory for air quality, climate impact and population exposure. The resulting emissions map and social cost estimates provide quantitative context for environmental impact assessment and near-airport health policy evaluation for US domestic aviation. --- ### What does FFN compression change downstream? Same-state causal restoration in diffusion language models Authors: Shaurya Omar Published: 2026-09-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.31685v1 Diffusion language models (DLMs) enable flexible, parallel generation, but their iterative denoising remains computationally expensive, motivating increasingly aggressive compression. Existing compression objectives largely measure how well compressed computation approximates the original locally, but local error does not reveal which removed computations actually matter to the downstream denoising trajectory. We introduce Same-State Causal Restoration (SSR), which restores the original FFN on the exact current input reached by the compressed model and measures how the resulting trajectory changes. To our knowledge, this is the first direct measurement of the same-current-input closed-loop effect of removed FFN computation in DLM compression. Across LLaDA-8B-Instruct and Dream-v0-Instruct-7B, compressed-side state ranks this downstream effect substantially better than local NMSE at fixed denoising phase, while controlled interventions show that correction structure matters beyond magnitude. Using task-label-free calibration, SSR freezes a single restoration window for held-out inference. Under aggressive LLaDA compression, restoring only four transitions recovers 89.9% of the lost accuracy while retaining an estimated 36.8% whole-model MAC saving and outperforming an equal-budget local-error baseline. Dream further shows that restoring dense behavior and repairing the final task are distinct outcomes. --- ### The Temporal Tug-of-War: Visualizing and Detecting RAG Conflicts in Diffusion Models via Trajectory Variance Authors: Sravan Karthick T, Pranav Darshan, Pranav A, Minal Moharir, Ivan P. Yamshchikov Published: 2026-09-16 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.31684v1 Retrieval-Augmented Generation (RAG) introduces a specific failure mode in discrete diffusion language models: when retrieved context contradicts parametric knowledge, the iterative denoising process becomes a visible battleground between competing knowledge sources. We identify temporal semantic divergence as an observable for detecting these conflicts and introduce the Trajectory Variance Score (TVS), a simple and interpretable measure of this divergence. TVS computes the mean pairwise cosine distance of answer embeddings across independent stochastic denoising trajectories, capturing the temporal tug of war between parametric and contextual attractors. Requiring as few as two parallel inference runs, TVS is computationally lightweight. Across four diverse datasets (Synthetic, SciQ, PopQA, and CounterFact), a simple Logistic Regression classifier using TVS achieves $70.10\%$ accuracy and $0.7647$ AUROC on LLaDA. On Dream 7B, increasing the number of trajectories from two to five improves accuracy from $63.91\%$ to $69.62\%$. More complex sequential models provide only marginal improvements over the linear classifier. Evaluation across LLaDA and Dream 7B demonstrates that conflict-induced trajectory dynamics and their key properties transfer across distinct diffusion architectures. --- ### Autonomous Research Project Management as an Agent Skill: A Case Study in Exact Spectral Spatial Regression Authors: Alexander Chen, Jeffrey Meng, Bram Hoex, Tong Xie Published: 2026-09-16 Categories: cs.LG, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2609.31683v1 This work presents an end-to-end demonstration of autonomous machine learning research conducted by an agent skill on consumer hardware. The demonstration evaluates an FFT-based Kernel Ridge Regression (KRR) solver for regular spatial grids using 2005 monthly NOAA Kaplan SST v2 anomaly fields on a $36 \times 72$ grid. This was autonomously executed by DeepSeek V4 Flash, orchestrated by our agent skill suite within DeepSeek Harness (DSH). Experiments were executed on CPU-only hardware (Apple M2 Pro; 78.7 s solver time, 1.57 GB peak RSS). Long-horizon state was decoupled into a file-based epic- and issue-tracking substrate. Across 74 sub-agent sessions, the agent demonstrated closed-loop scientific resilience: routing two failed hypothesis review gates back to literature retrieval, patching bootstrap indexing bugs, and executing with only four discrete human steering events. Finally, we reflect on autonomous research governance, arguing that scientific credibility requires inspectable state, falsifiable review gates, and transparent reporting of negative results, urging the machine learning community to favour agent-accessible structured formats over static PDF manuscripts. --- ### Towards Transparent Diagnostics: Investigating Architectural Trade-offs and Explainability in Malaria Detection Authors: Suman Kunwar, Avishek Dangol Published: 2026-09-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.31682v1 More than 80 countries have reported malaria cases with 610 thousand deaths and are projected to increase. Identifying malaria early and accurately helps save lives. The effective way to diagnose malaria is through microscopic methods that are labor intensive and require experts with special equipment. Deep learning (DL) has shown promising results in medical diagnosis. Here, we explored various DL models: ResNet18, MobileNetV2, EfficientNet-B2, VGG19 and also proposed a model for detecting malaria presence using blood smears taken from the NIH Malaria dataset. Our experiment shows that MobileNetV2 achieved 96.35% accuracy with the smallest model size (8.49 MB) and fastest inference (1.35 ms). The proposed model achieved 97.67% accuracy, 0.9756 AUC with longest inference time (13.17 ms). The larger architecture outputs a larger model size with moderate accuracy. Upon further pruning, the proposed model gained a slight improvement in accuracy and inference time. The GRAD-CAM, SHAP and LIME shade explainable AI (XAI) insights of the model. --- ### Devanagari Handwritten Character Recognition Using TrOCR: A Transformer-Based Model with Real-Time Web Deployment Authors: Amrit Baskota, Samyam Budhathoki, Shubham Ghimire, Abiskar Ghimire, Sarwesh Phuyal, Baskaran P Published: 2026-09-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.31681v1 