# Research Papers — 2026-10 · bundle page 12 of 156 > Full-text markdown of papers #551–600 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/12 [← Previous bundle](https://aipod.dev/papers/archive/2026-10/page/11.md) [Next bundle →](https://aipod.dev/papers/archive/2026-10/page/13.md) ### Condition-Contrastive Extrapolation for On-Policy Distillation of Language Models Authors: Wenxuan Luo, Chenxi Li, Haoyue Liu, Yongxin Guo, Xiaoying Tang Published: 2026-10-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.21195v1 On-policy distillation (OPD) improves a student language model by training on its own generated trajectories with supervision from a stronger teacher. However, when conditioned on student-generated prefixes, the teacher can favor invalid continuations that violate the question's premises, causing OPD to encourage erroneous reasoning steps. As a remedy, we introduce Condition-Contrastive Extrapolated On-Policy Distillation (CCE-OPD), which makes teacher supervision sensitive to question conditions. CCE-OPD incorporates (1) a fixed-prefix comparison in which the same frozen teacher evaluates the complete question and a counterpart with a selected condition masked, and (2) a bounded log-probability contrast that reweights the teacher distribution into an auxiliary distillation target. On 200 diagnostic reasoning states, condition contrast reduces the rate of preferring invalid continuations from 27.0% to 16.0%. Extensive experiments across six mathematical benchmarks show that CCE-OPD improves avg@8 over OPD by an average of 1.60 and 1.95 percentage points when distilling Qwen3-8B into 0.6B and 1.7B students, respectively. It also achieves the strongest results on four transfer benchmarks. --- ### FedSumUp: User-Auditable Privacy-Aware Representation Sharing for Resource-Constrained Federated Intelligence Authors: Jingwei Zhao, Tiantong Sun, Yuanyuan Song, Jinhuan Guo, Wei Zishuo, Shengyu Huang, Ziyuan Ren, Wei Chen, Xiaojin Zhang Published: 2026-10-15 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2610.21194v1 Existing federated data condensation methods face privacy risks, as uploaded synthetic data may preserve sensitive information and remain vulnerable to reconstruction attacks. Moreover, their generation often incurs considerable client-side computational overhead, limiting deployment on resource-constrained devices. To address these issues, we propose FedSumUp, which employs a learnable lossy compressor on clients to generate compact and visually interpretable representations. By controlling information capacity, FedSumUp reduces privacy leakage while allowing users to directly assess the privacy-utility tradeoff. We further introduce a dual-objective optimization mechanism to preserve task-relevant semantics while suppressing reconstruction risks. The compressor is trained on the server and only performs lightweight inference on clients. Since the server cannot access raw data, we develop a data-free closed-loop optimization strategy that optimizes the compressor by minimizing the discrepancy between original and twice-compressed representations after structure-preserving upsampling. Experiments on BloodMNIST, CIFAR-10, and ChestMNIST demonstrate reconstruction PSNR as low as 8.56 dB (with synthetic PSNR as low as 5.45 dB), client runtime reductions up to 96.5% (from 778s to 27s on ChestMNIST), and competitive classification accuracy (89.72% ChestMNIST, 82.24% BloodMNIST, 65.63% CIFAR-10), while remaining inherently robust to non-IID data distributions. --- ### ControlFlow3D: Distilling Multi-View Knowledge into Latent Flow Matching for Point Cloud Upsampling Authors: Yuang Liu, Zhi Zuo, Zhengkai Zhao, Lirui Zhang, Pan Gao, Hao Feng, Zhengzhe Liu Published: 2026-10-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.21190v1 Point cloud upsampling is essential for 3D applications but remains challenging due to sparse, under-constrained observations. Multi-view images can resolve geometric ambiguity, but existing multi-modal methods do not fully exploit visual cues. We propose ControlFlow3D, a framework that distills knowledge from pretrained foundation models into a lightweight generation network during training, enabling strong performance without multi-view images available at test time. Specifically, our method performs conditional flow matching in a structured latent space defined by a frozen 3D encoder. Multi-view image tokens and 3D latent tokens are jointly clustered into shared prototypes via unsupervised soft KMeans; the resulting prototypes guide the flow trajectory through velocity control and are aligned by a consistency loss that progressively transfers image knowledge into the base network. A Mamba-based geometry decoder then maps latent features to dense coordinates with linear complexity. We also construct ShapeNetPU, a 35K-object multi-modal benchmark that is 31 times larger than prior datasets. Extensive experiments across multiple benchmarks demonstrate the effectiveness of our method and its strong generalization capability. --- ### Resisting Harmful Instructions through Training-Free Weight Editing Authors: Ali Ebrahimpour-Boroojeny, Xiaocong Yang, Samuel Schapiro, Zahra Borhani, Francisco R. Ortega, Yujia Zheng, ChengXiang Zhai Published: 2026-10-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.21189v1 Instruction-following language models can comply with requests that conflict with intended behaviors and safety alignment. We introduce a training-free weight-editing approach for reducing compliance with targeted undesirable instructions. Our method needs only forward passes on a small set of prompt pairs per target behavior, and because the edit is stored in the model's weights, changing or deleting instructions in the prompt cannot undo the weight modification. We evaluate the approach on two target harmful behaviors across five instruction-tuned models: instructed falsehood and instructed sexism. On two instructed-lying benchmarks, it improves mean honest response rates by 6.2 and 4.6 percentage points over the strongest alternative, significantly on three of the five models and within noise on the other two. In a controlled study of seven prompt formats, it maintains higher honest-response rates than single-layer activation steering when orders to lie arrive in single-turn formats not used to construct the edit. For instructed sexism, it reduces the mean sexist-response rate from 57.9% to 24.3%; combining the edit with a fairness prompt reduces it further to 11.9%. These results establish our contrast-based weight editing approach as an effective training-free intervention in two distinct behavioral domains, supporting its use both independently and alongside prompt-based safeguards. --- ### Sensor Diagnosis for Fuel and Emissions Monitoring in Heavy-Duty Diesel Vehicles Authors: Tejas Dahiya, Saurabh Kumar Gupta Published: 2026-10-15 Categories: cs.LG, eess.SY arXiv: https://arxiv.org/abs/2610.21188v1 Faulty sensor readings can distort estimates of fuel use and carbon dioxide emissions from diesel engines. We evaluate two procedures that use relationships learned from healthy measurements to diagnose faults and guide fuel correction. The diagnosis procedure tests whether replacing a suspected faulty reading with an estimated healthy value helps a model predict another sensor's recorded reading more accurately. It then predicts the fault type and decides whether to report the diagnosis. We evaluate five synthetic fault types on 217 steady-state operating points from a heavy-duty diesel engine, excluding all measurements at selected engine speeds from training. Across 31,500 fault-injected groups of 20 operating points, it issues diagnoses for 77.3% of groups, with 92.1% of diagnoses issued on these groups correct. The fuel correction procedure uses a different sensor-selection rule at individual operating points, testing how each replacement changes the largest prediction error across all six sensors. Fuel correction requires a fault alarm and engine speed and torque close to the training conditions. A fuel reading is replaced only when its replacement reduces the largest prediction error sufficiently more than replacements for the other sensors. Assuming faults in 1% of one-hour scenarios, equally likely sensors and fault types, and equal time at each measured condition, selected fuel corrections reduce mean absolute error in calculated combustion CO2 by 83.8%. On this engine map, learned relationships support complete sensor diagnoses and fuel corrections that improve emissions accounting while preserving unaffected readings. --- ### Mine, Sample, Render: Test-Time Diversity Alignment Of Generative Models Authors: Kostas Triaridis, Morris E. Sharp, Nebojsa Jojic Published: 2026-10-15 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.21185v1 Modern generative models produce high-quality individual outputs but struggle to sample diversely, even when explicitly instructed to do so. We introduce MINE-SAMPLE-RENDER (MSR), a test-time approach that externalizes the diversity into an explicit, corpus-derived sampling procedure. Our pipeline (i) mines an interpretable categorical schema from a corpus of real artifacts and supplies statistics for sampling; (ii) samples attribute configurations from the corpus-derived statistics; (iii) uses a generative model purely as a conditional renderer of a sampled configuration. Across weather report generation, user simulation, webpage design, text-to-image generation, and agent-generated 3D assets, we evaluate the diversity and output quality of MSR-guided generation and show that MSR improves alignment with corpus distributions and diversity of generated outputs. --- ### Beyond Retrieval Failure: Understanding Why LLMs Miss Evidence in Multi-Hop RAG Authors: Jiaqi Wei, Wenxuan Huang, Chengdong Xu, Xiang Zhang, Wanli Ouyang Published: 2026-10-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.21184v1 Multi-hop retrieval-augmented generation (RAG) requires an agent to retrieve evidence for a sequence of dependent sub-questions. When a wrong answer lacks a required passage, the passage may be inaccessible to the retriever, or the agent may have failed to issue a query that would retrieve it. Standard retrieval evaluations conflate these two causes. We study how much apparent retrieval