# Research Papers — 2026-10 · bundle page 21 of 156 > Full-text markdown of papers #1001–1050 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/21 [← Previous bundle](https://aipod.dev/papers/archive/2026-10/page/20.md) [Next bundle →](https://aipod.dev/papers/archive/2026-10/page/22.md) ### CoDy: Codec Dynamics as Complementary Priors for Unsupervised Temporal Action Localization Authors: Tianyu Yan, Qingyi Yang, Qin Yang, Xufei Guo, Yuan Tang, Rui Wang, Yixue Hao, Long Hu Published: 2026-10-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.19880v1 Unsupervised temporal action localization (UTAL) aims to identify action categories and localize their temporal boundaries without annotation supervision. Existing methods typically derive supervision for both tasks solely from RGB and optical-flow representations, often resulting in noisy category assignments and inaccurate temporal boundaries. In this work, we reveal an overlooked property of video codecs: group-of-pictures quantization patterns preserve category-discriminative dynamics, while motion-vector and residual variations exhibit pronounced responses around action transitions. Based on this insight, we propose CoDy, a codec dynamics-guided framework that exploits the codec as complementary information to the visual view for UTAL. CoDy integrates a codec-enhanced view with RGB and flow through confidence-aware consensus clustering, producing reliable soft pseudo-labels. It further converts codec dynamics into a class-agnostic boundary prior, which supervises visual boundary learning and guides proposal initialization and iterative refinement. The codec branches are only used during the training stage and introduce no extra codec-side computation at inference. Extensive experiments on THUMOS14 and ActivityNet v1.3 demonstrate that CoDy consistently outperforms existing UTAL methods and achieves state-of-the-art localization performance. These results establish codec signals as effective annotation-free priors for jointly inferring which actions occur and when they occur. --- ### Neural Wasserstein Splines: Representation-Invariant Second-Order Priors for Trajectory Inference Authors: Amartya Banerjee, Harlin Lee, Caroline Moosmüller Published: 2026-10-14 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2610.19878v1 Population dynamics are often observed only as unpaired snapshots, which leave the evolution between measurements underdetermined. Second-order regularization can constrain it, but a penalty on the accelerations of sampled particles is a prior on joint particle paths, and different particle representations of the same marginal curve can have different acceleration costs. We therefore introduce Neural Wasserstein Splines (NWSP), a sample-based method that learns a continuous population curve under a Wasserstein smoothness prior. A neural network maps latent variables to the control points of a cubic spline in time, so samples at any time come from the spline basis without numerical integration. We project the generator's velocity onto gradients of a finite dictionary of scalar potentials and differentiate this measure-dependent projection in time, obtaining a finite-dimensional surrogate for the intrinsic Wasserstein acceleration, trained jointly with distributional fit losses. For a fixed dictionary and ridge parameter, we prove that the population penalty depends only on the marginal curve and bound its sensitivity to moment-estimation errors. Learned potentials (NWSP-N) sharpen acceleration estimates. On various synthetic and single-cell benchmarks, NWSP is highly competitive with transport and flow-based methods, ranking in the top two in 11 of 16 settings. The penalty improves on an unregularized spline in 13 of 16 settings and, while competitive with a particle-acceleration penalty, adds provable representation invariance. --- ### SPARS: A Stability-Plasticity-Aware Region Selection Framework for Continual Learning Authors: Teif Aldaajani, Huda Hakami, Maha A. Thafar Published: 2026-10-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.19876v1 Continual learning aims to acquire new knowledge while retaining previously learned knowledge. However, updating shared parameters when learning new tasks often overwrites existing knowledge, causing catastrophic forgetting. Memory replay methods mitigate catastrophic forgetting but rely on previous samples, raising privacy, memory, and scalability concerns. On the other hand, parameter isolation-based methods preserve learned knowledge but may limit knowledge transfer, whereas regularization promotes adaptability but remains susceptible to interference between old and new tasks. To maintain the stability-plasticity trade-off, this paper proposes Stability-Plasticity-Aware Region Selection (SPARS), a replay-free hybrid framework combining global parameter isolation with localized parameter regularization. SPARS estimates parameter importance using either the Fisher Information Matrix (FIM) or a novel Confidence Score (CS) estimator that leverages logit sensitivity and achieves comparable performance to FIM without requiring labelled data. Based on parameter importance, SPARS partitions parameters into three importance-aware regions namely, winning, neighboring, and non-important parameter regions. Each region receives a different adaptation strategy: selective freezing, soft regularization, or unrestricted learning based on its role in the stability-plasticity trade-off. To mitigate classifier bias in class-incremental learning, we employ Quadratic Discriminant Analysis to improve performance on previously learned classes .Experiments on CIFAR-10 and TinyImageNet