Devnagari is a one of the ancient language of the Indian subcontinent consisting of 36 vowels, 14 consonants and 10 numerals. The accurate recognition of handwritten Devnagari characters is challenging due to high complexity of Devnagari scripts. This paper presents a method to fine tune the pre trained TrOCR model to accurately recognize Devanagari handwritten characters. The Methodology consists of a preprocessing mechanism where input images are standardized into RGB format, tokenized in batches and integrated with Hugging Face Dataset. The pre-trained microsoft/trocr-base-handwritten model is fine-tuned over a dataset of nearly 5000 character images that are uniformly partitioned in the ratio 8:1:1 for training, evaluation and testing. Further optimization is done is the training process through mixed precision training, gradient checkpointing, and early stopping mechanism. The model achieves a character error rate (CER) of 3.95% and a character-level accuracy of 96.05%, outperforming the previous CNN based models. A scalable web application is developed using Vite.js, Golang, and FastAPI which practically deploys the OCR model and serves character recognition task with a latency less than 5 seconds per request. This study demonstrates the use of TrOCR model to build a scalable handwritten Devnagari character recognition system and also a foundation to future research on Devnagari Script Recognition using Transformers. --- ### Does Joint-Embedding Predictive Architecture Pretraining Help Time Series Forecasting? Authors: Yutong Feng, Bowen Liao, See Kiong Ng, Yuxuan Liang Published: 2026-09-16 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2609.31680v1 Joint-embedding predictive architectures (JEPA) have emerged as a promising self-supervised pretraining paradigm for time series, learning representations by predicting target embeddings in latent space rather than reconstructing raw signals. Yet evidence on their benefits remains mixed, and most studies test only a single backbone or a narrow set of architectures, leaving unclear whether JEPA pretraining is a reliable improvement or one that depends heavily on the downstream model. We address this gap through a large scale evaluation of one JEPA instantiation across nine backbones and eleven benchmarks spanning temporal and spatio-temporal forecasting, the most extensive cross architecture assessment of JEPA for time series to date. We find that the benefit of this instantiation varies sharply across backbones, producing consistent gains for some architectures and consistent degradation for others, even on the same dataset. This pattern holds across both task families, indicating the variability is a general property of this instantiation rather than a dataset specific artifact worth accounting for when choosing a backbone in practice. --- ### Toward AI-Assisted Poultry Coccidiosis Diagnosis: Evaluating Gemini and BiomedParse on Eimeria Microscopy Images Authors: Ali Alsalama, Ahmed Kubba, Manar Abu Talib Published: 2026-09-16 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.31679v1 Coccidiosis caused by Eimeria parasites is a major economic burden in poultry production, and effective control depends on accurate species-level diagnosis. This study evaluates whether a general-purpose multimodal large language model can support such diagnosis. Google Gemini was assessed on 4,225 mi- croscopy images covering the seven fowl-infecting Eimeria species under two prompting conditions, one without candidate labels and one with a predefined class list, and was further tested for pathology-report generation, while BiomedParse was examined for parasite segmentation. Without candidate labels, the model produced broad and taxonomically inconsistent outputs. With candidate labels, overall accuracy reached only 14.9%, with a strong bias toward E. tenella at 74% and no correct classifications for E. acervulina, E. mitis and E. praecox. Generated treatment reports were coherent but unverified, and segmentation was only partial. Current multimodal models are therefore not yet reliable for standalone Eimeria diagnosis without domain-specific fine- tuning and expert validation. --- ### When Keywords Drop but Classifiers Hold: Soft Refusals under KV Cache Compression Authors: Kang Chen, Xiuze Zhou, Hong Chen, Yuanguo Lin Published: 2026-09-16 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2609.31678v1 KV cache compression is widely used for long context LLM inference under memory constraints, while deployed systems typically score refusals after generation with keyword filters or learned classifiers. Such monitors are intended to indicate whether a model declined a harmful request under the serving regime actually used. However, it remains unclear whether matched compression that preserves task accuracy also preserves agreement between lightweight lexical monitors and stronger refusal classifiers. We study this with a paired protocol on n=200 harmful prompts with a long filler context: each prompt is answered once under full retention and once under matched eviction after a shared prefill, and the same replies are scored by keyword heuristics, the HarmBench Llama-2-13B classifier, an auxiliary LLM judge, and humans on disagreements. On Qwen2.5-3B, keyword refusal falls from 98.0% to 80.5% (McNemar p~1e-8) while classifier refusal stays near ceiling (99.0%-99.5%) and MMLU accuracy is unchanged (50.0%); human labels predominantly follow the classifier, consistent with soft refusals. The gap is not universal and weakens under short fillers and paired SnapKV, so safety auditing under compression should rely on several judges matched to the serving context rather than on keyword rates alone. --- ### A Comparative Transfer-Learning Study of CNN Backbones for Partial Face Recognition on the SoF Dataset Authors: Ahmed Kubba, Ali Alsalama, Abdelrahman Abdalla, Qassim Nasir, Manar Abu Talib Published: 2026-09-16 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.31677v1 Face recognition is widely deployed in surveillance, access control, and forensic workflows, yet accuracy degrades sharply once the face is occluded by accessories, foreground objects, or the frame edge. Because most faces in the wild are partial, robust partial face recognition (PFR) remains open. This paper compares three pretrained convolutional backbones, ResNet-50, VGG-16, and FaceNet, fine-tuned for PFR by transfer learning under identical preprocessing, splitting, and optimization protocols on the Specs-on-Faces (SoF) dataset. All