failure is instead caused by search drift: the search no longer tracks an unanswered sub-question. Holding the retriever, corpus, and generation model fixed, we introduce ExecutionRAG, a training-free requirement register that records open sub-questions and their supporting evidence. The register changes search guidance but not evidence access, so each gold passage it recovers certifies that the passage was reachable by the original retriever. On 1,000 MuSiQue questions, the number of wrong answers with unretrieved required evidence falls from 382 to 234 with all-MiniLM-L6-v2 and from 383 to 274 with Qwen3-Embedding-0.6B. These counts correspond to 69% to 44% and 66% to 48% of each system's wrong answers, respectively. Crucially, evidence recovery does not produce a proportional reduction in total error: premature resolutions and abstentions increase as missing-evidence failures decrease. The central finding is therefore a shift in the remaining bottleneck, from guiding search toward required evidence to verifying that the retrieved evidence is sufficient. --- ### Monotone Piecewise-Linear Harmonization of Multitemporal Multispectral Surface Reflectance With Unsupervised Deep Multiview Pseudoinvariant Features Learning Authors: Lino Garda Denaro, Chia-Hsiang Lin Published: 2026-10-15 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2610.21183v1 Surface reflectance products derived from optical satellite may exhibit systematic inconsistencies across acquisition dates, because atmospheric correction is generally performed independently for each image. Such residual biases distort the temporal behavior of invariant ground targets and reduce the reliability of multitemporal surface reflectance analysis. This study proposes Deep Multitemporal Generalized Canonical Correlation Analysis (DeepMGCCA), an unsupervised deep multiview pseudoinvariant feature learning framework that integrates Deep Generalized Canonical Correlation Analysis (GCCA) with Multivariate Alteration Detection (MAD) to identify deep-pseudoinvariant features (DIFs) for the removal of surface reflectance biases across multitemporal satellite observations. Unlike conventional MAD-based approaches that rely on linear GCCA, the proposed framework replaces date-specific linear projections with a shared convolutional encoder. The framework learns deep invariant features (DIFs) directly from pixel-weighted canonical variates via iterative reweighting strategy, while a reconstruction regularizer preserves surface reflectance information and prevents degenerate collapse from suppressing genuine temporal variability. Experiments were conducted on four annual Landsat-8/9 and Sentinel-2 acquisitions across four regions of interest (ROIs) to evaluate four DIF-based harmonization transforms. A monotone piecewise-linear transform derived from DIFs quantiles consistently achieved the largest bias reduction, lowering the between-date spectral angle by up to 2.54 and RMSE by 0.015, and raising PSNR by up to 4.04~dB. These findings demonstrate the potential of deep invariant feature learning for multitemporal surface reflectance bias removal while highlighting the importance of preserving physically meaningful temporal and spectral information during nonlinear representation learning. --- ### Does Latent Chain-of-Thought Actually Reason? A Single, Unifying Taxonomy for Latent Reasoning Authors: Jingjie Qiu, Sheldon Yu, Xunyi Jiang, Jiajin Liu, Zihan Huang, Zhendong Chu, Tong Yu, Julian McAuley, Junda Wu Published: 2026-10-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.21182v1 Latent chain-of-thought replaces written reasoning steps with continuous hidden states, giving models additional steps to compute before answering. It remains unclear what computation these steps actually perform. High task accuracy and decodable intermediate answers do not establish that a model uses its latent chain to reach an answer. We study this question across twenty-one model-task configurations covering three training recipes, three reasoning tasks, and two backbones. We combine chain deletion and content replacement with probes and trajectory analysis to test whether the chain affects the answer, what it encodes, and how its states change. On logical tasks, COCONUT often carries an answer that is already readable before the chain begins. Its states settle early, and deleting the chain leaves predictions almost unchanged. Per-step supervision produces an ordered layout of reasoning steps and can make the model depend on the chain. Yet even an ordered chain can act as a placeholder, with deletion hurting performance while content replacement leaves answers unchanged. On arithmetic tasks, all tested recipes show dependence on chain content. These results show why readable latent states alone are insufficient evidence of reasoning. We introduce a taxonomy that separates what a chain represents from how the model uses it. Seen this way, earlier reports no longer compete: placeholder tokens, collapsed superposition and step-dependent causal roles are each consistent with a different kind of chain, each obtained on a different task, training recipe or measurement. Once a study says which property it tested, whether the model uses the chain, what the chain holds, or how its state moves, claims about latent reasoning can be compared. --- ### Judging the Judges: Confidence and Disagreement in Rubrics as Rewards Authors: Michael Tian-Yue Liu, Anne Harrington, Trevor Darrell, Yutong Bai Published: 2026-10-15 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.21179v1 Rubrics as Rewards (RaR) extends reinforcement learning to non-verifiable domains by using an LLM judge to score responses against a structured rubric. Prior work has focused on improving the rubric or strengthening the single judge, with comparatively little attention to how different single or multiple judges might be used during RaR training. We first show that judge identity alone produces a substantial spread in scores when training Qwen3-4B-Base on RaR-Medicine and RaR-Science across five frontier and open-weight judges. Building on this, we propose RaRE (Rubrics as Rewards with Ensembles), a novel judge ensemble strategy for RaR with two mechanisms: a soft-Likert reward that uses judge logprobs to weight more confident judges more heavily, and a drop-on-disagreement mask that excludes high-disagreement rollouts from the GRPO update. We find that this design is critical: while a naive average of judge scores fails to outperform the best single judge, RaRE outperforms every single-judge RaR variant on both HealthBench and GPQA Diamond, with per-theme analysis showing that it inherits the complementary strengths of its constituent judges. Our findings establish judge ensembling as a compelling axis for improving RaR. --- ### AgentEval: Evidence-Bounded Assessment of Stateful Agents Authors: Ruiqi Gao Published: 2026-10-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.21177v1 Task completion alone does not determine whether a stateful agent satisfied its obligations, and a recorded judgment does not guarantee that its supporting evidence remains valid. We present AgentEval, a system that carries a contract-bound assessment record through tool execution, state and event capture, report qualification, and case maintenance. It separates what the agent did, what the evidence establishes, and whether the conclusion is supported for present use. On 32 tool-world administrations, independent checks agree on all 30 complete episodes, distinguishing satisfied, violated, and unresolved obligations; two interrupted administrations are retained. Controlled interventions on 48 evidence views expose 36 binding faults missed by hash-only checks without changing agent behavior. Scenario Studio connects reviewed cases to 12 two-turn reports with 24 independently checked answers. A separate public-benchmark study on 192 held-out executions reveals ten completed return subgoals within broader task failures and isolates the effect of missing evidence. These studies show how an executable assessment record makes scope, evidential support, and report reuse inspectable across an agent evaluation workflow. --- ### Language Models Share a Readout Bottleneck in Working Memory Authors: Dongyu Gong Published: 2026-10-15 Categories: cs.LG, cs.AI, cs.CL, q-bio.NC arXiv: https://arxiv.org/abs/2610.21176v1 Large language models (LLMs) reproduce a human working-memory signature on the N-back task: performance declines as memory load N increases, and errors concentrate on lures, items that repeat the current stimulus at a neighboring but incorrect serial position. We ask whether this shared behavioral signature reflects a shared mechanism. The literature offers two candidate accounts. On a precision account, softmax attention cannot concentrate its weight on the item N positions back, so adjacent items are retrieved instead. On an interference account, attention selects the correct item, but the content of competing items corrupts the decision. We dissociate these accounts in 15 pretrained LLMs from three families (70 million to 14 billion parameters) and in minimal transformers trained from scratch. In all three families, the attention heads that carry the task attend to the target on most missed matches. Linear probes decode near-perfectly whether a matching letter occurred at the target or at a lure position, even on trials where the model false-alarms to the lure, although its own decisions barely distinguish the two. Sharpening attention yields negligible gains, whereas suppressing the letter identity of non-target items improves sensitivity (d') in nearly all model-by-load conditions. In larger models the task is spread over more heads, and removing interference helps more. In minimal transformers, precision limits a single attention layer, but a second layer removes this constraint. The working-memory limit of LLMs therefore lies in reading items out under interference rather than in locating them, consistent with interference accounts of human working memory. --- ### MemScope: Evolving Agent Memory Architectures through Localized Code Repair Authors: Miao Su, Yucan Guo, Zixuan Li, Long Bai, Zhongni Hou, Xiaolong Jin, Jiafeng Guo Published: 2026-10-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.21170v1 Agent