# Research Papers — 2026-10 · bundle page 10 of 156 > Full-text markdown of papers #451–500 of 7799 published in 2026-10, newest first. AI-readable mirrors of the full 7799-paper 2026-10 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-10/page/10 [← Previous bundle](https://aipod.dev/papers/archive/2026-10/page/9.md) [Next bundle →](https://aipod.dev/papers/archive/2026-10/page/11.md) ### Identifying Effective Strategies in Prompt Evolution for Stress and Emotion Prediction Authors: SeungHyun Yi, Seungjun Yi, Sriram Sattiraju, Haeun Park, Joakim Nguyen, Terence Lim, Joseph Skrovan, Mehak Beri, Hitakshi Modi, Eloy Carrion, Andrew Well, Carlos M. Mery et al. Published: 2026-10-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.21407v1 Early stress detection and risk prediction are crucial for timely mental health assessment and support. While large language models have recently shown promise for social media stress prediction, relying on accuracy can obscure false positives. Also, prompt revisions yield inconsistent gains across models and tasks, with unclear links to strategy combinations and instruction changes. By comparing six methods on social media stress and emotion data across two model sizes, we found that GEPA and its extension combining instructions from two prompts (GEPA+merge) improved prediction over initial prompts in several settings. We also identified five prompting strategies associated with development gains. These strategies included directing attention to emotional evidence, distinguishing current from past distress, illustrating indirect cues, requiring emotional context, and guiding label selection. Moreover, we documented four observations across tasks and evaluation settings. In a separate set of searches, binary stress prediction improved early, whereas multilabel emotion prediction initially declined and partly recovered. The other three concerned incorrect or conflicting instructions, gains on small comparison samples that did not hold on full development data, and changes in selected prompts' development and reported test rankings. These findings identify effective prompt evolution methods, strategy combinations associated with gains, and task and evaluation limits, providing guidance for applying prompt evolution methods to social media stress detection. --- ### MemCut: Every Secret Leaves a Trail in the Long-Term Memory of LLM Agents Authors: Cheng Zhang, Xuanning Cao, Zhicheng Zheng, Hui Xiong Published: 2026-10-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.21405v1 Long-term memory has become a crucial component of large language model (LLM) agents, with most research focusing on retrieving relevant information accurately and efficiently. However, a dependable memory system must also forget sensitive user data upon request. To evaluate this capability, we introduce MemCut, a systematic benchmark for user-requested forgetting. Its 456 hand-designed secrets in long-horizon conversations have fully annotated evidence trails to test recovery after deletion, including from messages that never state the secrets directly. We propose two recovery metrics. Native recovery measures reader success through the system's retrieval, whereas residual recovery measures the same reader's success when directly given surviving objects traced to annotated disclosures or evidence. We establish three reference deletion baselines to test how far existing retrievers and write models support forgetting across five memory designs and four LLMs. Disclosure removal reduces native recovery far more than residual recovery. LLM-guided deletion of ten additional turns from twenty retrieval candidates leaves 39-76% residual recovery. Subset sweeps (144 facts, three systems, two models) show that widening the pool at a fixed budget reduces residual recovery more than deleting all original candidates. These sweeps identify candidate coverage as a bottleneck in the reference baselines. --- ### Multi-Reward Hacking: From Aggregation-Induced Drift to Trust-Anchored Defense Authors: Yushu Li, Jiin Woo, Xiaoxiao Li, Youngsuk Park Published: 2026-10-15 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.21404v1 To improve task performance while encouraging desirable response properties, LLM post-training often combines a primary reward (e.g., correctness) with auxiliary rewards (e.g., brevity or efficiency). However, how these rewards are aggregated can critically affect training outcomes. We show that symmetric aggregation, which treats reward channels equally, can induce a failure where aggregate reward improves while primary-task performance degrades, even when individual rewards are meaningful. We investigate this aggregation-induced failure through a one-step multi-reward decision formulation, characterizing when it constitutes multi-reward hacking. We prove that, under symmetric aggregation, deterministic conditional-mean GRPO converges to auxiliary-favoring behavior when auxiliary rewards are more reliably obtained, regardless of initialization. We propose Trust-Anchored Gating (TAG), which first elects an anchor channel based on the policy drift induced by optimizing each channel alone, then gates auxiliary credit on anchor satisfaction. Unlike calibration-sensitive static reweighting, TAG structurally eliminates credit for auxiliary-only outcomes while preserving additional credit for joint success. In the same analytical setting, TAG provably reverses this selection, converging to the primary-favoring action from any initialization when the primary channel is anchored. Experiments across Qwen and Llama models on mathematics and program synthesis reveal substantial degradation under symmetric, constrained, and normalized aggregation, whereas TAG mitigates this failure. On Qwen3-4B with a brevity reward, TAG achieves 0.581 pass@4 versus 0.220 for additive aggregation, while shortening responses by 44% relative to correctness-only training. --- ### Beyond Invariance: Factor-wise Selective Treatment of Shifts for Multimodal Learning Authors: Guimin Hu, Qiwei Peng Published: 2026-10-15 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2610.21403v1 Distribution shifts pose a fundamental challenge to robust multimodal learning. Existing methods typically promote invariance by suppressing environment-dependent variations, implicitly applying a uniform treatment to shifted information. However, shifted information can have different predictive consequences: some contributes little to prediction, some remains reliably informative, and some exhibits environment-dependent predictive effects. This raises a fundamental question: which shifted information should be suppressed, preserved, or attenuated? To address this question, we propose FaShift, a factor-wise shift framework that diagnoses latent representation factors according to their distributional changes, intervention effects, and cross-environment stability. By factorizing multimodal representations and evaluating these complementary properties, FaShift distinguishes non-predictive factors, stably predictive factors, and predictively useful but unstable factors. It then selectively suppresses, preserves, or attenuates their contributions, rather than enforcing uniform invariance. Experiments on MOSI, MOSEI, and CH-SIMS show that FaShift achieves the best ID accuracy and F1 across all three datasets. Compared with the strongest competitors reporting OOD results, it improves OOD accuracy/F1 by 1.5/3.6 points on MOSI and 1.7/2.7 points on MOSEI, while achieving the best reported OOD accuracy and F1 on CH-SIMS. --- ### Fault Detection and Bit-Error Rate Diagnostics in Optical Wireless Links Using Edge-AI Authors: Sarthak Bhattarai, Sheshadri Shikhar Bandyopadhyay, Suprabh Dhakal, Jitendra Kumar Manandhar Published: 2026-10-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.21402v1 Optical Wireless Communication (OWC) systems provide high-bandwidth, spatially secure, and RF-interference-free digital transmission. However, direct free-space optical links suffer from extreme sensitivity to line-of-sight disruptions, optical attenuation, high ambient light saturation, and transmitter-receiver misalignment. Traditional channel diagnostic frameworks rely on external computing nodes or cloud-based processing, which introduces severe diagnostic latency and reduces edge node autonomy. This paper presents an autonomous, self-diagnosing optical wireless receiver node that integrates physical-layer signal telemetry extraction with an on-device TinyML classification engine. Built around an ESP32-S3 microcontroller, the receiver recovers 1000 bit/s On-Off Keying (OOK) digital payloads using a 5-sample majority voting mechanism while concurrently extracting real-time channel features: Bit Error Rate (BER), received signal voltage (Vsignal), Signal-to-Noise Ratio (SNRdB), and ambient light baseline (Lambient). Evaluated against a Random Forest baseline (77.22% accuracy) and a floating-point neural network (78.48% accuracy), a post-training INT8 quantized TensorFlow Lite Micro model occupying only 3.32 kB of SRAM runs directly on the receiver firmware. The quantized model achieves 74.68% overall accuracy across four distinct operational conditions: normal transmission, optical filter attenuation, ambient light interference, and severe obstruction/misalignment. On-device deployment tests confirm real-time, deterministic fault classification, establishing a practical approach for self-aware optical IoT nodes. --- ### Watts If? A Benchmark for Counterfactual Reasoning About the AI Data Center Buildout Authors: Pankaj Chouhan, Rajarshi Das, Aditya Dubey, Manminder Tomar, Sreekar Reddy, Samta Sharma, Satyapragnya Kar, PR Panigrahi Published: 2026-10-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.21397v1 An AI data center is committed years before it draws a watt: a few discrete choices (grid or on-site gas, evaporative or dry cooling, which county to file in) fix its capital, water draw, and carbon path, and LLMs are now asked to help screen them with no test of whether they track what each commitment rules out. We introduce DCBench-440, with two arms reported separately: 200 generative questions over STRIPS worlds for five US deal archetypes, with search-verified gold answers and no tested shortcut