three arms use a common 160x160 input and a frozen backbone with a trainable head under a fixed epoch budget and no per-backbone hyperparameter search. The FaceNet configuration, denoted PFN (Partial FaceNet), substantially outperforms the other two, reaching 97.4% test accuracy with macro-averaged 87.04% precision, 84.61% recall, and 84.17% F1 over the 112 identity classes, the highest accuracy and recall reported on SoF. --- ### An Evaluation of AI-Supported Evidence-Based Learning for Public Speaking Skill Development Authors: Sashini Hettiarachchi, Shahbaz Siddeeq, Mika Saari, Pekka Abrahamsson Published: 2026-09-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.31676v1 Public speaking is an essential skill in academic and professional contexts, but it often causes anxiety. Although several AI-based speech coaching tools exist, they typically provide generic feedback and lack model speeches for learning. This study addresses these gaps by developing a system that incorporates speech context into evaluation criteria, enabling more tailored feedback. It also generates improved model speeches in both text and audio formats to support example-based learning. The system was evaluated in a pilot study with seven undergraduate students over one to three weeks. Participants used the system repeatedly and practiced the same speech at least three times. Results showed improvements in public speaking performance for all participants. Filler word usage decreased, and anxiety levels dropped by 15.3% to 34.4%. Participants found the context-aware feedback and revised speeches useful and confidence-building. These findings suggest that context-aware feedback and model speeches can enhance public speaking skills and reduce anxiety. Future studies could explore video-based analysis of physical behavior during speeches. --- ### Active Causal Discovery Benchmark: Evaluating LLM Agents Under Budgeted Interventions Authors: Sagar Deb, Devam Shah, Ashwanth Krishnan Published: 2026-09-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.31675v1 We introduce the Active Causal Discovery Benchmark (ACDB), an SCM-grounded environment for evaluating whether LLM agents recover causal graph structure from observations and budget-constrained hard interventions. ACDB pairs a linear-Gaussian world generator with a fixed observe-intervene-submit API and a three-layer scoring contract that separates skeleton recovery, DAG recovery, and intervention efficiency. On the current six-level ladder, PC with a greedy active orientation heuristic is the strongest non-oracle method (directed F1 42.7%, SHD 4.79), ahead of Claude Sonnet 4.6 raw active (31.7%, 7.25) and GPT-5.4 raw active (22.9%, 9.27). The most informative diagnostic is the precision-recall decomposition: PC under-commits with high precision, LLMs over-commit with lower precision, and statistical-tool access often increases abstention rather than useful intervention. A structure-blind random DAG baseline reaches 23.6% directed F1 on this dense v0 ladder; a density probe lowers this floor to 16.9%, motivating the v1 calibration pass. The current results should therefore be read as a benchmark audit and calibration report, not as evidence that current LLMs solve active causal discovery. --- ### A Benchmark Framework for Screening Automation in Systematic Reviews Authors: Gauransh Kumar, Luciano Marchezan, Guillaume Genois, Kévin Delcourt, Eugene Syriani Published: 2026-09-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.30298v2 Systematic reviews (SR) are essential for evidence-based research, but their screening phase is highly time-consuming and labor-intensive. Large language models (LLMs) offer a promising opportunity to reduce this workload by assisting with article relevance classification. However, existing evaluation approaches often rely on traditional metrics that may be misleading for highly imbalanced SR screening datasets. This paper presents a benchmark dataset of $45\,064$ labeled entries for evaluating LLM performance in SR screening across 32 curated secondary studies. It proposes an evaluation framework that accounts for class imbalance, i.e., the natural prevalence of excluded articles relative to included articles in SRs. It also introduces PromptSR, a tool designed to support prompt experimentation, experiment management, and result analysis for LLM-based screening. We also present a use case demonstrating the application of SRBench and PromptSR. --- ### Bootstrapping Conversational Recommendation Agents At Spotify: Synthetic Data Generation and Self-Improvement Loops Authors: Enrico Palumbo, Alexandre Tamborrino, Victor Ode, Ben Lacker, Adrià Casas Escoda, Jeremy Hopple, Marcus Better, James Leoni, Hugo Galvão, Hugues Bouchard, Mounia Lalmas, José Luis Redondo García et al. Published: 2026-09-16 Categories: cs.CL, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2609.30297v1 Conversational recommendation agents are a new paradigm for content discovery, enabling users to express complex intents through natural language (e.g., "recommend Italian indie artists I haven't heard before"). A central challenge in building such agents is optimizing agent planning -- deciding how to select, sequence, and invoke tools -- particularly in cold-start settings where real user interactions are not yet available. We introduce a pipeline for multi-turn synthetic data generation and a self-improvement loop to address this challenge. The synthetic data pipeline transforms single-turn prompts into realistic multi-turn conversations, enabling systematic evaluation before launch. The self-improvement loop combines variance-based contrastive optimization with iterative refinement through a coding agent, automatically identifying and fixing planning and tool-use errors. Our approach improves quality by +8% on top of a highly optimized manual prompt. The system has been productionized and significantly accelerated iteration cycles for the launch of a conversational recommendation agent at Spotify. Online A/B tests demonstrate its effectiveness, with +14% user listening, +5% increase in weekly active users, and a 5% reduction in skip rate compared to a prior experience supporting only session refinement. This work provides a practical framework for accelerating the development of conversational recommendation agents in industry. --- ### TW3Cast: A Frozen Router of Lightly Fine-Tuned Foundation Models for Time-Series Forecasting on GIFT-Eval, Selected Entirely on the Training Split Authors: Nathan