memory architectures define how LLM agents store and reuse experience across tasks, but they are typically fixed after deployment, limiting their adaptability across task types. Recent self-evolving approaches instead adapt these memory architectures using execution feedback, typically represented as evaluation scores or compressed summaries. However, such coarse-grained feedback is insufficient for precise failure localization in current agent systems, where long-horizon task execution involves multiple interacting components. Without a precise failure location, existing approaches lack a clear code-level target for modification, leaving the update scope weakly constrained and often leading to large-scale rewrites of an otherwise capable memory architecture. We propose MemScope, a framework for evidence-grounded, localized evolution of an existing memory architecture. Its tool-using Patch Agent jointly inspects raw execution traces, runtime memory state, and current architecture code to identify repair targets and apply bounded, in-place edits under provider-identity and memory-compatibility constraints. On GAIA, the trace-and-memory inspection variant achieves 86.67% accuracy, compared with 70.00% for trace-only and 63.33% for summary-only feedback. Under xBench tasks, the evolved memory architecture improves over its original version from 49 to 55 correct answers with DeepSeek V3.2 and from 50 to 53 with Kimi K2.7 Code. On disjoint ALFWorld unseen tasks, success rises from 50.75% to 71.64%. Across archived architecture-snapshot transitions, the median code-change ratio is 4.4%. These results support fine-grained execution evidence as a basis for localized, in-place memory-architecture evolution. --- ### GRADS: Graph-Regulated Agentic Data Synthesis with Controllable Difficulty Authors: Gaocheng Yang, Ruijie Tao, Kai Ye, Senhua Zhang, Zhengqin Zhu, Ziyang Li Published: 2026-10-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.21167v1 Deep research agents are increasingly deployed to retrieve precise information from large corpora, yet multi-hop, long-horizon tasks remain challenging. Synthetic data generation has emerged as a scalable solution, with existing pipelines typically expanding seed tasks to increase their apparent depth and breadth. However, this expansion does not reliably translate into necessary reasoning: newly introduced evidence may be only weakly coupled to the answer, creating a mismatch between intended and empirical difficulty. To address this problem, we introduce GRADS, a graph-guided agentic data synthesis framework with explicit difficulty control. GRADS runs a closed loop of seed selection, evidence expansion, question--answer construction, and verification while maintaining a graph of the evidence and inference dependencies required to derive each answer. At each step, it conditions generation on a relevant subgraph, preserving indispensable inference without accumulating irrelevant context. Experiments across security, software-engineering, and scientific-document domains show that GRADS consistently generates verified tasks with empirically separated difficulty distributions, as measured by independent solvers. Moreover, under matched training budgets, post-training on this data delivers consistent gains at every level: SFT raises the solution-termination rate to over 95% while cutting tool calls and turns by up to 75%, RL trims tool use by up to a further 19.5%, and on our held-out, domain-specific benchmarks, the resulting 4B model matches Sonnet~4 on software engineering and surpasses it on the scientific and security domains. --- ### From Long Context to Selective Memory:A Survey of Memory-Centric Compression for Large Language Models Authors: Chaogui Gou Published: 2026-10-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.21165v1 Long-context capability has become essential for large language models (LLMs) to handle complex tasks, yet continuously expanding the context window does not remove the computational, storage, and information-selection pressures incurred at inference time. Existing work on prompt compression, KV-cache management, efficient serving, retrieval augmentation, and agent memory is usually discussed in isolation, leaving the flow of information between storage and computation insufficiently understood. This survey reframes long-context compression as a memory-management problem for allocating inference-time resources. We distinguish compute-active memory, which directly participates in model computation, from compute-inactive memory, which lies outside the computation path but can be stored, retrieved, updated, or forgotten, and we characterize offloaded KV caches, persistent prefix caches, and precomputed KV states as intermediate states on the activation path. On this basis, we formulate writing, offloading, recall, retrieval-and-injection, materialization, eviction, consolidation, and forgetting as state transitions within an information lifecycle, and introduce a budgeted cost model that places these operations in a single cost account. The resulting framework unifies short-term context compression, long-term memory management, and the transitions between them, and shows that the central challenge is not merely reducing information volume but deciding which information should participate in costly inference, when, and in what form. We further summarize evaluation dimensions, benchmark gaps, and open challenges, and argue that future research should move from static, pointwise compression toward dynamic, governable, lifecycle-aware memory management. --- ### Automatic Sentence Completion Using Bengali Audio Speech with a Transformer-Based Early Speech Recognition System Authors: Md Asif Akram, Arif Faisal, Sakir Hossain Faruque, Sharun Akter Khushbu Published: 2026-10-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.21164v1 Dementia severely impairs communication abilities and turns everyday conversations into challenging experiences. Individuals affected by dementia frequently struggle to express their thoughts or complete sentences, making it difficult for family members and caregivers to understand their needs. This study proposes a novel approach to assist dementia patients by developing an integrated system that detects signs of dementia through Bangla speech and text analysis and provides sentence auto-completion support during conversations. To achieve this, recorded voices from individuals with and without dementia were analysed, and key acoustic features were extracted to capture vocal patterns associated with cognitive decline. A transformer-based model was employed to transcribe voice signals into text for linguistic analysis. In the classification task, several Machine Learning (ML) and Deep Learning (DL) models were evaluated using both acoustic and textual representations, and the LSTM model architectures demonstrated strong capabilities for modelling contextual patterns in speech and language data. For the sentence auto-completion task, a sequential learning model based on a Bidirectional LSTM (Bi-LSTM) network with an attention mechanism was developed to sequentially complete partially expressed Bangla sentences during conversation. This research bridges the gap in dementia analysis in an underrepresented language and implements a sentence auto-completion framework for cognitive disorders. --- ### Coordination-Free Workload Regularization for Variable-Cost Distributed Training Authors: Tao Huang, Chen Zhu, Antonio Alonso, Daming Li, Adarsh Goura, Jaideep Ray, Yitong Zhou Published: 2026-10-15 Categories: cs.DC, cs.LG arXiv: https://arxiv.org/abs/2610.21162v1 Synchronous data-parallel training usually assigns every rank the same number of records, even when record costs vary by orders of magnitude. For variable-length models, this converts input variation into idle time because each step waits for its most expensive rank-local batch. We present Batch Cost Lookahead (BCL), a coordination-free data-loading policy that buffers a bounded rank-local window and repartitions it into fixed-cardinality packs with balanced estimated cost. BCL preserves the trainer's record-count contract and requires neither cross-rank metadata exchange nor runtime modification. In simulation over public workload distributions, enabling BCL reduces per-rank estimated batch-cost variability by up to 82.8%. Across 13 NeMo-RL SFT corpora on eight H200 GPUs, rank-local BCL runs 1.050 to 1.167 times faster than pooled MFFD. Compiled H200 measurements on an internal sequence workload show speedups of 1.197 to 1.343 times over packed execution from one to four nodes. We also identify a memory-feasibility boundary: a p99 cap for high-variance or OOM-prone data bounds outliers before BCL balances the rest. These results show that substantial variable-cost imbalance can be removed at the data-loader boundary, while clarifying when data preparation or broader coordination is still necessary. --- ### VisualTrust: Video Reasoning under On-Screen Claim Framing Authors: Huachao Zhu, Junjielong Xu, Sicheng Li, Liang Yang, Mingtao Chen, Zhichao Hu, Li Jiang, Pinjia He Published: 2026-10-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.21159v1 On-screen text can describe what a video shows, or it can frame what the video is supposed to mean. Current benchmarks treat both alike, testing whether a model can read the text rather than whether it should trust it. We study claim deference, multimodal large language models' tendency to let an on-screen claim override conflicting visual evidence. We introduce VisualTrust, a counterfactual benchmark with 5,063 cases across 14 claim-fact classes. Each case pairs a question with three versions of the same video: one with no claim, one with an accurate claim, and one with a misleading claim that alters a single grounded fact. The option the misleading claim supports is the trap answer. Across seven open-weight and four proprietary models, mean accuracy falls from 90.1% without a claim to 51.9% with a misleading claim. Among initially correct responses, 42.8% flip to the trap answer and only 0.6% become other errors. Strong no-claim accuracy does not ensure resistance. We also introduce DEAR (Decoupled Evidence Arbitration and Reading), a training-free agent for video question answering that separates