demonstrate consistent improvement in average incremental accuracy over existing isolation- and regularization-based methods across task- and class-incremental learning. On TinyImageNet, SPARS achieves the best performance with 6% improvement for class-incremental learning while retaining over 60% of parameters for future tasks. --- ### RCCM: Diagnosing Gains and Harms in Reasoning-Prompt Transfer Authors: Yuqi Zhang, Di Zhang Published: 2026-10-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.19872v1 A reasoning prompt can improve one deployment and degrade another. RCCM (Reasoning-Control Capability Mismatch) examines these reversals by pairing answers to the same questions with records of how generation ends. Across five open-weight deployments and nine strategies, aggregate accuracy hides substantial question-level gains and harms; a common-budget MATH500 evaluation examines transfer on a separate sample. On 60 additional questions, concise reasoning improves Phi's automatic answer matching at a 2,048-token cap across three collections, but sharply reduces Qwen's. Author-reviewed final-answer commitments give a smaller, statistically unresolved Phi gain. Reserving an answer stage also improves matching, with additional input and call costs. These results show why a prompt benefit must be interpreted alongside its execution and evaluation: matching a reference answer need not mean delivering it, and an apparent compression benefit may admit another explanation. RCCM records this evidence for reproducible transfer comparisons. --- ### Rationale Distribution Distillation via Flow Matching for Distributional Continuous Latent Reasoning Authors: Mingyeong Kim, Gyusang Cho, Juho Lee, Giung Nam Published: 2026-10-14 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2610.19871v1 Sampling multiple chain-of-thought rationales from a language model can uncover correct solutions missed by a single attempt. However, these rationales are typically lengthy, making repeated autoregressive generation costly. Continuous latent reasoning offers a compact alternative, but point-valued methods condition repeated answer sampling on a single rationale, which can limit exploration of diverse paths and answer coverage. We thus propose rationale distribution distillation (RDD), training a conditional flow over fixed-length latent sequences by distilling from multiple textual reasoning paths. Furthermore, we expand the distillation targets through within-query mixup, interpolating between complete latent rationales for the same query. The flow nonautoregressively generates the entire latent sequence, and a frozen language model autoregressively decodes answers from sampled rationale contexts. Empirically, the resulting distributional reasoner achieves higher answer coverage than the evaluated point-valued latent reasoning baselines, particularly on advanced mathematical tasks. --- ### SEA-HELM Audio: Evaluating Multilingual ASR-LLM Pipeline Performance Across SEA-HELM Subsets Authors: Yixian Tan, Aulia Adila, Jonathan Heng, Kunat Pipatanakul, Donghang Wu, Anocha Sutaveephamochanon Published: 2026-10-14 Categories: cs.SD, cs.CL arXiv: https://arxiv.org/abs/2610.19869v1 We introduce SEA-HELM Audio, a Southeast Asian (SEA) multilingual evaluation framework that extends the text-based SEA-HELM benchmark to assess performance degradation in cascaded automatic speech recognition and large language model (ASR-LLM) pipelines. Using synthesized speech, we compare speech-input and text-input performance across five languages (Chinese, English, Malay, Indonesian, and Tamil) on multiple-choice reasoning and instruction-following tasks. We evaluate open-weight and commercial ASR-LLM systems using identical verifiers and quantify the speech gap as the difference between text and speech accuracy. Results show substantial degradation, with accuracy drops of 9.00 to 18.50 percentage points for multiple-choice reasoning and 20.00 to 42.86 points for instruction following. Tamil exhibits the largest degradation, exceeding 40 percentage points. Our findings highlight the limitations of text-only benchmarks in predicting voice-agent reliability and demonstrate the value of SEA-HELM Audio for evaluating multilingual voice-agent systems. --- ### Explorer-Zero: Improving Self-Play for Long-Horizon Tasks with Decomposable Verifiable Rewards Authors: Tianyu Liu, Davide Belli, Bence Major, Arash Behboodi, Tribhuvanesh Orekondy Published: 2026-10-14 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.19868v1 Training LLM agents on long-horizon interactive tasks with reinforcement learning typically relies on human-annotated tasks and reliable verification, both expensive to construct for stateful environments. Self-play offers an alternative, but must generate achievable, compositional tasks and provide feedback beyond binary outcomes. We propose Explorer-Zero, a self-play framework that jointly generates tasks and fine-grained, verifiable rewards through environment interaction. A learned proposer explores the environment, constructs tasks, and records intermediate and final states as verification targets. These checkpoints reward partial completion, while alternating proposer--solver training adapts the generated curriculum. We show theoretically that subtask rewards reduce collapse among unsuccessful rollouts when they complete different numbers of subtasks. Without human-annotated training tasks, Explorer-Zero outperforms the evaluated self-play baselines across ALFWorld, ScienceWorld, and AppWorld; on AppWorld, our 30B agent reaches 59.67% task success, approaching 62.65% for RL on human-annotated tasks. Further analyses support