above 12% on any question type, and 240 multiple-choice questions grounded in quoted site records, emission equations, and stated scenarios. Across open-weight deployments, accuracy spans 12.5-71.5% (generative) and 58.3-92.5% (multiple choice). One skill fails everywhere: asked to list every action available at a decision gate, no model exceeds 4.0% exact match. The strongest list 72-85% of the actions that would change the project's state but omit most permitted actions that change nothing; with those excused, the best exact match is still 24%. Code, data, and other materials are available upon request. --- ### When do quantum views help? Complementary classical-quantum representations in multi-view fusion Authors: Azadeh Alavi, Fatemeh Kouchmeshki, Hossein Akhoundi, Yongli Re, Abdolrahman Alavi, Muhammad Usman Published: 2026-10-15 Categories: quant-ph, cs.AI arXiv: https://arxiv.org/abs/2610.21395v1 Recent studies have reported promising results from quantum machine learning in drug discovery, healthcare, materials science and cybersecurity. Research includes comparisons with classical machine learning algorithms and the development of sequential hybrid pipelines. We propose that fusion can improve prediction when classical and quantum representations capture complementary predictive relationships. Our classical-quantum multi-view framework preserves the full classical input alongside simulated quantum features. Concatenation and attention combine the views; single-view comparisons, replacement and masking controls assess both views' contributions. Controlled angular-polynomial experiments distinguish targets adequately represented by a single view from those that depend on complementary angular and polynomial relationships. For these mixed targets, fusion improves prediction by combining the relevant feature sets, while matched classical representations recover the same benefit, linking the improvement to their complementary predictive content. Controlled classification tests further show that gains depend on alignment between the chosen representation and the target, and on a suitable fusion rule. Benchmark validation shows improved mean predictive performance over classical baselines on Wine, Wisconsin Diagnostic Breast Cancer, three-class Fashion-MNIST and Steel Plates Faults within the evaluated protocols. Classical replacement and masking controls remain competitive, classical baselines lead on Digits and Covertype, and outcomes with missing or corrupted views depend on the available inputs. These findings support evaluating quantum representations for their complementary predictive contribution and matching the representation and fusion strategy to the target relationships. --- ### Matoi: Selective Revalidation of Consequence Evidence for Agent Authorization Authors: Zexun Wang Published: 2026-10-15 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2610.21394v1 Matoi separates reusable consequence evidence from current execution authority and durable occurrence history. Its finite query-aware contract covers branches, ordered collections and negative lookups. A consumer reuses only its own checked evidence whose observations remain valid; signed requests, live grants, quota and uncertain outcomes remain separate obligations. Conditional correctness arguments distinguish locally serialized claims from nontransactional remote effects. Two studies strengthen cost attribution and domain evaluation. A 1,440-cell matched-wire study repeats 144 authored inputs. With compact input bytes identical, reuse reduces complete lifecycle cost by 3.49 percent in JS and 1.79 percent in Python. Combined representation/reuse reductions against full proof are 10.87 and 16.53 percent; five of twelve family intervals for the matched comparison cross one in each language. A prospectively frozen AgentDojo Banking mapping covers 5/16 user plans and 7/9 attack plans. Both governed strategies preserve five exact benign transfers and refuse 35 reused attack-plan/policy crosses. Pre-satisfied utility predicates are reported separately from completed work. These are original scripted synthetic tools, not autonomous agents or a real bank. Earlier studies retain cheaper protected-cache alternatives, policy-compatible phishing, provider duplication and post-claim revocation. Separate JS/Python consumers establish finite-profile interoperability within the same project; durable recovery rechecks evidence and retains uncertain reservations. The results support a bounded, auditable reuse and execution contract, not a new general incremental algorithm, arbitrary-tool closure, atomic third-party commitment or production superiority. --- ### Self-Guided LLM Reasoning for Error Diagnosis in Vehicle Routing Problems Authors: Ni Zhang, Jianan Zhou, Yue-Jiao Gong, Zhiguang Cao Published: 2026-10-15 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.21393v1 Vehicle Routing Problems (VRPs) are fundamental to many real-world applications. Recent advances in large language models (LLMs) have spurred progress in solving these NP-hard problems. However, most existing approaches assume that input instances are error-free, neglecting the presence of faults commonly encountered in real-world data. In this work, we systematically investigate the capability of LLMs to detect (and correct) errors in VRP instances, and identify key limitations, particularly in handling complex instances or errors that substantially increase the LLM's reasoning burden. To overcome these challenges, we propose a self-guided reasoning framework in which LLMs autonomously generate code that provides structured insights to aid in error diagnosis. Experiments across diverse problem settings and LLMs demonstrate that our framework significantly improves error detection performance, achieving near-perfect accuracy. --- ### Learning to Reason with Selective Internal Feedback Authors: Xun Lu, Shumeng Yang, Xinrui Wang, Songjun Tu, Linjing Li, Daniel Dajun Zeng Published: 2026-10-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.21392v1 Reinforcement learning from internal feedback can improve language models without ground-truth answers or external verifiers. However, confidence and correctness can diverge during training, and continued optimization of average self-certainty can increase confidence while degrading reasoning accuracy. We introduce SIF, a reinforcement learning method that combines comparative reward construction with selective policy updates. SIF compares ranked token-level self-certainty profiles across multiple windows and peers, assigning positive rewards only when both levels of voting provide sufficient support. Sample and group level filtering determines which responses contribute to policy optimization. Experiments on three backbones across 12 mathematical and scientific reasoning benchmarks show that SIF's final checkpoints achieve higher average accuracy than the best-validation checkpoints of Intuitor and Vigor, with a gain of 4.71 percentage points over Intuitor on Qwen2.5-Math-1.5B. Further analyses show better retention of accuracy during continued optimization, while test-time training experiments demonstrate sustained improvements with as few as four rollouts per prompt. --- ### PriorityFEC: Deadline-Aware Streaming FEC for KV-Cache Handoff in Edge Multi-Agent Systems Authors: Han Shen, Qifu Tyler Sun, Fanyang Meng, Ye Wang, Yongsheng Liang Published: 2026-10-15 Categories: cs.NI, cs.AI arXiv: https://arxiv.org/abs/2610.21390v1 Multi-agent large language model (LLM) systems are increasingly deployed at the edge to support complex tasks that require collaboration and information exchange among multiple agents. However, when task contexts are passed across agents, shared context that has already been processed by upstream agents often needs to be prefilled again, resulting in substantial redundant computation. Reusing an already prefilled key--value (KV) cache can avoid this recomputation, but requires the reusable KV state to be transferred across the network before the receiving agent can begin generation. Under strict time-to-first-token (TTFT) deadlines and unreliable edge links, delivering the complete KV cache may be infeasible, making it necessary to prioritize and protect the most valuable KV information within a limited transmission budget. This paper proposes PriorityFEC, a utility-aware KV-cache handoff scheme that jointly exploits model-side KV importance and transport-side reliability. PriorityFEC first constructs a utility-aware source stream by placing high-utility KV blocks at earlier transmission positions. It then protects the ordered stream using a feedback-adaptive Streaming Forward Erasure Correction (FEC) mechanism, which schedules repair packets according to receiver feedback before the TTFT deadline. We implement PriorityFEC on a distributed edge LLM serving prototype and evaluate it with Qwen2.5-7B-Instruct and Llama-3.1-8B-Instruct across multiple datasets. Results show that PriorityFEC achieves superior task quality over the compared transport schemes, with its advantages becoming particularly pronounced under stringent deadline constraints. These results demonstrate the importance of jointly optimizing KV-cache utility and deadline-aware transport reliability when reusable LLM state must be handed off across unreliable edge networks. --- ### Calibration Language Shapes Block-Influence Pruning in Multilingual Language Models Authors: Vedant Pandhare, Piyush Dhoka Published: 2026-10-15 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2610.21383v1 Block Influence (BI) ranks Transformer blocks for depth pruning from their input-output cosine change, but the ranking depends on the calibration distribution. We study whether English calibration transfers to Indian languages in Qwen2.5-1.5B-Instruct, Llama-3.2-1B, and Gemma-2-2B. English, Hindi, Marathi, and Tamil use disjoint Wikipedia articles for calibration and evaluation; every selector receives the same 150-chunk budget, and Tamil is excluded from multilingual aggregation to test cross-script transfer. Across all three models, late-block BI is 20.7-55.5% higher for the three Indian languages than for English, and every predeclared late-minus-middle contrast has a 95% bootstrap interval above zero. This