evidence arbitration from reading. An independent check reports conflicting evidence, a selector weighs it without a fixed modality priority and blinds what it withholds, and the reader answers from the resulting video in a fresh context. On 500 videos across three proprietary models, DEAR raises accuracy under misleading claims from 47.2--64.0% to 81.8--85.2% and reduces trap-answer selection from 34.4--50.8% to 11.6--15.0%, while preserving no-claim accuracy. --- ### Stop Training Against Soft Users: Mentalized Adversarial Self-Play for Proactive Dialogue Authors: Zanwu Liu, Dan Zhang, Xiaodi Wang, Yongbo Mao, Xiaoyang Guo, Yonglin Wu, Peiyue Jiang, Yangyang Wei, Zecheng Lin Published: 2026-10-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.21156v1 Proactive dialogue agents must guide multi-turn interactions toward task goals while adapting to users whose intentions and attitudes evolve. Existing planners improve system side action selection through search, learned policies, or user aware planning, but are often trained and evaluated against fixed or overly compliant simulators; as a result, high simulated success can reflect soft user bias rather than robust dialogue ability. We introduce MASP, a Mentalized Adversarial Self Play framework that treats proactive dialogue as a partially observable game between a system and a rationally resisting user. MASP represents the user's evolving mental state with a BDI based latent state, separates reward side teacher mentalization from policy side student mentalization, and alternates self play updates for the system and user policies. This turns robustness to rational resistance into a training objective rather than only an evaluation condition. Across diverse proactive dialogue benchmarks, compared with the widely used SFT and Planner-only approaches, MASP substantially improves success rate (SR) and rationality constrained success (RCSR), reduces average turns (AT), and performs better against hard users who make the task goal more difficult to achieve. --- ### CARE-SD: Explainable Reasoning Architecture for Local SLM Self-Disclosure Analysis in Textual Data Authors: Aisvarya Adeseye, Adeyemi Adeseye, Mohammad Tahir, Jouni Isoaho Published: 2026-10-15 Categories: cs.CR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.21151v1 Cybersecurity interviews uncover critical security experiences, behaviors, and privacy concerns often not fully captured by conventional technical assessments. Consequently, identifying genuine self-disclosures is challenging because statements are context-dependent, categories overlap, and automated interpretations may introduce unsupported claims. Locally deployed Small Language Models (SLMs) protect sensitive participant data by keeping processing within controlled environments, but their limited reasoning capabilities make simple prompting insufficient for context-aware and factually reliable analysis. This study developed CARE-SD (Context-Adaptive Reasoning and Explanation for Self-Disclosure), a novel four-module architecture integrating context-adaptive processing, hierarchical disclosure reasoning, explanation-consistency verification, and cross-batch reconciliation. We evaluated three local SLMs, including Llama 1B, Qwen 1.5B, and Llama 3B, using 82 independently annotated cybersecurity interviews across five organizational sectors. Comparisons included conventional classifiers, three prompting strategies, larger 8B--32B models, and architectural ablations. Two independent reviewers assessed disclosure labels, factual claims, and explanation correctness. CARE-SD improved the accuracy and evidence reliability of SLMs, increasing Llama 3B Macro-F1 from 0.80 to 0.88 while reducing unsupported claims by 60\%. Remarkably, the 3B model matched the 20B reference model in category Macro-F1, demonstrating the effectiveness of the architecture without requiring a larger model. --- ### From Observation to Intervention: Distilling Self-Generated In-Context Demonstrations via Executable Causal Intervention Authors: Minming Ye, Min Liu, Haoang Chi, Ciheng Wu, Naiyang Guan Published: 2026-10-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.21149v1 Self-generated In-Context Learning (ICL) enables LLMs to synthesize their own few-shot demonstrations, often outperforming manual prompts. However, existing methods filter demonstrations by observation, assuming a rationale is high-quality if it leads to the correct output. We show such filtering suffers from \textit{observational equivalence}, whereby both faithful causal rationales and spurious post-hoc rationales can yield same outputs and are statistically indistinguishable from observation alone. Inspired by independent causal mechanisms, we argue that faithful rationales imply \textit{transfer invariance}, in which causal rationales should remain effective across logically similar samples. We instantiate this criterion as \textbf{E}xecutable \textbf{C}ausal \textbf{I}ntervention for \textbf{D}emonstrations \textbf{D}istillation (ECI2D), which abstracts language rationales into executable programs and applies the causal interventions ($do$-operator) on logically similar samples, retaining only those demonstrations that imply transfer invariance. Experiments on math, logical and commonsense reasoning benchmarks demonstrate that ECI2D consistently outperforms observation-based ICL while retaining far fewer demonstrations, with gains exceeding 7 points as the test distribution shifts. --- ### All-in-One Memory: Process-Rewarded Reinforcement Learning for Memory Agents Authors: Bingbing Wang, Jingjie Lin, Weiming Qiao, Jing Li, Ruifeng Xu Published: 2026-10-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.21147v1 Large language models increasingly rely on external memory to answer queries grounded in long-horizon histories such as multi-session dialogues and lengthy documents. However, existing memory methods often optimize retrieval and memory construction separately, without a shared reward space for evaluating search, writing, and stopping decisions. To address this, we propose All-in-One Memory (AiO-Mem), which organizes these operations as transitions over a shared evidence state and directly evaluates the semantic quality of each action in a unified reward space. AiO-Mem compiles heterogeneous histories into source-traceable multi-view events, providing a shared substrate for retrieval and memory writing. A unified memory policy actor then rolls out complete interaction trajectories over this shared evidence state. A separate trajectory-conditioned process reward model is trained through evidence-grounded supervised fine-tuning and trajectory-level DPO to assign process scores to the collected trajectories. These scores are aggregated into an action-balanced trajectory reward and used by Process-Aligned DAPO (PA-DAPO) to optimize the memory policy. Across long-context memory benchmarks, AiO-Mem consistently improves answer accuracy over both static memory systems and RL-trained memory agents. --- ### CoSTA: Compressed Speech Token Adaptation for Efficient Spoken Dialogue Models Authors: Yingzhuo Deng, Chong Li, Bingxin Liu, Yi Shu, Tianyu Peng, Can Xie, Siyao Song, Shuo Ren, Jiajun Zhang Published: 2026-10-15 Categories: cs.CL, cs.AI, cs.SD arXiv: https://arxiv.org/abs/2610.21143v1 Spoken Dialogue Models (SDMs) typically share a speech-token space for generation and synthesis, leading to long autoregressive sequences and costly inference. Lower-rate speech tokenizers shorten sequences but may introduce compression-quality trade-offs and costly replacement without breaking this coupling. To address this limitation, we propose CoSTA, a compatibility-preserving post-hoc framework that decouples generation and synthesis token spaces while retaining the original speech tokenizer and decoder. CoSTA extends the generation token space with compressed representations via mean-initialized vocabulary extension, pronunciation adaptation, and dialogue adaptation, followed by deterministic expansion back to the original speech-token space before synthesis. On bilingual speech-dialogue benchmarks, CoSTA achieves approximately $1.7\times$ expanded speech-token generation speed, lower full-response latency, and higher throughput while preserving response quality. Analyses show more sustained interaction under limited budgets and a practical trade-off among compression, decoding efficiency, and quality. Further experiments demonstrate cross-architecture transfer and complementarity to low-rate tokenization. --- ### When is a better LLM worth paying for? Stochastic Optimization with Switching Mixed-Fidelity Oracles Authors: Swati Gupta, Tianjiao Li Published: 2026-10-15 Categories: math.OC, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.21139v1 Large language models (LLMs) are increasingly used upstream of decision-making to clean data, detect label errors, and reconstruct missing values. Yet LLM-assisted data curation creates a new operational tradeoff: higher-fidelity models and richer prompts can be substantially more expensive, while the value of this additional fidelity depends on the downstream optimization accuracy. This raises the central question of this work: when should one pay for a better LLM, given a specific downstream task at hand? We study this question through stochastic optimization with mixed-fidelity first-order oracles, which can have systematic bias and state-dependent variance. We develop two cost-aware algorithmic frameworks that allow adaptive switching between stochastic oracles. With known bias, the first meta-algorithm applies a restarted, cost-aware policy that adaptively selects oracle fidelity across optimization stages. Its cumulative cost is no larger than that of the best fixed oracle in hindsight and can be substantially smaller. With unknown bias, we develop a budgeted certification scheme that uses occasional trusted-gradient evaluations to certify the optimization progress and eliminate unsuccessful oracle sources, and show an explicit tradeoff between certification cost and delayed detection of biased sources. We provide concrete realizations of these meta-algorithms by applying biased stochastic gradient extrapolation (SGE) and recursive regularization under state-dependent noise as subroutines. Synthetic and LLM-completion