task-relevant composition and benefits on complex tasks, while self-play initialization improves subsequent human-data RL across all three benchmarks. --- ### Euler: Towards Human-Centered Multi-Agent Mathematical Discovery Authors: Qiuyu Chen, Qi Wang, Liang Xu, Xin Jin, Baao Xie, Wenjun Zeng Published: 2026-10-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.19864v1 Mathematical research drives scientific discovery, and recent advances in AI for mathematics have shown that language-model agents can solve challenging problems and develop substantial mathematical proofs. Yet much of today's AI-for-mathematics work centers on obtaining a final answer. This emphasis leaves the exploration behind a result difficult for researchers to understand, while long-running investigations face fragmented context and the risk of unsupported claims propagating across reasoning steps. We present Euler, a human-centered mathematical research system built around a shared, structured representation of the research process. Euler organizes mathematical statements, assumptions, proof dependencies, alternative approaches, failed attempts, and verification evidence into connected research graphs. This representation allows researchers to trace how results are developed and supplies agents with persistent, task-relevant knowledge for planning, collaboration, and verification across sessions. Researchers can also select a graph node linked to a saved team state, revisit the agents' earlier reasoning, and explore alternative directions through continued interaction. We illustrate Euler's capabilities through three mathematical research case studies and describe the implemented system and its software validation. --- ### On the Optimisation Landscape of Overparameterised Weighted MMD Authors: Tharrshann Jayan Logarajah, Jeremias Knoblauch, Louis Sharrock Published: 2026-10-14 Categories: stat.ML, cs.LG, math.OC arXiv: https://arxiv.org/abs/2610.19861v1 We study the optimisation landscape of the maximum mean discrepancy (MMD) over weighted atomic measures. For the one-dimensional Gaussian kernel, we show that, for any compactly supported target distribution, sufficiently many particles ensure that every local minimum has arbitrarily small MMD. Moreover, any stationary point whose MMD remains bounded away from zero is unstable under an unweighted gradient flow over the particle locations. These results hold both when the weights are constrained to the simplex, and when they are unconstrained but optimised at each step. When the target is itself finitely supported, we further strengthen this result: beyond an explicit particle threshold, there are no spurious local minima, and every spurious stationary point is unstable. To our knowledge, these are the first finite-particle overparameterisation guarantees of their kind for weighted MMD optimisation. --- ### Text-Informed Training Data Filtering for Enhanced Virtual Flow Meter Performance Authors: Kristoffer Hjelmen Nesland, Bjarne Grimstad, Antorweep Chakravorty, Dan Sui Published: 2026-10-14 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2610.19860v1 In sectors such as energy, aquaculture and chemical processing, the effectiveness of both mechanistic and data-driven models is frequently limited by poor-quality training data, which obscures underlying physical laws and degrades predictive accuracy. Such quality issues commonly manifest as anomalies in the dataset, ranging from sensor faults to process upsets and incorrect operator inputs. While traditional rule-based filtering can remove a subset of the anomalies, it is unable to leverage contextual information stored as unstructured text, such as engineer comments and operational logs that explain under what conditions the data was collected. We propose a text-informed data filtering method that leverages large language models (LLMs) to integrate unstructured operational data with tabular sensor data. The method consists of two steps: (1) contextual anomaly detection by reasoning over both data modalities, and (2) generation of a binary mask that is applied to filter the training dataset for model development. To investigate the potential benefit, a steady-state soft-sensor regression model, namely a virtual flow meter that estimates well flow rates, is used as the downstream evaluation target. Experiments on a synthetic oil and gas dataset show improved model performance compared to traditional rule-based filtering. Ablation studies show that textual operator comments can provide filtering-relevant signals beyond sensor data alone, with the multimodal approach reducing downstream MAPE from 7.1% to 5.4% relative to sensor-only filtering. This work demonstrates that integrating unstructured operational knowledge with sensor data through LLMs can improve data quality for industrial machine learning applications, offering a scalable alternative to manual data curation. --- ### OmniPoser: Flexible Human Motion Recovery in the Wild with Masked Flow Matching Authors: Minghao Liu, Tutian Tang Published: 2026-10-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.19857v1 Recovering 3D human motion from sparse wearable sensors is challenging due to the inherent noise, occlusion, and instability of real-world tracking signals. Existing approaches are restricted to fixed sensor configurations and, when built on diffusion models, are computationally prohibitive for real-time deployment. We propose OmniPoser, a universal framework that recovers full-body SMPL motion from a flexible combination of heterogeneous inputs, such as 3D keypoints, sparse IMU rotations, head-mounted 6-DoF poses, or any subset thereof, within a