mismatch changes the low-BI blocks selected for removal despite high global rank correlations. Averaging BI over equal English, Hindi, and Marathi budgets mitigates the resulting perplexity damage for Qwen at six removed blocks and for Gemma at all tested depths, including held-out Tamil. The mitigation is not universal: on Llama, balancing improves Hindi and Marathi at two removed blocks but severely harms Tamil, while larger pruning budgets select the same blocks and collapse perplexity regardless of calibration. Rank-mean and minimax-rank aggregators do not dominate the raw mean. These results support a diagnostic claim rather than a universal pruning rule: English-only BI systematically misses late-layer activity for Indian-language text, but multilingual calibration must still be validated per architecture and pruning budget. --- ### RDL-Bench: A Benchmark for Task-Aware Question Answering over Relational Databases Authors: Yao Cheng, Siqiang Luo Published: 2026-10-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.21382v1 Relational databases (RDBs) remain the primary infrastructure for storing and managing structured data across enterprise and scientific domains. Natural-language (NL) interfaces to RDBs aim to let users ask questions without writing SQL, but real user needs go beyond SQL-style lookup: some questions require reasoning over the observable database state, while others require predictive inference from historical relational records under temporal constraints. Existing benchmarks address these goals in isolation. To address this gap, we introduce RDL-Bench, a benchmark for task-aware question answering (QA) over real RDBs. RDL-Bench organizes diverse user questions into reasoning-oriented questions, whose answers are determined by the current database state, and prediction-oriented questions, whose answers depend on future outcomes under temporal constraints. Each instance contains an NL question, task metadata, schema information, temporal context, either executable evidence or target-construction logic, and denotation-level ground truth. RDL-Bench supports two evaluation settings: native solvers under their intended capabilities, and task-aware modular systems where a router dispatches each question to an appropriate execution module. --- ### Perception or Reasoning? Diagnosing and Tackling Reinforcement Learning Bottlenecks in VLMs Authors: Zeyuan Yang, Zhuohao Chen, Jiaben Chen, Yao Zhang, Maohao Shen, Chuang Gan Published: 2026-10-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.21380v1 Reinforcement learning has brought strong gains to language model reasoning, but its improvements on visual tasks remain less consistent. One difficulty is that visual task failures can arise from different sources: the same benchmark may be limited by perception for one model and by reasoning for another. We introduce Perception and Reasoning Attribution (PARA), which measures the remaining perceptual and reasoning headroom of each model--benchmark pair by comparing how many current errors are recovered with more accurate visual information versus a stronger reasoner. Across 4 vision-language models and 17 multimodal benchmarks, PARA broadly agrees with the expected characteristics of existing benchmarks while revealing substantial model-specific variation. More importantly, it shows that RL gains become smaller as perceptual headroom increases, but larger when reasoning explains more of the recoverable errors, suggesting that current RL exploits reasoning headroom more effectively than perceptual headroom. Motivated by this gap, we analyze how existing RL objectives affect visual perception and find that reward- and token-level signals influence visual attention only indirectly. We therefore propose GRAD, a group-relative attention distillation objective that uses the best rollout in each group to directly guide the visual attention of weaker rollouts. GRAD consistently improves performance across two model scales and seven benchmarks, and further complements existing RL methods. --- ### DPA-MoE: A Runtime Precision Control Framework for MoE Inference Authors: Jaeyun Kim, Hoonki Lee, Susie Shin, Hyunmin Kim, Dahyun Lee, Sangyeob Kim Published: 2026-10-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.21378v1 Mixture-of-Experts (MoE) models reduce computation by routing each token to a small set of experts, but each selected expert is still used at a fixed precision. We present DPA-MoE, a runtime precision control framework that makes routed experts any-precision. DPA-MoE encodes expert feed-forward weights as prefix-decodable chunks using SharedScale AnyBCQ, profiles per-expert reconstruction residuals offline, and allocates chunks at inference time using live router gate scores. This post-routing allocation lets a single encoded MoE checkpoint operate at multiple effective weight budgets without retraining or re-encoding. Experiments on Qwen3-30B-A3B and DeepSeekMoE-16B show that DPA-MoE improves KL divergence and downstream accuracy over uniform chunk allocation at matched budgets, with modest steady-state throughput overhead in our prototype. --- ### Does Compression Imply Generalization? A Minimum Description Length Perspective Authors: Lincen Yang, Jiayang Shi, Nan Pu, Daniël M. Pelt, Matthijs van Leeuwen, Zhong Li, Shujian Yu Published: 2026-10-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.21376v1 A central question in modern learning theory is what notion of compression, if any, explains why over-parameterized neural networks generalize. Existing answers measure complexity at different levels, ranging from weights to representations; however, estimating the associated quantities either requires held-out data in principle or relies on the challenging (ultra) high-dimensional mutual information estimation. To overcome these challenges, we approach the question through the minimum description length (MDL) principle, and specifically, we propose the prequential regret as a complementary signal that is computable from the training trajectory alone. We establish that, in the (nearly) interpolating regime, the expected prequential regret upper-bounds the description length of the trained parameter under the algorithm-induced distribution, and that this description length translates into a high-probability generalization bound in the PAC-MDL setting. Along the way, we show that the encoder-complexity correction recently added to the algorithm-level information bottleneck (IB) is upper-bounded by an MDL parameter description length, \new{bringing together} the two views of compression from MDL and IB. Empirically, the prequential regret tracks the generalization error on CIFAR-10 and CIFAR-100, with Pearson correlations exceeding 0.9. --- ### Memorilla: Latent Semantic Memory for LLMs Authors: Adibvafa Fallahpour, Parsa Idehpour, Vignesh Kothapalli, Nikita Mounier, Shirley Wu, Shayan Pardis, Jure Leskovec Published: 2026-10-15 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.21375v1 Memory enables large language models (LLMs) to use information beyond their parameters, such as past user conversations, long documents, or an agent's earlier actions. For a frozen LLM, access to this accumulated knowledge is limited to what a memory system places in its context window. However, gathering and combining relevant information needed for each query while keeping the model's context short remains challenging for existing systems. Here we introduce Memorilla, a memory system that gathers information from an entire document collection into a fixed number of query-dependent 'memory tokens' for a frozen LLM. Memorilla encodes documents (such as user chats, book chapters) once into reusable embeddings, then learns to retrieve and place query-specific information in the LLM's input embedding space. Using only 16 memory tokens, Memorilla achieves the best performance against baselines including Mem0 and MemoRAG on five of eight benchmarks spanning personalization, long-document and knowledge-intensive question answering. Notably, on FactKG, it reaches 84.33% accuracy versus 80.43% with full-context inference, while using 108x fewer tokens to represent the source documents. Furthermore, Memorilla can facilitate continual learning in agentic systems where the document count (the agent's past turns) increases throughout the trajectory. In a TextWorld environment, we show that Memorilla reduces the agent's tendency to wander between rooms it has already explored, and improves its average success rate from 18.6% with full-history in-context learning to 24.2%. Overall, Memorilla aids frozen LLMs in accumulating and using knowledge effectively across long-context interactions and takes a step towards building continually learning AI systems. --- ### Same Target, Different Origins: Aligning Latent Rollout for Consistent PDE Emulation Authors: Xinying Li, Jing Xu, Wenjun Wang, Limei Han, Fenglei Cao, Ruoxi Jiang, Yuan Qi Published: 2026-10-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.21370v1 Neural PDE solvers commonly generate multi-step predictions through autoregressive rollout, recursively applying a learned evolution operator and feeding each prediction back as input for the next step. Approximation errors can therefore propagate through the rollout, causing predictions at a shared target time to depend on their temporal origins and rollout depths. For a well-posed deterministic PDE flow, however, states at different times along the same physical trajectory should, under exact evolution, reach the same target state. To this end, we propose Align Latent Rollout (ALR), a regularization approach that promotes consistency across rollout origins through the neural PDE solver's internal representations. A second-order Taylor analysis of latent discrepancy propagation motivates two objectives: zeroth-order latent state consistency, which aligns representations at a shared target time, and first-order latent dynamics consistency, which aligns local evolution responses to shared perturbations. ALR can be integrated into different neural PDE solvers by regularizing suitable internal representations, without modifying their backbone architectures. Experiments across multiple PDE benchmarks and neural-operator backbones show that ALR improves