experiments illustrate the qualitative switching behavior predicted by the theory: the adaptive policy skips several expensive LLM oracles and substantially reduces cumulative cost relative to fixed high-fidelity alternatives while achieving comparable accuracy. --- ### CleanRM: Reward Modeling from Noisy Feedback with a Few Clean Feedback for RLHF Authors: Licheng Pan, Haocheng Yang, Yuzhou Chen, Yichen Sun, Yuan Lu, Yunfei Teng, Jiajun Fan, Guangyi Liu, Zhixuan Chu, Hao Wang Published: 2026-10-15 Categories: cs.AI, stat.ML arXiv: https://arxiv.org/abs/2610.21138v1 Feedback noise is pervasive in preference data, arising from subjective human judgments, annotation mistakes, and imperfect LLM judges. Standard reward modeling trained on such feedback yields a biased estimate of the clean risk. Although classical denoising methods are directly applicable to noisy feedback learning, they generally assume a uniform noise ratio across samples. However, this assumption fails for feedback data, where noise is intrinsically sample-wise. To address this challenge, we propose CleanRM, which uses a few clean feedback to calibrate sample-wise noise ratios via optimal transport. Specifically, CleanRM aligns the joint distribution of preferences reverted from noisy feedback with that of clean feedback and then trains the reward model using a noise-corrected surrogate loss. Theoretically, we prove that the resulting objective is unbiased with respect to the clean risk. Extensive experiments demonstrate that CleanRM outperforms state-of-the-art denoising baselines and yields more effective downstream RLHF alignment. --- ### OnBodyAI - Why the Next AI Needs a Body Authors: Michael Beigl Published: 2026-10-15 Categories: cs.HC, cs.AI, cs.GL arXiv: https://arxiv.org/abs/2610.21137v1 The next AI will not win by knowing more about the world. It will win because it knows you: because it lives on your body, works for you and answers to you. That is what the term OnBodyAI stands for. It describes what happens when large language models are given a body, and what research and industry need to make that happen. This article is based on my talk in the Industrial Panel at UbiComp/ISWC 2026 in Shanghai (October 13, 2026) and follows its ten key statements. --- ### Pathwise Shrinkage and Probabilistic Calibration of the Multiplicative Half-Cauchy Process Authors: Siddhesh Kulkarni Published: 2026-10-15 Categories: stat.ME, cs.LG, math.PR, math.ST arXiv: https://arxiv.org/abs/2610.21136v1 We characterize the multiplicative half-Cauchy process through its log-scale random-walk representation, establishing shrinkage, expansion, and critical regimes, almost-sure summability, local rebounds, and effective dimension. We also derive a semi-analytic calibration rule linking interpretable prior probability statements to its scale parameter. --- ### Stronger Judges Do Not See More: Deployment-Integrity Blindness in LLM Evaluation Authors: Jianchang Su, Dawei Xiang, Yifan Zhang, Wei Zhang Published: 2026-10-15 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2610.21135v1 LLM-agent evaluation reports behavioral scores but leaves the identity of the deployed runtime stack unreported. A tampered deployment that preserves evaluated outputs passes every output-only evaluator. We introduce DIB-Bench, a benchmark that measures this deployment-integrity blindness across 7,560 scored examples, six tamper types, and an evaluator ladder from regex scorers through LLM judges to GPT-5-nano. Stronger evaluators accept more tampered outputs: mean acceptance rises from 88.6% (rule-based) to 94.1% (GPT-5-nano), and a trigger-conditional tamper invisible on the evaluation suite produces 48-100% harmful outputs, rising with model capability. A PAC-style bound shows that tampers with zero output shift are undetectable from outputs at any sample size; a manifest-hash identity channel detects them with zero samples. Behavioral fingerprinting identifies the model component above chance (76.7%) but covers one of six stack components. We also propose a graded deployment-identity descriptor for evaluation reports. --- ### Predicting Live Birth After Fresh Embryo Transfer in IVF/ICSI: Differential ICM/Trophectoderm Morphology Encoding and a Hybrid Attention--Logistic Regression Ensemble Authors: Abdul Raheem Shahzad, Jinxin Chen, Ming Zhang, Juan Deng Published: 2026-10-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.21134v1 Predicting live birth before fresh embryo transfer could support shared decision-making in IVF/ICSI, but routine clinical data are small, heterogeneous, and contain pathway-dependent variables prone to outcome leakage. We aimed to construct a curated single-centre IVF/ICSI dataset and develop a prediction model suited to small tabular clinical data. \textit{Materials and Methods:} We assembled 616 fresh embryo-transfer cycles (251 live birth, 365 non-live birth) with clinical, laboratory, and embryological predictors, and embryo morphology encoded with a novel differential weighting of the inner cell mass and trophectoderm. After KNN imputation, robust scaling, and selection of 50 features, we developed a Hybrid Attention Network (HAN), a learnable feature-attention gate followed by a compact multilayer perceptron, and a HAN + logistic-regression (LR) ensemble with a validation-tuned weight. Models were benchmarked against classical machine learning, TabPFN, and text-serialized language models on a held-out test set; AUC-ROC was the primary metric. \textit{Results:} The HAN + LR ensemble achieved the highest test AUC-ROC (0.710; accuracy 0.710, F1 0.630), ahead of the HAN backbone alone (0.700), logistic regression (0.667), the TabPFN + LR hybrid (0.666), and TabPFN (0.650). Text-serialized language models performed near chance (AUC $\le$ 0.61). The differentially weighted trophectoderm feature ranked highest by consensus importance across models. \textit{Discussion:} A compact attention network combined with a linear model outperformed both components and strong foundation-model baselines on a small clinical cohort. \textit{Conclusion:} The curated dataset and HAN + LR ensemble offer a transparent, reproducible basis for IVF/ICSI live-birth prediction; external validation is the next step. --- ### Trajectory Prediction Method for person under WSN with Hierarchical Envelope Adversarial Domain Adaptation Authors: Wenqian Jiang, Qifeng Sun, Xiaosong Gao, Xin Zou, Xingrui Ni, Yuan Hu, Yongming Li Published: 2026-10-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.21132v1 Pedestrian trajectory prediction holds significant applications across autonomous driving, intelligent surveillance, and smart cities. However, the complexity and unpredictability of pedestrian interactions make this task a persistent challenge. Current models face two common limitations: 1) Consider only a single type of social coupling. This introduces redundant interactions. More critically, it fails to account for the varying nature of trajectory coupled across different scenarios and between different pedestrians. Consequently, models cannot deeply adapt to diverse scenes. 2) Inadequate domain shift handling. Although very few methods address domain shift, they rely on statistical criterion-based domain distribution alignment. Such approaches exhibit strong dependency on predefined statistical metrics. This leads to significant limitations in complex and dynamic environments. To address these problems, a Hierarchical Envelope Adversarial Domain Adaptation with Loosely-Tightly coupled model (HEADA-LTCTPM) is proposed. First, an envelope sample construction mechanism was proposed. It constructs envelope samples and extends them into graph structures. Secondly, an adversarial domain adaptation module was proposed. This integrates both local and global domain adaptation strategies. It dynamically adapts to diverse coupled relationships across scenarios. These innovations collectively enhance prediction accuracy and robustness. In the experimental section, two representative public datasets were employed for validation and comprehensive comparisons with six relevant baseline algorithms were conducted. Results demonstrate that our model achieves significantly higher accuracy compared to existing methods, with the ADE and FDE metrics reduced by 17.6% and 19.1% respectively. The time overhead meets practical requirements, which verifies the effectiveness of our key innovations. --- ### Sparse Attention for Video Generation Acceleration via Growing Sparsity and Reduced Search Authors: Yun Dai, Yuyun Chen, Jiarui Wen, Huiping Zhuang, Cen Chen, Ziqian Zeng Published: 2026-10-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.21129v1 Diffusion Transformers (DiTs) dominate video generation but suffer from high inference cost due to the quadratic complexity of self-attention. Sparse attention mitigates this by skipping unnecessary computation in the attention matrix, but existing methods apply a fixed sparsity ratio throughout denoising and struggle to accurately determine which computations to skip. To address these limitations, we analyze attention dynamics through attention entropy and mean attention distance, and find that attention becomes increasingly concentrated across denoising steps. We further observe that blocks selected early continue to capture a large fraction of the total attention weight at later steps. These findings suggest two acceleration opportunities: the sparsity ratio should grow as denoising progresses, and earlier search results can be reused to reduce the search space. Based on these findings, we propose Growing Sparsity and Reduced Search (GSRS), a training-free framework that retains more computation early and progressively reduces it later, while restricting subsequent searches to an early candidate set to reduce search overhead. GSRS adopts Top-p selection for adaptive sparsity control, supported by a precise evaluation scheme that computes exact attention weights within the FlashAttention computation at negligible overhead. Experiments on HunyuanVideo and Wan 2.1 validate that GSRS achieves 1.55$\times$--2.21$\times$ speedup while maintaining generation quality comparable to full attention. --- ### When Judges Agree and Are Wrong: Consistency-Accuracy Dissociation as a Blind Spot for Label-Free Evaluation Authors: Xiang