Thierry, Andre-Louis Rochet Published: 2026-09-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.28506v1 TW3Cast is a time-series forecasting system that reaches position 3 of 130 entries on the GIFT-Eval benchmark by mean MASE rank, as of 2026-09-14. The two entries above it belong to the leaderboard's agentic category, multi-step systems that use agents or language models to reason about, generate or select forecasts. TW3Cast runs no agent and no language model. Its selection is a table computed once on the training split and then frozen, and its experts are public foundation models lightly fine-tuned on those training splits. For each of the 97 dataset, frequency and horizon configurations, the table serves one of four modes: a specialist, which is a LoRA or full fine-tune of Chronos-2, TiRex or Toto whose training data was cleaned and enriched by explicit rules; a quantile blend that contains a specialist; a blend of base models; or a selection tournament played on a backtest carved from the training split. Every decision in the table was taken on that backtest. A specialist is admitted the moment it beats the tournament there, so a candidate costs a few megabytes and minutes of GPU time, and a failed candidate changes nothing. Three guarded mechanisms protect the selection from its own biases: a dual accuracy and calibration criterion, an asymmetric margin against candidates that saw the series during training, and conservative per-window gates. The selection rules themselves were chosen inside a temporal meta-backtest. The best base model served alone reaches a mean MASE rank of 33.8, the tournament served on every configuration reaches 38.0, and the full router reaches 19.4. The routing table, the expert index, the pinned base-model revisions, the submitted score file and the dated snapshot of the public scores are released, and every leaderboard number in this paper regenerates from them by one script. --- ### Semantic-Guided Fusion Network for Multi-Source Remote Sensing Image Classification Authors: Yuwei Zhao, Chuanzheng Gong, Baogui Huan, Feng Gao, Junyu Dong, Qian Du Published: 2026-09-16 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2609.27854v1 Multi-source remote sensing image classification has attracted increasing attention due to the complementary spectral, structural, and geometric information. However, existing methods still suffer from two limitations: insufficient semantic contextual modeling and unreliable feature fusion caused by slight spatial misalignment. To address these issues, we propose a Semantic-Guided Fusion Network (SGFNet) for multi-source remote sensing image classification. Specifically, the Semantic Mixing Convolution Block (SMCB) is designed to dynamically generate semantic-aware convolution kernels according to contextual relationships among feature representations. In addition, the Frequency Modulated Fusion Block (FMFB) is introduced to perform cross-modal interaction in the frequency domain, which effectively alleviates the influence of slight spatial misalignment and improves complementary information fusion. Extensive experiments conducted on the Augsburg and Houston 2018 datasets demonstrate that the proposed SGFNet consistently outperforms several state-of-the-art methods. The codes are publicly available at https://github.com/oucailab/SGFNet . --- ### The Drift Contract: Spectral Updates for Depth-Robust Local Learning Authors: Fabien Polly Published: 2026-09-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.26811v1 Local learning trains each layer with its own auxiliary loss and no global backward pass, which makes layer updates structurally parallel. Two problems have kept it marginal: accuracy degrades as depth grows, and hyperparameters are fragile. We apply Muon-style spectral update geometry (momentum orthogonalization with spectral step scaling) to per-layer local updates, an intersection not previously studied. On CIFAR-10 MLP benchmarks with local linear heads, a single step-size setting is the best value in our tested grids from width 128 to 2048 and from depth 12 to 48, while local Adam requires re-tuning along both axes and still collapses at depth 48 (31.3 percent re-tuned per depth, 19 percent with its depth-12 setting transferred, vs 42.7 percent for the spectral update at its unchanged setting). At five seeds and width 512 the spectral update leads local Adam by a clear margin (48.9 +/- 0.5 vs 46.6 +/- 0.3). Prospectively specified controls attribute the transfer and most of the depth robustness to the spectral geometry itself rather than to any step-size rule on top of it. We additionally formulate the step size as a drift contract, lr = epsilon / RMS(input), which bounds each layer's weight-induced pre-activation change per step, conditioned on its current input. The contract yields a small gain over the best fixed learning rate where that baseline is measured, makes the step size interpretable, and provides a per-layer, input-conditioned drift bound that standard optimizers do not offer. We report one negative result: with RMSNorm and weight decay in the trunk, the stability benefit of spectral updates accrues to global rather than local training, so the local advantage concentrates precisely where normalization is absent. --- ### AgroBench: A Reproducible Multimodal Benchmark for Weakly Supervised Crop Yield Learning from County Statistics and Pixel Observations Authors: Udaiveer Singh, Rajiv Ranjan, Shashank Tamaskar, Dharmendra Saraswat Published: 2026-09-16 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.26809v1 Reliable agricultural yield statistics are typically reported at coarse administrative scales, whereas modern geospatial machine learning methods require spatially explicit, pixel level supervision. This mismatch has limited the development of large-scale benchmarks for crop yield learning using multimodal Earth observation data. A reproducible benchmark, AgroBench, is presented for transforming publicly available U.S. county level crop yield statistics into weakly supervised pixel-level crop time series. Each crop pixel time series is paired with a county-level yield value as a weak supervisory signal rather than a directly measured pixel-level yield label. Our geospatial data generation pipeline integrates USDA crop yield statistics with crop-specific land cover masks, Sentinel 2 multispectral imagery, Sentinel-1 synthetic aperture radar observations, climatic variables, and terrain information to produce temporally aligned multimodal