prediction accuracy while reducing shared-target discrepancies across rollout origins. --- ### ESG-Kor: A Korean Dataset for ESG-related Information Extraction and Practical Use Cases Authors: Jaeyoung Lee, Geonyeong Son, Misuk Kim Published: 2026-10-15 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2610.21368v1 With the expansion of pre-trained language model usage in recent years, the importance of datasets for performing tasks in specialized domains has significantly increased. Therefore, we have built a Korean dataset called ESG-Kor to automatically extract Environmental, Social, and Governance (ESG) information, which has recently gained importance. ESG-Kor is a dataset consisting of a total of 118,946 sentences that extracted information on each ESG component from Korean companies' sustainability reports and manually labeled it according to objective rules provided by ESG evaluation agencies. To verify the effectiveness and applicability of the ESG-Kor dataset, classification performance was confirmed using several Korean pre-trained language models, and significant performance was obtained. Additionally, by extending the ESG classification model to documents of small and medium enterprises and extracting information based on ESG key issues and in-depth analysis, we demonstrated potential and practical use cases in the ESG field. --- ### SATOR: Backpropagation-Free 3D Test-Time Adaptation via Sample-Adaptive Token Routing Authors: Inseok Kong, Geunyoung Jung, Jiyoung Jung Published: 2026-10-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.21367v1 Test-time adaptation (TTA) mitigates the performance degradation of source-pretrained models on unlabeled test data under distribution shifts. Recent backpropagation-free token-purging methods address 3D point cloud distribution shifts by filtering unreliable tokens. However, their reliance on predefined purge-size candidates requires multiple forward passes per sample and increases inference cost. We propose SATOR (Sample-Adaptive TOken Routing), a source-free and backpropagation-free 3D TTA framework that eliminates this search by deriving both the partitioning threshold and routing decision directly from each sample. SATOR computes token abnormality scores from complementary attention and geometric relation graphs. It then derives a sample-specific partition into retained and pruned tokens via Otsu-based separability, without evaluating candidate sizes. Keep-ratio-calibrated routing then selects the pruned prediction only when its entropy, penalized by the keep ratio, is lower than that of the original prediction. Experiments on ModelNet40-C, ScanObjectNN-C, and ShapeNet-C demonstrate that SATOR achieves state-of-the-art accuracy on three 3D corruption benchmarks. --- ### RenoLayout: Unified Floorplan Renovation and Furniture Layout for Constraint-Aware Residential Design Authors: Jingguo Liu, Yuanqing Liu, Chong Zhang, Yue Yang Published: 2026-10-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.21366v1 Residential design aims to transform existing homes into functional living spaces while satisfying diverse design preferences and physical constraints. However, existing floorplan generation methods typically assume empty building boundaries as input, whereas renovation requires reasoning over existing floorplans. Furthermore, floorplan renovation and furniture layout are commonly addressed as separate tasks, overlooking their inherent spatial dependency. Consequently, practical residential design must preserve immutable structural components while transforming editable spatial elements. It must also optimize furniture placement under design objectives and physical constraints. To address these challenges, we formulate residential design as a design-point-guided conditional generation task and propose RenoLayout, a framework that translates a pre-design residential state together with a design-point set into an executable Geometry-as-Code program. To enable controllable supervision, we construct a Design Map comprising 123 fine-grained design points covering structural renovation and furniture layout. We further introduce Difference-Grounded Design-Point Annotation to derive design-point sets automatically from before--after design pairs with VLM-based consistency verification. RenoLayout is trained using a three-stage CPT--SFT--RL pipeline, progressively improving spatial reasoning, instruction following, and constraint compliance. We also introduce the RenoLayout Benchmark, a set of 200 real-world before--after renovation cases with complete furniture layouts. To the best of our knowledge, it is the first benchmark for unified residential design. These cases include design-critical structural and building-service constraints. --- ### CoDeFont: One-Shot Font Generation via Multi-Scale Factor-Specific Representation Learning Authors: Rejoy Chakraborty, Prasun Roy, Saumik Bhattacharya, Umapada Pal Published: 2026-10-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.21364v1 One-shot Font Generation (OFG) aims to synthesize a target glyph by transferring the stylistic characteristics of a single reference glyph while preserving the structure of the target character. However, accurately capturing font style from a single reference image remains challenging due to the limited stylistic information available in a single glyph, and this challenge is further amplified for complex scripts. We propose CoDeFont, a script-agnostic OFG framework that addresses this challenge through multi-level style-content factorization and progressive style-content reconciliation. CoDeFont independently aggregates complementary style and structural information across multiple spatial levels to obtain factor-specific representations, while a contrastive objective explicitly encourages separation between style and content embeddings. During reconstruction, the disentangled representations are progressively injected through multi-level style conditioning, enabling stylistic information to be incorporated at different decoding resolutions while preserving the underlying glyph structure. We evaluate CoDeFont on structurally distinct Bengali and Latin scripts across seen and unseen font styles. Extensive quantitative and qualitative analyses demonstrate consistent improvements over existing state-of-the-art methods, highlighting the effectiveness of the proposed framework for OFG across diverse writing systems. --- ### Two Sample Sizes in Test-Time LLM Ensembling: Buffered ERM and Minimax Theory Authors: Zhi Zhang, Arash A. Amini Published: 2026-10-15 Categories: math.ST, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2610.21363v1 Test-time scaling can improve the performance of large language models by generating multiple answers to a question and aggregating them. Weighted ensembles extend this idea by drawing answers from several models, with the weights determining how often each model is used. Learning these weights from a training dataset involves two sample sizes: $Q$ labeled questions and $N$ generations per model and question. We study their interplay through the clean risk, the population error of the ensemble's infinite-generation voting rule. Under a margin condition with exponent $β$, we show that empirical risk minimization (ERM) with a calibrated margin buffer achieves excess risk of order $Q^{-1/2}+N^{-β/2}$, up to logarithmic factors, for fixed numbers of models and candidate answers. To investigate the optimality of this dependence on $Q$ and $N$, we analyze a simplified submodel with two models and two possible answers per question. We characterize its minimax excess risk up to constants by a Hellinger modulus for a binomial-mixture experiment. Polynomial approximation and spectral analysis reveal three regimes. When questions are relatively scarce, the $Q^{-1/2}$ term governs learning and the general buffered ERM is optimal. In an intermediate regime, pooling generation counts across questions improves upon estimating each answer distribution separately, with only logarithmic gains from additional questions. With sufficiently many questions, the minimax excess risk reaches an $N^{-β}$ identification floor that persists even with infinitely many questions. The submodel's lower bounds also apply to general ensembles, matching the buffered-ERM upper bound up to logarithmic factors when questions are scarce and in parts of the intermediate regime. Questions remain about the transitions between regimes and the construction of matching pooled estimators for general ensembles. --- ### LTM: Latent Transition Based In-Context Memory for Vision-Language-Action Models Authors: Qixin Sun, WenLong Gao, Xiansheng Chen, Zhongyuan Wang, Si Liu, Pengwei Wang Published: 2026-10-15 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2610.21362v1 Robotic manipulation often requires remembering interactions that are no longer visible. We introduce Latent Transition Memory (LTM), which stores history as compact latent transitions between consecutive observations. Instantiated on $π_{0.5}$ as LTM-$π$, our method uses a frozen latent action encoder, a lightweight adapter, and causal KV caching for incremental inference without memory-specific semantic annotations or external reasoning-model calls. With DreamDojo transitions, LTM-$π$ achieves 58.54% success on RoboMME and 80.5% on LIBERO-Mem, performing best among baselines without external reasoning models or memory-specific annotations. Ablations support the contribution of transition content beyond temporal cues and the efficiency of delayed memory admission. Scaling RoboMME demonstrations tenfold improves success from 57.67% to 87.50%, while a Cup Swap diagnostic highlights the role of process supervision in temporal composition. Under a 200-token memory budget, success remains 84.00%, versus 87.50% without compression. Finally, real-robot counting success improves from 11.25% to 82.50%. Together, these results demonstrate the effectiveness, scalability, and efficiency of latent transition memory, highlighting its capacity for complex temporal information, bounded-context operation, and real-world robotic control. --- ### Controlling the False Discovery Rate via Model-Agnostic Importance Measures Authors: Mengtao Wen, Haojie Ren, Changliang Zou Published: 2026-10-15 