Zhang, Lovedeep Gondara, Jekaterina Novikova Published: 2026-10-15 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2610.21128v1 Label-free evaluation methods, such as self-consistency filtering, majority-vote aggregation, and agreement-based reliability scoring, rely on an implicit assumption that consistency can serve as a proxy for correctness when ground-truth labels are unavailable or expensive to obtain. In this paper, we test this assumption directly. Using four financial QA datasets (multiple-choice and free-form), ten consistency dimensions, and two frontier model families, we measure the joint distribution of consistency and accuracy at the level of individual examples rather than in aggregate. We find that 60% of all incorrect answers fall in the high-consistency region (consistency $\geq$ 0.8), and that 77.7% of these show complete answer collapse, i.e. identical wrong answers across all perturbation variants. This high-consistency/incorrect quadrant cannot be detected by any evaluation signal that is built on agreement alone, as the model appears maximally reliable while being wrong. We show that the phenomenon is robust to the choice of consistency threshold t (it persists from t=0.50 to t=1.00), is shared across model families, and is concentrated in specific intersections of perturbation dimension and domain. We map where this quadrant occurs, analyze its stability properties, and discuss the implications for evaluation pipelines that use agreement-based signals in place of human labels. --- ### Compression Does Not End at Selection: Post-Selection Positional Geometry for Sparse KV Caches Authors: Wanyang Hong, Zhaoning Zhang Published: 2026-10-15 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.21126v1 Sparse KV compression reduces long-context inference costs by retaining selected historical states, yet these states typically keep their coordinates from the full history. Under Rotary Position Embedding (RoPE), gaps left by evicted tokens continue to affect query-key matching, potentially limiting the use of retained evidence. We study post-selection positional geometry on a fixed selector-produced cache, examining how positional organization affects the use of retained information and which coordinate and continuation rules improve answer quality. To reorganize this geometry, we propose RoPERelay, which assigns compact, order-preserving RoPE coordinates, relocates cached key phases through inverse rotation and re-rotation, and synchronizes the current query and subsequent generation. It reuses existing K/V without renewed selection, historical re-prefill, or additional cache budget. Across 36 comparisons spanning two models, six sparse selectors, and three long-term memory tasks, RoPERelay improves answer quality in 32 cases. For Llama-3.1-8B-Instruct with BM25 on LongMemEval-S, accuracy increases from 23.6% to 35.4%. Measured complete-request time overhead is approximately 1%-3% in the evaluated configurations. These findings establish positional organization as a distinct optimization dimension for sparse KV caches after content selection. --- ### Noise-Space Reward Alignment for Few-Step Generative Models Authors: Woocheol Shin, Taeyoung Yun, Jiwon Sung, Hyeongyu Kang, Jeongmin Park, Jaewoo Lee, Kyuil Sim, Dohyun Kim, Yutong He, Jinkyoo Park Published: 2026-10-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.21125v1 Few-step generative models produce high-quality samples in one or a few evaluations. However, steering them toward desired properties remains difficult, especially when only black-box reward evaluations are available. While one could apply approaches developed for iterative diffusion and flow-based models, such as direct RL fine-tuning or test-time scaling, we find that neither transfers well to the few-step regime: direct fine-tuning suffers from severe reward over-optimization, and test-time scaling sacrifices the efficiency advantage of few-step generation. We propose Noise Policy Optimization (NPO), which explicitly targets the alignment problem for few-step generative models. The key idea is to learn an amortized flow policy over the initial noise space of the generator. The trained policy transports Gaussian noise to a reward-tilted noise distribution, whose pushforward distribution through the frozen generator is exactly the reward-tilted output distribution. By keeping the generator frozen, we can effectively utilize the knowledge encoded in the pretrained model, yielding a better reward-quality trade-off than direct fine-tuning. The amortized policy moves the search cost into training, so inference adds only a lightweight noise sampling step on top of the pretrained model. To improve sample efficiency during training, we use ELBO-based likelihood estimation that requires only sampled endpoints rather than simulated trajectories. Across image, language, and protein structure generation, NPO consistently achieves a better reward-quality trade-off than direct fine-tuning, and matches test-time search methods with 16 to 549 times lower inference cost. --- ### DST-Net: Decomposed Spatio-Temporal Network for Time Series Forecasting Authors: Yaohua Zha, Hai Wu, Shu-Tao Xia Published: 2026-10-15 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.21123v1 Series decomposition has emerged as a widely acknowledged paradigm in deep time series forecasting models. However, existing approaches predominantly employ a homogeneous modeling strategy for all subsequences, thereby overlooking the distinct inductive biases inherent in different components. We identify that the trend component exhibits dominant spatial coupling across channels but carries significant temporal redundancy, whereas the seasonal component is characterized by local temporal evolution but remains susceptible to attention distraction. To address this, we propose a novel disentangled architecture that tailors specific modeling strategies to align with the intrinsic properties of each component. For the trend branch, we design a Latent Graph Block, employing latent graph modeling to capture global topological dependencies and system-wide co-movements. Conversely, for the seasonal branch, we introduce a Gaussian Multi-scale Attention mechanism to mitigate attention distraction. By injecting learnable Gaussian priors, we impose structural constraints that compel the model to focus on multi-granular local contexts, effectively filtering out global noise and accurately capturing local evolutionary phases. Extensive experiments on multiple real-world benchmarks demonstrate the effectiveness of our proposed model. --- ### ResStreamGS: Residual-Sensitive Dual-Stream Gaussian Splatting for Mobile Volumetric Video Streaming Authors: Haoran Liu, Di Wu, Wang Luo, Hengyuan Na, Miao Hu, Guocong Quan Published: 2026-10-15 Categories: cs.GR, cs.CV arXiv: https://arxiv.org/abs/2610.21121v1 Real-time mobile volumetric video enables immersive free-viewpoint experiences, but delivering high-quality 3D content under constrained bandwidth and computation remains challenging. Recent 3D Gaussian Splatting (3DGS) systems, such as V$^3$, enable efficient mobile streaming by encoding time-varying Gaussian attributes with commodity video codecs and hardware decoding. However, existing pipelines treat all Gaussians as frame-varying signals, which is poorly suited to full-scene content where large portions remain temporally stable. Our empirical study shows that frame-wise adaptation and video coding of all Gaussians cause quality degradation in complex full-scene content, particularly in temporally stable regions. To address this issue, we propose ResStreamGS, a residual-sensitive dual-stream framework that processes Gaussians according to their temporal behavior. ResStreamGS identifies residual-sensitive primitives through lightweight probe adaptation and reuses stable Gaussians within each Group of Pictures (GOP). Stable Gaussians are transmitted once per GOP, while only residual-sensitive Gaussians remain in the frame-wise hardware-decodable video stream. Experiments on complex full-scene volumetric videos show that ResStreamGS improves post-codec PSNR by 7.51--8.35~dB over a controlled V$^3$-style all-Gaussians baseline, reduces amortized payload by up to 56.5%, and achieves 30.883~FPS on a Qualcomm Snapdragon 778G platform. --- ### Spectral-Spatial Interpretation Authors: Haotian Ma, Ruqi Yang, Philip Townsend Published: 2026-10-15 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2610.21114v1 Post-hoc image explanations usually show where a model looks using spatial heatmaps or indicate which channels matter using global channel scores. These separate views are limiting for multispectral data because channel relevance is often spatially localized and physically meaningful. We introduce Spectral-Spatial Interpretation (SSI), a full-grid attribution method over position-channel players (g,c). For each spatial position, SSI fixes the observed surrounding context, defines a conditional game over the channels at that position, and applies the Shapley value to this local game. The result is a full spectral-spatial attribution matrix rather than a single heatmap or a global channel ranking. SSI has a clear local interpretation. It satisfies Shapley fairness within each position, and aggregating its channel attributions exactly recovers the position-level contextual contrast obtained by replacing that position with the baseline. SSI also differs from context-averaged Owen-style hierarchical accounting, which uses the same position-channel grouping but averages over external spatial coalitions. On HLS Burn Scar, SSI outperforms an MC-Owen estimator across retained attribution metrics while using only about 6% of its evaluation budget. Across CUB-200, EuroSAT, and HLS Burn Scar under both per-channel mean and zero baselines, SSI achieves the best joint deletion and insertion AUC over dense, flat, and rank-1 baselines, yields the strongest spectral hit rates and channel deletion, and leads spatial localization on both annotated datasets. Code is available at https://github.com/AtheavenMa/Spectral-Spatial-Interpretation. --- ### SSR: Structural Signal Retriever for Scalable Agent Discovery in LLM-Orchestrated Multi-Agent Systems Authors: Giancarlo Maldonado Cárdenas, Carlos A. Astudillo, Nelson L. S. da Fonseca