sequences describing individual crop pixels throughout the growing season. The resulting benchmark contains over 13 million observations from 788,654 unique crop pixels spanning 5,107 county year combinations across eight growing seasons (2017 to 2024) for five major U.S. crops. To facilitate standardized evaluation, we establish a crop yield prediction benchmark using a Leave-One-Year-Out evaluation protocol and provide baseline results using representative machine learning models. By releasing the complete data generation pipeline, benchmark dataset, and evaluation protocol, AgroBench provides a reproducible foundation for future research in weakly supervised learning, multimodal remote sensing, spatiotemporal modeling, and geospatial foundation models for agriculture. --- ### SPARC: SuperPixel-Aware Region Contrastive Learning for Self-Supervised Dense Prediction Authors: David Szczecina, Yuanpei Xiang, Jitao Hu, David Clausi, Yuhao Chen, Jason Deglint, Paul Fieguth Published: 2026-09-16 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.25067v1 Self-supervised learning (SSL) has become an effective approach for learning visual representations without manual annotations. Among SSL approaches, contrastive learning has been widely used for visual representation learning. However, existing contrastive SSL methods have focused primarily on image-level or pixel-level representation learning, while region-level representation learning remains less explored. We propose SPARC, a region-level contrastive learning framework that leverages superpixels to establish explicit correspondence between augmented image views. SPARC introduces a region contrastive branch that performs superpixel-based feature pooling and optimizes a region-level contrastive objective jointly with a global image-level objective. Under identical settings, SPARC consistently outperforms previous methods such as MoCo-v2 and DenseCL, achieving improvements of up to +9.79 mIoU for semantic segmentation and +4.88 AP for object detection. Ablation studies further demonstrate that region-level objectives produce the strongest performance. Thus, region-level contrastive learning is an effective approach for improving self-supervised visual pretraining for dense prediction tasks. Code repository can be accessed at https://github.com/xRIPEIx/SPARC. --- ### Understanding Reliability in LLM-based Human Behavior Simulation Authors: Pei Wang, Lei Wang, Yuanzi Li, Xu Chen Published: 2026-09-16 Categories: cs.CL, cs.CY arXiv: https://arxiv.org/abs/2609.25066v1 Large language models (LLMs) are increasingly used to simulate human survey responses and behavioral reactions, yet unreliable simulations can mislead social science conclusions. However, existing evaluations focus on end-to-end scores, leaving it unclear how different aspects of the simulation process interact to determine reliability. We propose ReliMap, which decomposes LLM-based human behavior simulation into three structured layers and evaluates reliability at both the individual level (R1) and population level (R2) across three configuration dimensions: model capacity, profile completeness, and population coverage. Through experiments across four simulation tasks and eleven LLMs, we find that all models exhibit substantial distributional bias without profile conditioning. Profile conditioning reduces this bias with diminishing returns. Larger models benefit more, and attribute informativeness matters more than quantity. Critically, R1 gains do not reliably transfer to R2--individual and population-level reliability can move in opposite directions. At the population layer, increasing coverage reduces variance but not systematic bias, with R2 stabilizing at around 50-100 individuals. These findings highlight that reliable simulation cannot be achieved by optimizing any single layer in isolation, but requires coordinated improvement across all three. --- ### Gradient-estimator design overcomes trainability barriers in neural-network-based variational optimization Authors: Yi-Ran Xue, Rui Wang, Baigeng Wang, Chenan Wei Published: 2026-09-16 Categories: cond-mat.dis-nn, cond-mat.str-el, cs.LG, physics.chem-ph, physics.comp-ph arXiv: https://arxiv.org/abs/2609.22342v1 Neural networks provide expressive representations for scientific computing. However, even sufficiently expressive networks can suffer training failure in weak-gradient regimes, limiting their practical use in quantum many-body physics and ab initio quantum chemistry. Here we derive an unbiased direct gradient estimator and introduce the adaptive minimum-variance phase (AMVP) estimator for neural-network variational optimization. By improving the signal-to-noise ratio of weak gradients, these methods enable reliable scientific calculations where training previously failed, while substantially reducing computational cost. The framework enables compact networks to outperform larger and fine-tuned default standard-estimator models with over an order of magnitude less GPU time on correlated flux models, and ultimately exceed the density matrix renormalization group (DMRG) accuracy. It further achieves chemical accuracy in N$_2$ bond breaking and, for the first time, in heavy-element I$_2$ with explicit spin-orbit coupling. These results demonstrate that gradient-estimator design expands the capabilities of neural-network variational methods for accurate scientific computing. --- ### Learning and Control Beyond Linearity: Towards a Non-asymptotic Theory for Bilinear Systems Authors: Yahya Sattar, Yassir Jedra, Robin Strässer, Frank Allgöwer, Maryam Fazel, Sarah Dean Published: 2026-09-16 Categories: eess.SY, cs.LG, cs.RO, math.OC, stat.ML arXiv: https://arxiv.org/abs/2609.22338v2 This tutorial provides a unified view of the emerging area of bilinear learning and control. Using linear systems as a benchmark, it explains what fundamentally changes in the bilinear settings, how recent theory addresses finite-sample learning and control, and how these ideas connect to broader themes in nonlinear control, representation learning, and data-driven decision making. For learning, we emphasize tools that are particularly useful in the bilinear settings, such as one-sided Bernstein's inequality for dependent and heavy-tailed covariates, blocking arguments, and martingale concentration for input-dependent noise. We then apply these tools to obtain finite-sample learning guarantees for fully observed bilinear systems, partially observed bilinear systems, and linear systems with