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2610.21360v1 Selecting covariates while controlling the false discovery rate (FDR) is critical for interpretable scientific discovery, especially with complex machine learning models. Traditional variable selection methods often rely on specific model assumptions, while Model-X knockoffs provide a general way that leverages knowledge of the covariate distribution to produce a variable selection algorithm. This study puts forward a complementary method to Model-X knockoffs, named Model-Agnostic Selection with agent-X importance (MAS), which utilizes the sample-splitting strategy and a novel variable importance measure to bypass distributional assumptions on covariates. The proposed model-agnostic agent-X importance is defined to evaluate the difference of oracle predictiveness on both the original distribution and the distribution with agent variable in population level, and can be efficiently estimated by constructing the agent variable as some constant and cross-fitting strategy. The MAS method integrates a resplit-per-covariate strategy to decouple estimator dependencies and a data aggregation technique to enhance power. Theoretical guarantees for asymptotic FDR control are established under mild conditions. Extensive simulations and real-data analyses demonstrate that MAS provides competitive performances with existing works in FDR control, computational efficiency and power. --- ### L2GSSL: Label-Efficient Local-to-Global Self-Supervised Learning for Volumetric Healthcare Data Authors: Po-Cheng Cheng, Hung-Hsuan Chen Published: 2026-10-15 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2610.21356v1 Healthcare institutions routinely accumulate high-dimensional computed tomography (CT) volumes, but only a fraction can be annotated by experts. We present L2GSSL, a local-to-global self-supervised learning framework that leverages unlabeled volumes by decomposing pretraining into intra-slice and inter-slice representation spaces. A slice encoder learns view-invariant local features, and a global encoder aggregates the resulting tokens to model volumetric context. The stop-gradient isolates the local space from the global objective, while slice-wise execution and a three-phase schedule support training under constrained GPU memory. On LIDC-IDRI lung nodule malignancy classification, L2GSSL reaches $0.9229$ AUROC with only $10\%$ of the labels and $0.9377$ with $25\%$, exceeding the volume-level VICReg by $0.0229$ and $0.0294$, respectively. With all labels, the strongest supervised baseline exceeds L2GSSL by only $0.0044$ AUROC, consistent with self-supervised pretraining providing its greatest value when annotations are limited. Without adaptation to the external LNDb cohort, a model fine-tuned on $25\%$ of LIDC-IDRI obtains $0.8138$ AUROC and $0.7589$ AUPRC, improving over the strongest evaluated self-supervised baseline by $0.1130$ and $0.0954$. Experiments across data sources, thoracic and abdominal anatomy, downstream tasks, and two backbones examine healthcare-data variety, while lesion-slice masking shows that the predictions depend on lesion-bearing content. --- ### Honesty is the Best Policy ... or is it? Demand Management for Probabilistic Service Options Authors: Daniela Sailer, Robert Klein, Claudius Steinhardt Published: 2026-10-15 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2610.21351v1 To enable well-informed customer choices and redistribute demand across service options, providers can display probabilities regarding predicted service levels at the time of booking, effectively offering probabilistic service options. In many service settings, the underlying truthful probabilities endogenously depend on the system state, rather than being static product attributes controlled by the provider. While customers rely on this information when making decisions, they cannot readily verify its accuracy. Consequently, providers may be tempted to manipulate the displayed probabilities to guide customers' choices in their favor, creating a novel lever for demand management. In this work, we model the resulting problem as a sequential decision process, define truthful probabilities recursively, and introduce transparency constraints that limit their distortion. Because the exact computation of truthful probabilities is intractable for realistic settings, we develop an adapted reinforcement learning algorithm to approximate them. Furthermore, we propose a sampling-based mixed-integer program to optimize the information communicated by the provider in each state. Our framework enables providers to gauge the benefits of dynamically disclosing probabilistic information at the time of booking and sheds light on incentives for manipulation. Our computational study is motivated by out-of-home delivery, i.e., the delivery to parcel lockers or shops, and reveals a trade-off between individual-level transparency and aggregate customer utilities. --- ### Hierarchical Graph Convolutional Network Approach for Detecting Low-Quality Documents Authors: Jaeyoung Lee, Joonwon Jang, Misuk Kim Published: 2026-10-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.21350v1 Consistency within a document is a crucial feature indicative of its quality. Recently, within the vast amount of information produced across various media, there exists a significant number of low-quality documents that either lack internal consistency or contain content utterly unrelated to their headlines. Such low-quality documents induce fatigue in readers and undermine the credibility of the media source that provided them. Consequently, research to automatically detect these low-quality documents based on natural language processing is imperative. In this study, we introduce a hierarchical graph convolutional network (HGCN) that can detect internal inconsistencies within a document and incongruences between the title and body. Moreover, we constructed the Inconsistency Dataset, leveraging published news data and its meta-data, to train our model to detect document inconsistencies. Experimental results demonstrated that the HGCN achieved superior performance with an accuracy of 91.20% on our constructedInconsistency Dataset, outperforming other comparative models. Additionally, on the publicly available incongruent-related dataset, the proposed methodology demonstrated a performance of 92.00%, validating its general applicability. Finally, an ablation study further confirmed the significant impact of meta-data utilization on performance enhancement. We anticipate that our model can be universally applied to detect and filter low-quality documents in the real world. --- ### FedSkillGit: Federated Skill Evolution via Version Control Authors: Boxun Lan, Jiamei Li, Weijian Li, Chengyu Yang, Zhuang Qi, Chengcheng Wan, Xiaohong Chen, Ming Hu Published: 2026-10-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.21348v1 Large language model agents can improve their capabilities by evolving reusable natural-language skills from execution experience. In real-world deployments, this experience is distributed across data owners who cannot pool their raw data, which motivates federated skill evolution. The natural first design lets each client evolve the whole skill document and upload the result for server-side aggregation. That design is poorly matched to skill evolution for three reasons. An evolved document can still carry client-specific content distilled from private traces, repeated transmission of a nearly unchanged document spends communication on knowledge that the population already holds and the contribution of a single client is buried in a document that the server cannot meaningfully attribute. We propose FedSkillGit, a federated skill evolution framework that replaces full-document updates with commits. Each participating client submits a bounded set of patches over named rules together with its local experience, which summarizes what the round taught it, and the pair passes a two-stage privacy filter before it leaves the client. The server deduplicates the submitted patches and the local experience of all participants, updates a global experience document that only the optimizers read, and merges the surviving patches into a candidate skill. The candidate is distributed to the clients, which score it on their own validation sets and report the results, and it is published only when the reported scores improve on the current version. Experiments on three datasets and three language model families show that FedSkillGit outperforms state-of-the-art baselines by up to 22% and approaches centralized evolution without sharing raw client data. --- ### Emotion Is Not External Knowledge: Internal Attention Signals for Affective State Reasoning Authors: Wenqiu Tang, Zhen Wan, Yihui Wang, Takahiro Komamizu, Ichiro Ide Published: 2026-10-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.21347v1 Large Language Models (LLMs) increasingly operate in multi-turn interactions that require maintaining latent conversational states, not only explicit facts. We study affective state as an implicit state inferred from sparse contextual cues that remain relevant after topic shifts, and ask whether LLMs expose internal attention signals for routing such evidence at inference time. Prior attention interventions rely on labeled in-domain head profiles and externally specified target spans, limiting transfer across affective-evidence distributions. We propose Self-targeted Internal Attention Boosting (SIAB), which localizes sparse affective heads via causal localization (in detail activation patching) on synthetic minimal pairs and boosts, at the answer position, the content tokens these heads already attend to; both edited heads and target tokens are derived from the model's own behavior, enabling the same head set to be reused across tasks.We evaluate on ECC and GoEmotions across three LLMs and multiple prompting settings. Across settings, SIAB improves prompt-matched baselines by up to +10.3 macro-F1 on ECC and +5.5 on GoEmotions. Combined with PASTA-style external supervision, it achieves up to +13.84 accuracy points and +12.51 macro-F1 points, while mechanistic analyses trace the gains to sparse, emotion-enriched heads and show that layer