Published: 2026-10-15 Categories: cs.MA, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2610.21113v1 Large-scale multi-agent ecosystems require mechanisms for discovering suitable agents without exposing entire registries to a large language model (LLM) orchestrator. The challenge is not only to retrieve relevant Agent Cards from a growing registry, but also to maintain a compact candidate context, since each additional candidate increases prompt size, inference cost, latency, and the risk of exceeding the model context window. We formulate this problem as candidate-context scalability and propose the Structural Signal Retriever (SSR), our deterministic and training-free retrieval method designed for Agent Card discovery. SSR derives structural lexical signals from capability-bearing Agent Card fields, weights them using inverse document frequency (IDF), and uses an Inverted Signal Index (ISI) for selective candidate scoring. We evaluate SSR using a synthetic agent benchmark, a public MS MARCO adaptation, and end-to-end LLM orchestration. At 1,000 agents, SSR reduces LLM input by 98.8% and orchestration latency by 70.9% relative to full-catalog orchestration. On MS MARCO, IDF improves retrieval effectiveness within the structural representation, while the ISI preserves retrieval effectiveness and reduces explicitly scored passages by 96.8%. End-to-end experiments show that candidate pre-selection maintains a compact candidate context as registry size grows and avoids the operational failures observed with full-catalog orchestration. These results support SSR as an Agent-Card-native, traceable retrieval mechanism for candidate-context scalability. --- ### Kolab: Benchmarking Human-Agent Collaboration in Long-Horizon Workflows Authors: Shirley Anugrah Hayati, Patricia Anugrah Setiani, Ruizi Wang, Zhouyi Li, Khanh Chi Le, Young-Jun Lee, Dongyeop Kang Published: 2026-10-15 Categories: cs.AI, cs.CL, cs.HC, cs.LG arXiv: https://arxiv.org/abs/2610.21109v1 When humans collaborate with AI agents on long-horizon tasks, what happens to the agents' contributions? For solving long-horizon tasks, humans place greater importance on ongoing interaction with AI agents (e.g., revising plans) than on an agent's ability to complete the task in a single attempt. However, most agentic benchmarks have focused more on automation. Strong performance on such benchmarks does not imply effective real-world collaboration. Professional workflows offer a useful setting, as they often involve interdependent steps. To address this gap, we introduce Kolab, a new dataset of 115+ hours of screen recordings of 50 professionals from 40 occupations collaborating with agents on realistic, long-horizon problems. Kolab also contains participants' collaboration and output quality judgments. Our analysis reveals diverse collaboration patterns, highlighting the importance of when and how professionals coordinate with agents. A collaborative agent must do two things that automation benchmarks never test: anticipate whether experts will adopt, modify, or reject its contribution once it leaves the chat window to guide its next steps, and assess collaboration quality from the unfolding workflow without constant expert feedback. Our benchmark operationalizes both: (1) forecasting how professionals use agent contributions at diverse workflows, and (2) verifying their judgments of collaboration satisfaction and output quality. Findings show that frontier models, both agentic and non-agentic, overestimate collaboration with experts and struggle to distinguish between high- and low-quality collaboration. Longer workflow context does not consistently improve these predictions. As frontier agents cannot yet understand long-horizon collaboration with experts, we position Kolab as a valuable dataset for studying human-agent collaboration grounded in real professional workflows. --- ### Planning Commitment of LLM under Partial Observability Authors: Cassie Huang, Zhanwei Cao, Yeawon Lee, Nathalia Gomez, Zhuoyi Yang, Ian G. Harris, Tiffany Do, Jiayuan Mao, Li Zhang Published: 2026-10-15 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.21108v1 LLM-based planning agents commit to plans of different lengths before interacting with a partially observable environment. Some aggressively commit to a long plan based on assumptions about unobserved states, while others conservatively plan only over what they have observed. Both behaviors emerge implicitly in pre-trained models, whether the LLM outputs a plan directly or generates a PDDL formulation for a classical solver. Aggressive commitment risks costly failures, while conservative commitment risks excessive LLM calls. This choice pits safety against efficiency, a trade-off that has been neither characterized systematically nor made controllable. We investigate aggressive and conservative LLM planners and formalizers on two partially observable domains, where priors are provided as either explicit statistics or common-sense knowledge. Across three LLMs, both strategies reach similar accuracy. Conservative methods achieve fewer failed attempts (safety) at the cost of more API calls (efficiency). Aggressive methods fail more often but replan efficiently only when priors are informative. Interestingly, analysis shows that LLMs treat the provided priors nearly as facts, which risks failure when priors are unreliable. We also explore hybrid strategies with tunable hyperparameters that adjust the balance between safety and efficiency. --- ### A One-Sided McDiarmid-Type Inequality for Heavy Tails via Reverse KL Tensorization Authors: Hanuka Eshima, Amedeo Roberto Esposito, Andrea Paudice Published: 2026-10-15 Categories: math.ST, cs.IT, math.PR, stat.ML arXiv: https://arxiv.org/abs/2610.21103v1 We revisit McDiarmid's inequality, a central tool in statistical learning theory and algorithm analysis. We show that large deviations above the mean are exponentially unlikely for functions of independent random variables that are almost surely bounded above and satisfy a conditional moment assumption of order $p\in(1,2)$. When $p<2$, the result applies even when the function has infinite variance. Our proof relies on a new tensorization inequality for the Kullback--Leibler divergence, termed reverse KL tensorization, which may be of independent interest. Applications include concentration of the sample mean and median-of-means estimator, and one-sided uniform risk bounds for unbounded losses. --- ### ToolBottleneckBench: Measuring Tool-Agent Performance under Controlled Pressures and Fixed Harness Budgets Authors: Zichuan Xu, Yuyang Dong, Makoto Onizuka, Chuan Xiao Published: 2026-10-15 Categories: cs.CL, cs.AI, cs.LG, cs.SE arXiv: https://arxiv.org/abs/2610.21098v1 The success score of a tool agent reflects both its model and the budgets of the harness that runs it. We present ToolBottleneckBench, a benchmark that measures tool-agent performance under controlled pressures and fixed harness budgets. Synthetic enterprise tasks stay fixed while one pressure varies: the registered tool catalog, the visible tool menu, the certified workflow, or the encoding of returned records. An exact grader records the first unmet obligation of each failed episode and the harness limit, if any, that ended it. Across 21 model and harness configurations, the visible menu is the only one of the three pressures that act on the model with a large penalty, and this penalty tracks truncation at the completion cap. Raising the cap sixteenfold removes most of the penalty in the truncation-heavy configurations. Most failures end at a harness limit, and the failure record identifies the assigned pressure no more reliably than a count of tool calls. The repairs that help change which tools reach the model or who issues the calls, and only two repairs, neither improving model behavior, beat every configuration switch. We recommend reporting pressure effects with the harness budgets under which they were measured. We release the benchmark at https://github.com/zichuanxu/tool-bottleneck-bench. --- ### Can World and Action Modeling Benefit Each Other under Unified Causal Training? Authors: Yue Su, Bokai Lin, Xinkai Wang, Chubin Zhang, Xiangnan Wu, Kuan Zhang, Weiyang Jin, Jiwen Yu, Yiming Li, Cewu Lu, Lixin Yang, Xihui Liu Published: 2026-10-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.21095v1 World and action modeling are closely related, yet their reciprocal benefits under unified causal training remain unclear. We introduce OneWM, a simple framework for unified causal training that treats actions as both conditions for world prediction and targets for policy learning within a shared video-action architecture. Using this framework, we investigate whether learning forward dynamics conditioned on specified actions improves action learning, and whether learning to generate actions in turn improves action-conditioned world modeling. We use LIBERO, LIBERO-Plus, and RoboCasa365 as embodied testbeds to evaluate both policy learning and world modeling, complemented by real-world policy experiments. Learning the visual consequences of specified actions improves policy performance and generalization across changing scenes. In turn, action learning improves multi-view world-prediction fidelity under the same architecture. Together, these results answer both questions positively, supporting reciprocal benefits between world modeling and action generation under unified causal training. --- ### MemComposer: Learning to Assemble Memories for LLM Agents via Reinforcement Learning Authors: Yixuan Xie, Xueqiang Xu, Xinyi Fan, Xinxi Lyu, Tao Feng, Xing Fan, Chenlei Guo, Jie Hao, Shaowen Wang, Jiashuo Sun, Jiawei Han Published: 2026-10-15 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.21091v1 Agent memory enables large language model (LLM) agents to reuse past experiences without updating their parameters. However, semantic similarity alone does not guarantee memory usefulness: downstream performance depends on how memories are selected and presented to the agent. We propose MemComposer, a memory composer that jointly examines the current query and retrieved candidates to decide which experiences to include, how many to select, and how to order them. We train the composer using Experience Policy Optimization (ExPO), a GRPO-based framework