bilinear observations. For control, we discuss quadratic control from bilinear observations, where the classical separation principle fails, and review tractable approaches based on belief-space receding horizon control. We also cover stabilization of bilinear dynamics under state feedback using semi-definite programming, LMI relaxations, sum-of-squares methods, and Koopman-based lifting. We conclude by discussing connections to reinforcement learning and machine learning, and some open problems in combined learning and control of bilinear systems. --- ### Dimensionality reduction for AI based hyperspectral image classification based on XAI Authors: Vladimir Zeljković, Branka Stojanović, Harald Ganster, Aleksandar Nešković Published: 2026-09-16 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.22333v1 This research addresses the challenge of limited material recycling in wood recycling processes by leveraging artificial intelligence (AI)-based dimensionality reduction. Our study explores the application of convolutional neural networks (CNNs) in multi-channel hyperspectral imaging (HSI), extending beyond RGB channels to over 200 spectral channels. Dimensionality reduction within this context involves streamlining the feature space for AI system training and inference. Focusing on explainable AI (XAI) methods, this paper contributes to a broader research initiative, presenting a solution framework that enhances the sustainability and efficiency of wood recycling processes. --- ### AffordanceWAM: Affordance-Aware Joint World-Action Modeling for Robot Manipulation Authors: Jiadi You, Qize Yu, Yue Chen, Minghong Cai, Zhide Zhong, Yuran Wang, Bowen Ping, Jiaqi Liang, Zhenhao Shen, Haodong Yan, Yinchuan Li, Ruihai Wu et al. Published: 2026-09-16 Categories: cs.RO, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2609.22332v2 Generalizable robot manipulation requires predicting how a scene will evolve, identifying where interactions are feasible, and determining how to act. Action-labeled robot videos directly supervise control but are costly and limited in diversity, whereas egocentric human videos capture diverse interactions but lack robot actions and differ in embodiment and appearance. We introduce AffordanceWAM, an affordance-aware generative World Action Model that represents object-centric spatiotemporal affordance through Scalar Affordance and Affordance Heatmap, within the generated future World. This representation grounds visual prediction in task-relevant objects and interaction regions for action generation, and provides shared interaction targets across human and robot videos. Built on a pretrained video diffusion Transformer, AffordanceWAM uses separately parameterized World and Action Experts, coupled through Masked Joint Self-Attention, to jointly predict future RGB observations, Scalar Affordance fields, Affordance Heatmaps, and continuous robot actions under a unified flow-matching objective. Human videos supervise all three future-World streams, whereas robot trajectories additionally provide action supervision, enabling transfer without human action labels or retargeting. Experiments on RoboCasa, CALVIN ABC$\rightarrow$D, and real-world manipulation demonstrate consistent gains over RGB-only and robot-data-only baselines. Under fixed robot supervision, RoboCasa performance improves monotonically as affordance-annotated human video scales. These results support affordance as an effective interface for both vision-language-action learning and human-to-robot transfer. --- ### Artificial Neural Networks as Surrogate Models in Black Box Optimization Authors: Md Khadimul Islam Zim, Martin Holeňa Published: 2026-09-16 Categories: cs.NE, cs.AI arXiv: https://arxiv.org/abs/2609.22329v1 Black-Box Optimization (BBO) is often applied in several engineering fields and can utilize an advancement of numerical measure- ments and simulation technologies. It deals with the optimization func- tions, where an analytical description is unavailable. It relies on meth- ods that require only an input point in the search space, paired with its corresponding objective function value, obtained through non-analytical means, e.g., sensors, experiments, or simulations. Common approaches include evolutionary optimization and other metaheuristics. Since BBO methods rely solely on objective function values, they typically require many evaluations, which becomes problematic when evaluating the ob- jective function is time-consuming or expensive. This leads to using surrogate-based optimization which evaluates selected true objective val- ues and trains a regression model to approximate the objective function across the search space. Surrogate-assisted black-box optimization is a small-data learning problem because the optimizer must approximate an expensive objective function from limited evaluations. Surrogate models act as data-efficient regressors, guiding the search toward promising or informative points under a restricted evaluation budget. In this paper, a new surrogate model using artificial neural networks, called Adaptive- Fidelity Nexus Covariance Matrix Adaptation Evolution Strategy (AFN- CMA-ES), is proposed for the selective evaluation of objective functions. The experimental results show its competitive performance compared to state-of-the-art surrogate-assisted BBO methods. --- ### Visual Graph Reasoning via Knowledge Compilation Authors: Rongzheng Wang, Zhe Wang, Ke Qin, Rongwei Wang, Muquan Li, Yizhuo Ma, Yihong Huang, Jielei Wang, Shuang Liang Published: 2026-09-16 Categories: cs.MM, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2609.22327v1 Visual graph reasoning requires answering graph-theoretic questions directly from graph images, where graph topology and state are conveyed visually rather than given in symbolic form. Despite recent progress of vision-language models (VLMs), current approaches to visual graph reasoning still fail on simple visual graph problems. This reveals a fundamental limitation of existing approaches: they prioritize final-answer supervision over the intermediate recovery of an explicit graph representation that preserves graph topology and state from visual input. To address this limitation, we propose VGCompiler, a compilation-centric paradigm for visual graph reasoning via knowledge compilation. VGCompiler organizes reasoning around two compilers: a representation compiler that recovers a structure-preserving intermediate graph representation from visual input, and an operation compiler that