proximity affects additivity. --- ### ARGUS: An Agenda-Driven Framework for Reliable User Simulation Authors: Hang Zheng, Nan Jiang, Zichen Zhu, Zixu Yang, Zhiyang Tang, Shuai Fan, Lu Chen, Xiaobao Wu, Kai Yu Published: 2026-10-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.21346v1 High-fidelity user simulators are essential for evaluating and training agents in interactive environments. However, current LLM-based simulators struggle with reliability issues, such as goal omission and policy non-compliance. We propose ARGUS (Agenda-dRiven Goal-oriented User Simulator), a neuro-symbolic framework that maintains the user's goal state using a dynamic agenda stack manipulated via symbolic operations. By rigorously decoupling state tracking from natural language generation, ARGUS facilitates strict goal progression and constraint-aligned interactions. For cost-efficient deployment, we distill ARGUS into compact models using a unified pipeline: evaluator-guided SFT followed by online RL with dense step-level rewards. To rigorously evaluate behavioral fidelity, we introduce a rubric-based metric Composite Behavioral Score (CBS). Evaluations on $τ^3$-Bench and MultiWOZ demonstrate the significant superiority of the ARGUS architecture and the efficacy of our training pipeline. Code and data will be released soon. --- ### OpCredit: Operation-Aware Policy Learning for Agentic Knowledge Graph Question Answering Authors: Yucheng Li, Mingyuan Li, Xiaxia Wang, Gong Cheng Published: 2026-10-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.21345v1 Agentic knowledge graph question answering(KGQA) relies on sequences of executable operations, but trajectory-level rewards obscure their individual contributions. Successful trajectories may contain ineffective operations, while failed trajectories may contain useful ones. To assess individual operations, we propose OpCredit, an operationaware policy-learning framework that combines downstream outcome credit with immediate transition credit: Branch Outcome Credit (BOC) reuses ordinary rollouts to compare terminal task rewards observed after different operations under matched navigation contexts; Frontier Transition Credit (FTC) measures operation-induced changes in answer-conditioned frontier potential. The two complementary signals jointly supervise the corresponding decision spans during training, while inference uses only the learned policy and standard KG interface. Experiments on ComplexWebQuestions, WebQSP, and GrailQA across three backbones demonstrate consistent improvements in KGQA performance. --- ### Quantum Versus Classical Machine Learning for Neuropsychiatric Disorders: A Feature-Matched Multi-Cohort Evaluation Authors: Utsav Poudel, Anuj Nepal, Vyas Viswanath, Subramaniyaswamy Vairavasundaram Published: 2026-10-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.21344v1 Resting-state functional connectivity is widely used in machine learning-based classification of neuropsychiatric disorders. Quantum machine learning models have been proposed for functional connectivity data, but few studies have evaluated them under leave-site-out validation or against matched classical models. We compared six quantum model families with classical ones using identical correlation-derived features across four public cohorts (4,308 subjects). Leave-site-out validation was used for the Autism Brain Imaging Data Exchange (ABIDE I), ADHD-200 (attention-deficit/hyperactivity disorder), and REST-meta-MDD (major depressive disorder) cohorts, while the UCLA Consortium for Neuropsychiatric Phenomics (UCLA-CNP) was evaluated using stratified 10-fold cross-validation. The quantum kernel was statistically indistinguishable from a matched classical kernel across all four cohorts, with the average accuracy difference within 1.4 percentage points at 95% confidence. On ABIDE I, a hybrid quantum convolutional network achieved similar accuracy to its classical counterpart (0.645 vs. 0.641), while a trainable quantum kernel exceeded its classical counterpart by 0.064 in area under the curve (AUC). Quantum convolutional networks also achieved higher AUC than their matched classical networks on this cohort and showed smaller train-test gaps on all four cohorts, without an accuracy gain. Overall, most quantum models matched their classical counterparts, but none consistently outperformed them. This study, among the first quantum evaluations of ABIDE I under leave-site-out validation, provides a feature-matched benchmark of quantum and classical models comprising 284 matched comparisons. We further analyse fidelity-based graph construction and account for the observed quantum-classical parity through effective-dimension and eigenspectrum analyses. --- ### Online Quantile Omniprediction for Proper Losses Authors: Hyunsuk Kim, Isaac Gibbs, Michael W. Mahoney, Ryan J. Tibshirani Published: 2026-10-15 Categories: cs.LG, stat.ME arXiv: https://arxiv.org/abs/2610.21342v1 The task of constructing a predictor that is simultaneously accurate under multiple evaluation metrics has been popularized recently under the name omniprediction. Prior work in this area has largely focused on binary prediction tasks, and existing results for multiclass and continuous outcomes typically suffer from slow error rates. In this paper, we consider forecasts expressed as a set of quantiles over a discrete but otherwise arbitrary set of probability levels. We develop sample-efficient algorithms for constructing forecasts that are accurate simultaneously across all proper losses that satisfy mild regularity conditions, where proper losses are those minimized by predicting the true quantiles. Our algorithms are online and can operate in a dynamic environment, while simultaneously taking multiple losses into account, and their forecasts offer the potential to provide diverse end-users with rich information for evaluating risk and informing a range of practical decision-making tasks. As an example, we demonstrate how our procedure can be used to ensemble quantile forecasts of COVID-19 hospitalizations made by experts during the pandemic. --- ### Dimension-Free PAC-Bayes Generalization for Deep Neural Networks via Dirichlet Processes Authors: Sumit Vashishtha Published: 2026-10-15 Categories: stat.ML, cs.LG, math.ST arXiv: https://arxiv.org/abs/2610.21340v1 Classical PAC-Bayesian generalization theory places prior distributions over Euclidean parameter space $Θ\subseteq \mathbb{R}^D$, causing relative entropy to scale with network dimension $D$. For modern overparameterized neural networks where $D \gg n$, this parameter-counting dependency yields vacuous generalization bounds ($> 1{,}000\%$). In this work, we resolve this barrier by shifting prior specification from internal parameters to the non-parametric space of data distributions $\mathcal{M}_1(\mathcal{Z})$ via a \textbf{Dirichlet Process (DP)}, $\mathcal{DP}(α, F_0)$, inducing parameter distributions through push-forward measures under the learning algorithm. By the Data Processing Inequality, parameter-space relative entropy is strictly bounded by the data-space DP divergence, which we evaluate in exact closed form using Digamma functions. The resulting PAC-Bayesian certificate is strictly invariant to network parameter count $D$, width, and depth. On intrinsic $d^*$-dimensional submanifolds, optimal partition scaling achieves the minimax non-parametric rate $\mathcal{O}(n^{-1/(d^*+2)} \sqrt{\ln n})$. Across vision architectures scaling up to 4.2 million parameters ($D = 7{,}850$ to $D = 4{,}203{,}522$) on the full MNIST benchmark, while classical weight-space bounds scale past $940\%$ (becoming vacuous), our data-space DP-PAC-Bayes certificate remains stable, non-vacuous, and certified at \textbf{$8.8\%$--$9.4\%$}. --- ### Does On-Policy Distillation Need to Complete Every Rollout? Authors: Zhengxin Zhang, Maosen Tang, Ning Wang, Changhao Li, Jingren Zhou, Bo Dai, Sainyam Galhotra, Alex Townsend, Claire Cardie Published: 2026-10-15 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.21337v1 On-policy distillation (OPD) effectively transfers capabilities from a teacher to a student through feedback on student-generated rollouts. However, generating complete student rollouts and computing teacher feedback for every token make OPD computationally expensive. We introduce Stochastic Truncated On-Policy Distillation (STOPD), which accelerates OPD by randomly truncating student rollouts and correcting the resulting sampling bias with blockwise inverse-probability weighting (IPW). At each training step, we sample a stopping position for each rollout before generation and let the student generate until that position or natural termination. We obtain teacher feedback on every generated token and use blockwise IPW to compensate for the lower probability of retaining later tokens while controlling the weights. We prove that this weighting preserves Vanilla OPD's gradient sum in expectation and derive one-step update-error bounds for SGD, Adam, and Muon. We evaluate STOPD across multiple teacher-student model pairs, task domains, and optimizers. STOPD reduces generated tokens by 25-48% while maintaining accuracy comparable to Vanilla OPD, achieving 1.3-2.2x training speedups. --- ### Ranking and Partitioning of Attention Heads for Sparse and Continual Reinforcement Learning Fine-tuning Authors: Ruizhe Shi, Zaiwen Yang, Qiubo Wang, Banghua Zhu, Maryam Fazel Published: 2026-10-15 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2610.21336v1 We study sparse and continual reinforcement learning fine-tuning of language models through attention-head ranking and partitioning. For sparse learning, we rank attention heads by gradient norm to identify a small subset of heads that can be trained effectively. For continual learning, we partition heads across tasks to reduce cross-task interference and preserve previously learned capabilities. Theoretically, we relate gradient norm to training effectiveness, and further characterize why sparse, separated head updates can remain stable. Empirically, across math, instruction-following, and coding tasks, tuning higher-ranked heads consistently outperforms tuning lower-ranked ones while often matching denser baselines, and head partitioning improves retention while preserving adaptation