that evaluates assembled memory contexts through complete agent interactions and uses task-success feedback to optimize the assembly policy. Across three $τ^2$-bench domains with two frozen executors, MemComposer outperforms the strongest baseline for each executor while reducing average memory-token usage by 16.9% and 4.9%, respectively. The learned policy also transfers to unseen domains, executors, and memory banks, and benefits from memories generated by stronger models without further training. These results demonstrate the value of learning query-specific memory assembly using downstream task feedback. --- ### RoboCloth: A Large-Scale Real Cloth Material Dataset for Neural Reflectance Reconstruction Authors: Zhen Li, Haoran Qin, Francesco Di Sario, Daniel Rebain, Andrea Tagliasacchi Published: 2026-10-15 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2610.21090v1 We present RoboCloth, a dataset of 500 real cloth materials captured under flexible, calibrated camera and lighting configurations, where both are robotically controlled during acquisition. Each material is imaged in approximately 580 high-dynamic range frames spanning a wide view-light hemisphere; camera poses are refined via structure-from-motion and aligned to the robot frame, yielding per-material sparse surface geometry and structured per-point reflectance observations ready for neural material training. We demonstrate the value of this data through a two-stage neural reconstruction pipeline: Stage 1 trains a shared MLP decoder on our corpus to learn cloth material priors; Stage 2 then freezes the decoder and fits a dense 2048x2048 latent texture to each target material. Evaluating on held-out materials from our own dataset and on the independent UBO2014 benchmark, we show that a decoder trained on our captures outperforms decoders trained on existing measured reflectance datasets and analytic PBR fitting, transferring to unseen acquisition systems without modification. The dataset, calibration files, observation tensors, and train/test splits are released under CC BY 4.0 on the Hugging Face Hub. --- ### Probe-and-Resume: When and How to Evaluate Agent Execution Authors: Jiakai Xu, Tiancheng Ge, Tujie Guan, Yusheng Li, Rohan Timmaraju, Eugene Wu, Kostis Kaffes Published: 2026-10-15 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.21088v1 Test-time search can improve agent performance by exploring alternative actions and using a critic to select promising branches. We study this approach in terminal-based computer-use environments, which expose only a partial view of a large underlying state, and find that the Monte Carlo tree search (MCTS) configuration we evaluate does not significantly improve task success. We identify two sources of poor critic performance: the agent's observations omit environment state needed for evaluation, and intermediate states offer limited evidence of whether a trajectory will succeed. At intermediate states, critics rank continuations only modestly better than chance, and environment access improves this little. We study when to invoke a critic and what access to give it to evaluate a node. Our findings motivate a policy that invokes the critic only at nodes the agent believes are final, rather than during partial progress. Further, the policy gives the critic read, write, and execute access to a fork of the computer's current and initial state, allowing it to probe and perform potentially destructive actions to surface any hidden state the trajectory omits. We call the resulting design Probe-and-Resume: when the agent claims to be done, the critic probes a fork of its state, and a rejected agent resumes where it stopped. On Terminal-Bench 2.1, this raises success by 8.4 percentage points over MCTS with conventional critics, and approaches the success rate of the Codex CLI agent with the same underlying model at less than half its cost. --- ### SIEVE: Overcoming Topological Obstruction in Equivariant Self-Supervised Learning Authors: Jongann Lee, Sun Woo Park, Yun Young Choi Published: 2026-10-15 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2610.21087v1 We identify a theoretical incompatibility between 3D point cloud masked autoencoding and SE(3)-equivariant networks. We prove that standard masking triggers a topological collapse, effectively forcing the model to hallucinate orientation without a reference frame. To resolve this, we introduce SIEVE (Scalar Invariant Extraction Via Equivariance), an SE(3)-equivariant self-supervised framework that compresses point cloud geometry into invariant scalar embeddings. At its core is the spherical projection mask, which preserves global pose while obfuscating local semantics, sidestepping the obstruction by construction. Experiments confirm that SIEVE circumvents the predicted collapse where constant and noise masks fail. On downstream point cloud tasks, the resulting embeddings improve over coordinate-based baselines and hand-crafted geometric descriptors, with the largest gains on generalization to unseen shape categories. --- ### RoPE-Flow: Monocular Vision-based Robot Pose Estimation via 2D Graph-Conditioned 3D Flow Matching Authors: Liangjing Shao, Wanhao Liu, Zhiwei Fang, Rulin Zhou, Quanlu Zhang, Changjing Liu, Beilei Cui, Yiming Huang, Hongliang Ren Published: 2026-10-15 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2610.21086v1 Camera-to-robot pose estimation from a monocular image is significant for vision-based robot navigation and control. However, recovering 3D structural features from 2D observations remains a challenging task. Existing camera-to-robot pose estimation methods either rely on time-consuming iterative rendering or involve sophisticated 2D-3D registration which suffers from projection ambiguity, accumulated errors for distal joints and imbalanced learning for different joints. In this work, we propose RoPE-Flow, an end-to-end flow matching-based framework for camera-to-robot pose estimation. From the predicted 2D heatmaps, we propose a Keypoint-centered Feature Extractor to obtain positional features along with contextual representations from keypoints-centered multi-scale patches. Moreover, we introduce Graph-guided Condition Generator, which embeds a learnable adjacency map to generate condition for flow matching based on correlation among keypoints. Besides, we introduce Bone Length Loss and Ray-Depth Loss for topological consistency and scale stability, with joint-wise weighting to mitigate varied prediction difficulty across joints. The proposed method outperforms state-of-the-art methods for pose estimation across different types of robots with mutiple cameras. Besides, we establish a novel cross-scene benchmark to demonstrate the outstanding performance of RoPE-Flow on zero-shot cross-scene robot pose estimation. Meanwhile, animated visualizations are shown on the website: ropeflow.netlify.app --- ### A Jury, Not an Electorate: Label-Free Reliability Estimation for Ensembles of Language Models Authors: Alessandro Rozza, Davide Mambelli, Steven Motta, Juri Taresch Published: 2026-10-15 Categories: cs.CL, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2610.21085v1 An ensemble of language models is a jury, not an electorate. The answers are testimony from witnesses of unknown reliability, and the question is not what the majority said but who is credible. Most ensemble methods assign each expert a fixed reputation, often learned from labels. We ask whether it can instead be inferred from the pattern of agreement and disagreement among the experts. We model the experts as a jury: each question has a latent true answer, each expert reports it with unknown reliability, and those reliabilities are estimated by Expectation Maximisation (EM) from unlabelled answer configurations alone. We show that its decision rule reduces to a log-odds weighted linear score over the experts' answer distributions. What changes is not how the jury votes, but how it learns whom to trust. On a 1560-question benchmark, the jury, with nine experts of up to 3B parameters, performs comparably to the same fusion rule with label-fitted weights, showing no statistically significant advantage from supervision. Instead, it outperforms the best single model with matched self-consistency and the strongest label-free alternative on the full benchmark. --- ### Sci$Π$vot: Benchmarking Principal-Investigator Judgment at Pivotal Moments of Scientific AutoResearch Agents Authors: Youran Sun, Xingyu Ren, Chugang Yi, Kejia Zhang, Di Wu, Yingkang Cao, Allen Zhou, Jianping Ye, Suying Liu, Jiaxuan Guo, Jianda Du, Weicheng Ye et al. Published: 2026-10-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.21082v1 Large language model (LLM) agents can keep scientific experiments running for months with little human supervision, but reliable autonomous research also requires scientific judgment. Evaluating scientific judgment is difficult because research decisions are open-ended and depend on project context. We construct Sci$Π$vot, a 248-case benchmark of scientific judgment based on human corrections. The benchmark draws on records from six months of research in which senior researchers ran LLM agents on 26 projects across six scientific fields and repeatedly intervened to correct the agents' research judgments. In each case, an agent chooses between the original LLM plan and the human-corrected alternative, using only the project record available before the correction as context. We compare LLM and human performance and examine the effects of reasoning effort, access to the project record, and reconsideration. At medium reasoning effort with the project record, models systematically prefer the original LLM plan over the human-corrected alternative. Four of five frontier models perform below chance on the selected cases. The highest accuracy in the project condition across the tested models and reasoning effort settings is 63.5%, compared with 73.4% for fresh researchers. At medium effort, every model achieves lower accuracy with the project record than without it, and reconsideration does not consistently improve overall accuracy. Even with a human-corrected alternative available, frontier models struggle with the selected research decisions, while Sci$Π$vot supports systematic evaluation of scientific judgment for LLM agents. ---