compiles query intent under the recovered graph state into an executable graph operation. Specifically, we build VGCompiler on Qwen3-VL-8B and train it with reinforcement learning guided by a layered reward over executability, compiled graph validity, representation quality, and operation quality. VGCompiler uses a frozen observer to summarize graph and question conditions into lightweight signatures, enabling archive retrieval and code reuse across similar regimes. Experiments on three benchmarks GVLQA, VisionGraph, and VGCURE, show that Qwen-VGCompiler, built on an 8B backbone, surpasses the strongest closed-source VLM baseline by 28.9% and the strongest code-based baseline by 23.7%, while maintaining high efficiency. We further evaluate VGCompiler on three real-world domains, including metro routing, logistics delivery, and network fault assessment, where it generalizes across heterogeneous visual graphs and domain-grounded tasks. --- ### ALPINE: Adaptive Localization for Parameter- and Sample-Efficient Few-Shot Learning Authors: Neeraj Yadav Published: 2026-09-16 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.22323v1 Few-shot learning research is predominantly evaluated on accuracy alone, with limited attention to the parameter and training-sample budgets required to reach that accuracy - a real constraint for practitioners without large-scale compute. We present an ultra-lightweight (22,249-34,917 parameter) spatial-relational architecture for few-shot image classification that combines fixed Gabor edge-energy guidance with a windowed, content-adaptive patch locator. Under a strictly matched, iso-episode-budget protocol (250 meta-training episodes, 5 canonical seeds, 600 evaluation episodes per seed), our architecture achieves 5-shot accuracy gains, consistent across all five seeds, over Prototypical Networks, Relation Networks, and MAML on both CIFAR-FS and MiniImageNet, while using 27-53% fewer parameters than any baseline. It also converges in fewer training episodes, generalizes better to an unseen fine-grained domain (CUB-200-2011 birds, zero retraining), and is more robust to 50% occlusion and 25% spatial translation than all three baselines. A series of falsification ablations - zeroing relational tokens at inference and retraining without them entirely - shows that the architecture's pairwise relational computation, while present, is not the primary driver of its performance; the content-adaptive patch locator is. We report this honestly, together with a capacity sweep showing a genuine accuracy plateau near 22-35k parameters, and release full seed-level results and checkpoint hashes for reproducibility. --- ### Elastic Threshold Attention: Learned Contextual Sparsity for Long-Context Decoding Authors: Themistoklis Haris, Henry Li, Maryam Karimzadehgan Published: 2026-09-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.20888v2 Massive KV caches can cause severe memory-bandwidth bottlenecks during long-context decoding. Sparse attention methods mitigate this problem, but often drop necessary context, leading to quality degradation. We introduce \textbf{Elastic Threshold Attention (ETA)}, an end-to-end trainable architecture that rivals dense model quality under hardware-aligned block-sparse decoding. ETA predicts dynamic, contextual thresholds directly from query representations, adjusting context retention depending on the task at hand. To learn this policy from scratch while enabling near lossless KV cache pruning at inference time, we filter attention logits through a shifted SiLU gate during training. We show theoretically and empirically that this creates a smooth, near-uniform attention floor that neutralizes sub-threshold value contributions while simultaneously causing localized attention sinks on initial tokens to disappear. To materialize these advantages, we implement a fused inference-time kernel in Triton that screens KV blocks in $O(1)$ time using cached geometric-probabilistic bounds. Across language modeling, reasoning, and RULER benchmarks, our 1.45B ETA model matches or exceeds dense quality, outperforming alternative fast decoding methods (Quest, H$_2$O, NSA) while achieving higher sparsity levels. Our kernel also achieves up to $2.15\times$ end-to-end speedups over FlashAttention-2 at context lengths of up to $512$K tokens. Finally, we introduce an offline calibration algorithm for domain-specific deployments that freezes per-head constant thresholds, cutting attention compute by an additional 27\% at no quality cost. --- ### BI-Agent and BI-Bench: Towards Automating End-to-End Business Intelligence Authors: Chuxuan Hu, Yeye He, Penny Zhou, Wee Hyong Tok, Daniel Kang, Surajit Chaudhuri Published: 2026-09-16 Categories: cs.LG, cs.AI, cs.CL, cs.DB arXiv: https://arxiv.org/abs/2609.20886v1 Business intelligence (BI) is a cornerstone of enterprise decision-making and is widely used by enterprise users in software such as Power BI and Tableau. In traditional BI workflows, users need to prepare data by (1) identifying relevant tables, (2) performing data transformations, and (3) building join relationships, before they can (4) answer their business questions. These steps can be complex and time-consuming, making BI challenging. Given the strong capabilities of large language models (LLMs) in working with data, we study their ability to answer BI questions end-to-end, without requiring users to manually perform the tedious preparation steps. To do this, we harvest a large collection of real-world BI projects from public sources, and manually extract pairs of (questions, ground-truth answers) from real user dashboards. The resulting benchmark, BI-Bench, is the first benchmark to systematically study LLMs' ability on end-to-end BI. We find that even frontier LLMs perform poorly on BI-Bench, with less than 50% accuracy. To address their limitations, we design a tool-augmented BI-Agent that decomposes BI workflows into subtasks on structured data, such as search, join, and transform, and orchestrates specialized data management methods across BI stages. Furthermore, we develop a post-training framework that synthesizes training trajectories from real BI projects, enabling BI-Agent to be further post-trained using both supervised fine-tuning (SFT) and reinforcement learning (RL). BI-Agent achieves substantial accuracy gains of up to 40 percentage points with vanilla LLMs, and post-trained BI-Agent yields gains of up to 30 points. Our results highlight the importance of combining tool-augmented reasoning