to new tasks. --- ### When Should a Low-Light Pipeline Generate? Auditable Risk Control for Selective Generative Enhancement Authors: Qiyi Xie, Wei Chen Ng, Suyang Xi, Xicheng Wang, Ziyao Li, Bohong Xu, Wenyi Liu, Jian Ding Tan Published: 2026-10-15 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2610.21335v1 Generative low-light enhancers recover plausible texture but may hallucinate structure; restoration networks preserve structure but can leave regions under-enhanced, and neither advantage is spatially uniform. Therefore, we formulate selective generative enhancement as a decision problem: determine where overriding a frozen base expert is beneficial and refuse to switch when the evidence is insufficient. We propose VetoNet, an auditable regional routing framework centered on a certified veto. It first measures the complementary strengths and routing direction of a frozen restoration generative pair, then predicts the utility of regional overrides from deployment-available signals alone and admits an override only when a distribution-free harm-budget certificate says the perceptual (LPIPS) risk budget allows it. Experiments across multiple expert pairs and domains show that VetoNet adapts its routing behavior to the strength and reliability of the available evidence. When expert complementarity is sufficiently predictable, it achieves statistically significant certified gains; when the relative strengths of the experts change, it correspondingly reverses the routing direction; and when routing evidence is weak or affected by cross-domain shift, it conservatively vetoes switching. --- ### QuasiLeak-Bench: Evaluating LLM-Based Privacy Detectors on Policy-Conditioned Quasi-Evidence Group Recovery Authors: Yufan Zhu, Yangfan Jiang, Yang Fei, Shizheng Hou, Shubhankar Mohapatra, Xiaokui Xiao Published: 2026-10-15 Categories: cs.CL, cs.CR arXiv: https://arxiv.org/abs/2610.21333v1 Natural language messages often contain quasi-identifiers that are weak in isolation but can jointly reveal an individual's private attributes. We call such a jointly revealing set of cues a quasi-evidence group. Existing privacy benchmarks focus on explicit identifiers, attribute inference, or task-driven disclosures, leaving inference from quasi-evidence groups largely unmeasured. In practice, whether exposing such a quasi-evidence group violates privacy also depends on sender-specified disclosure policies. We introduce QuasiLeak-Bench, a benchmark for policy-conditioned quasi-evidence group recovery, which evaluates whether detectors recover complete quasi-evidence groups and flag the disclosures the given policy prohibits. To obtain reliable ground truth at scale, a reverse-construction pipeline first selects weak quasi-identifiers, composes them into quasi-evidence groups verified to jointly reveal a target attribute, and generates documents around this evidence, followed by automated quality control. Experiments show that existing privacy detectors transfer poorly to QuasiLeak-Bench, and locally deployable LLM-based detectors fall far behind proprietary models, mainly because they miss most quasi-evidence groups altogether. However, a 4B model fine-tuned on our training split surpasses the strongest prompted model on held-out documents, showing that the task is learnable. --- ### Semantic Latent Alignment for Flow Matching with Invertible Bi-Lipschitz Adapters Authors: Felix Nützel, Mischa Dombrowski, Luca Hagen, Bernhard Kainz Published: 2026-10-15 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2610.21332v1 Pretrained latent spaces trade compression, reconstruction, and the learnability of the coordinates a downstream generator has to work in, which complicates adapting these spaces to different domains or tasks: continued training is expensive, and without a new alignment objective it often fails to improve downstream generation. We instead leave the encoder and decoder fixed and change only the coordinates between them, using an invertible bi-Lipschitz adapter aligned offline to a semantic teacher and frozen during class-conditional flow matching. Invertibility preserves compatibility with the pretrained autoencoder, while the bi-Lipschitz constraint limits how far alignment can distort its latent geometry. This provides a simple way to improve semantic organization while retaining the compression and reconstruction properties of the original latent space. On two medical imaging datasets, constrained latent adaptation improves feature metrics, seed stability and counterfactual edit strength, while remaining competitive on downstream classification. In contrast, unconstrained adaptation can become highly anisotropic and sensitive despite remaining invertible, highlighting the importance of controlling geometric distortion. Our results suggest that carefully constrained post-hoc adaptation offers a parameter-efficient and tuning-free alternative to jointly modifying the representation during generative training. --- ### VoteGEO-Bench: Measuring the Impact of Generative Engine Optimization on Electoral Visibility Authors: Shiqi Zhang, Xiaokui Xiao Published: 2026-10-15 Categories: cs.IR, cs.CL, cs.CY arXiv: https://arxiv.org/abs/2610.21330v1 Large language models (LLMs) are increasingly used for election information, yet little is known about how external web content shapes the political information they present. Generative engine optimization (GEO) rewrites web content to improve its visibility in generated responses. To investigate its potential risks in voting scenarios (VoteGEO), we introduce VoteGEO-Bench, a benchmark covering the 2024 U.S. presidential election and the 2026 Japanese House of Representatives election, combining election-related queries, historical webpages, and voter personas. We first analyze sources cited by generative engines and find that many citations come from lower-cost owned and open-platform sources, while some webpages remain visible across days. We then evaluate 11 rewriting strategies in 4 categories, examining target specification, effectiveness across engines and elections, and the role of voter personas. Rewriting without specifying a target rarely increases target exposure, whereas target-specified rewriting more often does. Strategies that improve page organization or strengthen a position through argumentation yield greater gains than adding supporting evidence or changing wording. For the two strongest strategies, gains remain broadly positive across evaluated U.S. personas, but persona conditioning shows no consistent effect on these gains. Explicit partisan identities can create baseline exposure gaps larger than the gain from rewriting one webpage. When partisanship is implicit in the voter profile, baseline shifts depend on how strongly the engine responds to that signal. --- ### Hybrid Generative-Tagging Decoding for Efficient Product Attribute-Value Extraction Authors: Keshav Kolluru, Manas Gupta, Maroof Ahmad, Suchitra Sathyanarayana Published: 2026-10-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.21329v1 Attribute-value extraction is important for building high-quality product catalogs in e-commerce. Existing systems either rely on generative or tagging strategies for extracting the attribute names and their corresponding values. Tagging models directly label spans in the source, making them fast and grounded, but they cannot produce values that require reformatting or generate rare attribute names outside their label space. Generative models avoid these drawbacks by generating both attribute names and values token by token, but this auto-regressive nature makes them slow and limits attribute coverage. We introduce hybrid generative-tagging decoding, a novel model architecture that combines tagging source spans and open-ended generation. For frequent attributes whose values are copyable, a tagging head extracts values directly from the source. This lets the generative head focus on the remainder - rare attributes outside the tagger's label space and non-copyable values, including implicit or normalized values. Integrated into vLLM inference, the hybrid decoder raises attribute coverage by 10% and extracts 63% more correct attribute-value pairs at no precision cost, while reducing latency by 44%. --- ### DocPilot: Interactive Agent Orchestration and Training for Long Visual Document Understanding Authors: Zhuowen Liang, Xiaotian Lin, Yuyu Luo, Haixun Wang, Nan Tang Published: 2026-10-15 Categories: cs.AI, cs.CL, cs.CV arXiv: https://arxiv.org/abs/2610.21327v1 Multimodal long-document question answering requires models to seek sparse evidence across pages and modalities, understand heterogeneous document content, and reason over the collected evidence. Even advanced vision-language models (VLMs) can overlook sparse evidence and struggle with cross-modal reasoning in a single pass. Existing document agents further introduce multi-step interaction, but some still rely on predefined workflows or coarse-grained actions, limiting the flexibility and granularity of document reasoning. We introduce DocPilot, an agentic document framework that supports expressive orchestration and makes complex document solving learnable by small language models (SLMs). DocPilot orchestrates evidence seeking through page-level navigation and fine-grained evidence localization, and integrates local visual inspection, code-based numerical reasoning, and cross-modal reasoning for multimodal understanding. To transfer these capabilities to small models, we propose curriculum-based agentic training that progresses from single-ability learning to adaptive orchestration through supervision from data-grounded reasoning traces and executable interaction trajectories. Across MMLongBench-Doc, DocBench, FinRAGBench-V, and MADQA, DocPilot achieves strong gains with frontier VLM backbones, while DocPilot-4B delivers competitive performance against substantially larger models, demonstrating strong effectiveness and generalization across diverse long-document reasoning settings. The code is available at https://github.com/HKUSTDial/DocPilot. --- ### CertEx: Exact Visual Retrieval at Scale by Certified Exclusion Authors: Dongfang Zhao Published: 2026-10-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.21325v1 Exact $k$-nearest-neighbor (kNN) search over image descriptors and embeddings underlies visual retrieval, near-duplicate detection, the evaluation of learned representations, and increasingly the memory of LLM agents. However, exhaustive search computes every distance at full precision, whereas approximate indexes return recall below one. We observe that exact search only needs a proof that each excluded vector cannot be a neighbor. Because such a proof only has to be conservative, it can be checked in low precision, much as the retina examines the whole scene at low resolution. We call this principle certified exclusion and realize it in an exact kNN method for GPUs, which we call \certex. Specifically, \certex\ stores a lower-bounding projection of each vector in half precision and folds a rounding certificate into the same tensor-core dot product, so that only the few vectors that the test keeps need exact distances. We prove that \certex\ returns the exact kNN of every query. On sixteen datasets with up to 100M vectors, \certex\ is exact for every query at 7.1$\times$ to 18.0$\times$ the throughput of the fastest cuVS search on one H100 and outperforms quantized and graph indexes whenever every query must be exact. --- ### AdaLoop: Thinking with the Vision Encoder Authors: Xinran Nicole Han, Yiyang Lu, Katelyn Gan, Todd Zickler Published: 2026-10-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.21323v1 Most vision-language models (VLMs) treat the vision encoder as a static feature extractor: it encodes an image once, independently of the question, and leaves subsequent reasoning to the language model. Yet different questions may require different visual operations and processing depths. We present AdaLoop, a framework for question-conditioned visual recurrence in VLMs. AdaLoop adapts visual computation to the question and reuses the encoder's transformations across multiple iterations, with the pretrained vision weights frozen. We also introduce VisRO, a procedural dataset and generation pipeline for training and evaluating vision-centric reasoning. On six VisRO tasks, AdaLoop outperforms standard fine-tuning and question-conditioned single-pass baselines with matched training data and optimizer updates. These gains hold across three VLM families on both in-distribution and out-of-distribution examples. Our findings suggest that pretrained vision encoders can contribute to reasoning through task-directed, iterative visual computation. --- ### CoViG: Coarsened Vision GNN for Image Classification Authors: Martial Guidez, Stefan Duffner, Christophe Garcia Published: 2026-10-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.21321v1 Although Graph Neural Networks are widely used in various domains, they remained mostly unexplored in computer vision. Convolutional Neural Networks and Vision Transformers were leading the field, until the quite recent introduction of Vision Graphs (ViG) that treat images as a set of nodes and apply graph convolution on their k-NN graphs. ViGs show impressive accuracy on image classification but their computational cost remains relatively high. Inspired by optimization methods for GNNs, we present CoViG, a novel approach combining graph coarsening and ViGs. Our method introduces an additional MinCUT pooling step within the Grapher component of intermediate ViG blocks. By simplifying the intermediate graphs and thus decreasing the number of nodes of specific blocks, our approach considerably reduces the computational cost of ViG during inference. We evaluated our approach on ImageNet with several ViG architectures, and we obtained accuracies equivalent to the original ViG models with only about 51\% of FLOPs. --- ### ZoomCap: Evidence-Routed Visual Zooming for Recoverable Visual Information Transfer Authors: Hao Shi, Jiafeng Wang, Yuzhuo Fu, Tao Zhang, Jian Bai, Juelu Zhang, Qing Cui, Chao Huang Published: 2026-10-15 Categories: cs.CV, cs.CL, cs.MM arXiv: https://arxiv.org/abs/2610.21320v1 Detailed captions transfer visual information into vision-language model supervision, but quality is easily conflated with length: long single-pass outputs still miss small objects, text, and spatial relations or promote uncertain observations into confident claims. We formulate fine-grained captioning as recoverable visual information transfer, in which a teacher acquires missing evidence under a finite observation budget and converts it into reusable supervision. ZoomCap uses a draft caption to route conditional knowledge retrieval, OCR-sensitive reading, coverage-gap recovery, and adaptive visual zooming, allocating deeper crops only to the most complex eligible region, deriving spatial relations from grounded geometry, and fusing non-duplicate evidence. We also introduce FactCycle, which scores caption-derived atomic claims on two blind anchors--source image (truthfulness) and reconstruction (realizability)--separating fabrication from generator loss claim by claim; human and multi-judge comparisons complement this fact-level view. Against Qwen3.5-397B-A17B captions, ZoomCap achieves an 81.9% human tie-adjusted preference score with a teacher over 10x smaller, and FactCycle counts 52.4 transferred claims per image vs. 31.5 for ScaleCap. The evidence also transfers: in continual pre-training, ZoomCap-450K improves the 11-benchmark average by 1.31-2.38 points over the strongest competing corpus and Ling-Tiny-VL-v3 gains 1.4 points on a production document/OCR monitor suite (1.5 on perception) at 60B tokens; in medical pre-training, 2.64M ZoomCap-captioned images improve five VQA benchmarks by 3.04 points (vs. 1.76 for same-image Gemini-3.1-Pro captions). --- ### Constrained Multi-Agent Reinforcement Learning in Imagination Authors: Raz Shmueli, Shahaf S. Shperberg Published: 2026-10-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.21319v1 Predicting cost in a multi-agent world model moves most constrained policy updates into imagination: the stronger model-free baseline needs $10$ to $20$ times CA-MAMBA's interactions on the median SMAC configuration, and CA-MAMBA earns $2.8$ to $12$ times the baselines' MAMuJoCo reward at equal budget. In controlled tests on one task per benchmark, pricing the model's cost advantages at parity more than halves a cost-blind learner's cost and meets a tight continuous-control limit the learned multiplier misses, suggesting the model's cost estimates are not the bottleneck. --- ### Loud and Clear: Making Visual Evidence Count in Multimodal Document RAG Authors: Eunchan Jo, Seounghyun Jang, Sangwoo Mo Published: 2026-10-15 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2610.21318v1 Multimodal document retrieval-augmented generation (RAG) has focused largely on retrieval, yet its answers depend on how well a vision-language model reads the retrieved pages. We find that evidence in retrieved pages remains underused even when the correct pages are retrieved. On SciEGQA oracle pages, five prior methods give the generator 0.7K to 2.7K visual tokens per query on average under a common image processor, yet raising the page-only budget from 1K to 32K improves accuracy by 15.22 points. At a fixed 16K budget, adding ground-truth crops improves accuracy by 3.75 points over page-only input. We study what the generator needs from retrieved pages through two requirements: Loud, making full use of visual token capacity, and Clear, refining the page so that its evidence becomes prominent. For Loud, increasing either the visual token budget or visual fidelity, the image resolution those tokens preserve, improves accuracy with the other held fixed, and full-page scaling outperforms repetition and tiling at matched budgets. For Clear, suppressing surrounding content improves accuracy without enlarging selected regions, and adding OCR of these regions to page images outperforms either input alone. We implement both as Loud and Clear (LoC), which combines higher-resolution pages with OCR from query-relevant regions without ground-truth annotations or additional training. LoC outperforms eight prior methods on SciEGQA, ViDoRe-v3, and MMLongBench-Doc, improving over the strongest, ColQwen3, by 8.88, 3.09, and 4.22 points with the same retriever and generator. It also outperforms its page-only variant under the same visual token budget. These results locate a bottleneck beyond retrieval: how the retrieved pages are given to the generator. --- ### Money-Mule Detection as a Relational Learning Problem: A Study on the RBIH NFPC Dataset Authors: Owais Ahmad, Anirudh Deodhar Published: 2026-10-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.21314v1 Money-mule networks move criminal funds through many small transfers, each of which looks ordinary on its own. What marks an account as a mule lies outside any single transfer: in the counterparties and addresses its network shares, and in the shape of its activity over time. Production systems remain largely rule-based and see neither, while most research classifies transactions rather than accounts, recovering account-level risk only by aggregating afterwards. We instead score the account directly, reading the bank's relational schema as a heterogeneous graph in which rows are nodes and foreign keys are edges. Each account is scored from a multi-hop neighbourhood using per-column encoders, a relative-time encoding and HeteroGraphSAGE message passing, with that neighbourhood restricted to rows predating the account's own pre-flag cutoff so that no model sees evidence recorded only after the account was flagged. On a five-year Reserve Bank Innovation Hub (RBIH) retail-banking dataset of 400 million transactions and 94{,}063 labelled accounts, 2.6\% of them confirmed mules, we compare against RelGNN, XGBoost, LightGBM and CatBoost trained on identical labels, splits and cutoffs. Our detector recovers nine in ten held-out mules at 83\% precision and a 0.5\% false-alarm rate, finding 115 more mules than the strongest tree ensemble given the same evidence. At the tuned thresholds the gap is mostly in recall: XGBoost and LightGBM lead across the first hundred alerts, but only the graph models hold their precision deep into the queue. Since the graph is the schema itself and every score is dated per account, the approach deploys on a bank's existing database without a custom feature graph build. ---