with domain-specific post-training in complex BI workflows, and point to promising directions for future research. --- ### Sparse Priors for Efficient Distribution Learning Authors: Saumya Goyal, Barnabás Póczos Published: 2026-09-16 Categories: cs.LG, math.ST arXiv: https://arxiv.org/abs/2609.20883v1 Despite the widespread use and success of generative AI techniques today, theoretical guarantees on learning a distribution supported in $d$ dimensions from $n$ samples degrade as $O(n^{-1/Θ(d)})$, though shown to be minimax optimal. We hypothesize that present bounds are too pessimistic because smoothness assumptions are not enough to capture the structure of distributions that often appear in real applications. Consequently, we introduce the class of sparse priors and define the "Sparse Dimension" as a measure of sparsity of a prior over the space of all distributions. We show that distribution learning under a $k$-sparse prior achieves a Bayesian risk lower bound of $Ω(\sqrt{k/n})$ under common distance metrics, and show a matching (up to logarithmic terms asymptotically in $n,k$) upper bound for the TV distance under mild additional assumptions. We show the statistical equivalence of distribution learning and learning to sample in the Bayesian setting so that our results apply to learning to sample as well. While $k$ can still depend on the dimension $d$, or a notion of intrinsic dimension, our results show that learning under an appropriate prior overcomes the curse of dimensionality with respect to the dependence on $n$. --- ### Reinforcement learning for post-coronagraphic wavefront control Authors: Manuela Castañeda-Medina, Yann Gutierrez, Johan Mazoyer, Baptiste Abeloos, Laurent Mugnier, Olivier Herscovici-Schiller Published: 2026-09-16 Categories: astro-ph.IM, astro-ph.EP, cs.AI arXiv: https://arxiv.org/abs/2609.20880v1 Direct imaging of exoplanets is limited by the extreme contrast between the star and the planets, which is mitigated using a coronagraph. However, optical aberrations cause starlight leakage through the coronagraph, producing speckles that obscure the planetary signal. Achieving the required contrast levels demands wavefront control with subnanometric precision. Deep reinforcement learning offers a promising alternative to traditional focal-plane wavefront control techniques by enabling adaptive correction strategies learned directly from interaction with the system. In this work, we present a fully data-driven method for post-coronagraphic aberration correction in a simulated high-contrast imaging testbed. The agent controls a deformable mirror using observations consisting of focal-plane measurements (images) and physics-informed wavefront sensing information derived from these images. We evaluate different observation representations and control strategies, and the method is validated on simplified simulations of a high-contrast imaging testbed, where it successfully creates dark holes, i.e., regions of the focal plane in which residual starlight is strongly suppressed, while approaching the performance of conventional wavefront control methods. --- ### Cross-Lingual Parkinson's Disease Severity Assessment Using Pre-trained Speech Embeddings: A Multi-Class Evaluation Authors: Simon Pals, Cristian Tejedor-Garcia Published: 2026-09-16 Categories: eess.AS, cs.CL, cs.SD, eess.SP arXiv: https://arxiv.org/abs/2609.20875v1 Parkinson's disease (PD) often manifests through speech impairments, facilitating accessible, non-invasive, and cost-effective severity assessment for early diagnosis and progression tracking. Despite advances in speech foundation models (SFMs), their cross-lingual generalization for PD severity multi-class classification remains underexplored due to limited labeled data, a lack of explainable methods and variability across languages and datasets. In this work, we evaluate pre-trained embeddings from four state-of-the-art open-source SFMs across three datasets in zero-shot and k-shot cross-lingual settings for multi-class PD severity assessment. Our results show that pre-trained speech embeddings enable meaningful cross-lingual transfer, although performance is sensitive to dataset properties, preprocessing, and adaptation strategy. Misclassifications under these conditions related to inter-speaker variability and atypical speech patterns highlight the need for more robust feature extraction and modeling for PD severity assessment while emphasizing the importance of explainability for reliable clinical insights. --- ### The Refutation Gap: Certifying Both Halves of an Optimality Claim Authors: Rohan Pandey Published: 2026-09-16 Categories: cs.LO, cs.LG arXiv: https://arxiv.org/abs/2609.20873v1 Synthesis pipelines increasingly claim not just that a program is correct, but that it is optimal. Such a claim has two halves with radically different verification stories. The upper bound, "a program of size m exists", is witnessed by an artifact that can be re-executed, proved equivalent to its specification, and shipped with a machine-checked certificate. The lower bound, "no program of size m-1 exists", has no witness and is discharged by running a solver until it reports UNSAT. Combinatorial optimization has known this asymmetry for decades and has largely addressed it: certifying algorithms make it explicit (McConnell et al., 2011), and pseudo-Boolean proof logging can certify optimality end to end with a formally verified checker (Bogaerts et al., 2023; Koops et al., 2025). That discipline has not reached circuit minimization. We call this the refutation gap: published gate counts for minimal XOR circuits provide no certificate for either half of the claim, and neither did 121 optimality results we ourselves produced. We close the gap with a pipeline that synthesizes minimal linear straight-line programs over GF(2), where every decisive UNSAT answer emits a DRAT proof checked by an independent third-party checker. We certify all 121 optimality results established by the project, across n = 6 to 9: 111 carry independently verified refutations, 10 are closed by a free counting bound, and none disagrees with the uncertified value. The median proof is 1.1 MB and checking costs 1.9x solving. We give five case studies where verification caught defects that code review did not, report two interface obstacles that push practitioners toward the uncertified path, and describe an adversarial audit that revealed a failure tail we were about to attribute to the problem was actually caused by our own budget. ---