single model. OmniPoser introduces a cross-modal masking mechanism paired with a Masked Conditioning Encoder, enabling one architecture to incorporate diverse sensor configurations through a masked design. A decoupled dual-stream generative backbone generates complete motion via Conditional Flow Matching, requiring only a single ODE integration step at inference. Across three settings and seven benchmarks, including in-the-wild Nymeria and Ego-Exo4D datasets, OmniPoser performs on par with state-of-the-art methods while running at over 700 FPS. The project page is available at https://jamesbridgewater51.github.io/omniposer-eccv/. --- ### Lost in the Fallback: How Reliably Do Typed Decision Models Use Fallback Options? Authors: Yuanbo Xie, Mingli Zhu, Tianyun Liu, Yingjie Zhang, Haixiao Xiong, Tingwen Liu Published: 2026-10-14 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2610.19856v1 Typed decision models (TDMs) are increasingly used in applications such as request routing and model selection, making reliable decisions critical to system performance. Fallback options accommodate categories outside regular choices, enabling deferral to human experts or more capable models. While recent works have examined adversarial vulnerabilities in TDMs, their ability to follow fallback rules in non-adversarial settings remains underexplored. We introduce the Paired Fallback Robustness (PFR) Test to evaluate two aspects of fallback reliability: whether models correctly switch between regular and fallback options, and whether they make consistent decisions under logically equivalent definitions of the same rule. We evaluate open-source decision models on three benchmarks, with controlled comparisons across architectures and parameter counts. We find that correct recognition does not reliably transfer to correct fallback options, and errors persist even when the correct category is explicitly supplied.Moreover, logically equivalent formulations of the same fallback rule can also produce substantial disagreement in model decisions. These findings reveal a crucial reliability gap in current TDMs: fallback mechanisms designed to improve reliability can instead introduce errors. It highlights faithful execution of fallback rules and consistency under equivalent definitions as essential requirements for reliable typed decision-making. --- ### Energy Consumption Analysis of Discrete Diffusion and Autoregressive Language Models Authors: Boris Ruf, Marcin Detyniecki Published: 2026-10-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.19855v1 As Large Language Models (LLMs) continue to scale, their energy consumption during inference has become a critical concern. While Autoregressive (AR) models are the industry standard, Diffusion Language Models (DLLMs) have emerged as a promising alternative capable of parallel token generation. In this paper, we perform a comparative energy benchmark of diffusion models (LLaDA-8B, Dream-7B) against AR counterparts (Llama-3.1-8B, Qwen-2.5-7B). We analyze the trade-offs between model architecture, KV-cache optimization, and Joules-per-token efficiency. Our results show that at longer sequences (200--600 tokens), diffusion models achieve 2.5--2.7 J/token, approximately 2$\times$ more efficient than AR models with KV-cache (5.3--5.7 J/token). KV-cache provides substantial benefits for AR models at longer sequences (50--70\% energy reduction). --- ### DeltaStreamer: Towards Human-Like Agentic Streaming Video Understanding Authors: Boyuan Sun, Deshui Miao, Wenzhao Gao, Shaoyong Jia, Shaohui Jiao, Chi Liu, Yan Shu, Derek Li, Bryan Dai, Shengsheng Qian, Qibin Hou Published: 2026-10-14 Categories: cs.CV, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2610.19849v1 We propose DeltaStreamer, a novel agentic framework for streaming video understanding inspired by how humans observe, remember, and investigate. Streaming video understanding requires a system to retain evidence before knowing which details future queries will need. Existing approaches often obscure event transitions and omit relevant details when compressing video history, and cannot recover missing visual evidence. DeltaStreamer addresses these limitations by combining change-aware memory with query-driven planning and targeted evidence gathering with replay. Before a query arrives, it continuously observes the stream and explicitly records visual changes in structured memory, preserving how events unfold rather than only what is present. When a query arrives, a query-driven planner identifies the required evidence and guides memory retrieval and targeted replay. By revisiting historical frames, the agent can recover visual details omitted during observation and ground its answer in evidence beyond the retained descriptions. This connects continuous observation with active investigation tailored to each question. Experiments on OVO-Bench and StreamingBench demonstrate improvements over representative streaming video understanding methods, with overall scores of 66.07% and 59.53%, respectively. Project page: https://bbbbchan.github.io/DeltaStreamer/ --- ### OpenTWBench (Open Taiwan Benchmark): Taiwan-Domain Knowledge Evaluation for Large Language Models, and How the Measurement Apparatus Shapes the Score Authors: Liang-Hsun Huang, Min-Yi Chen, Chao-Chun Chuang, Yu-Wei Liu, Che-Yu Wu, Po-Feng Lee Published: 2026-10-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.19848v1 We present OpenTWBench, an open evaluation suite for Taiwan-domain knowledge in large language models, built around two benchmarks. tw-exam-bench contains 255,854 four-option questions across 148 academic subjects, from fifteen years of Taiwan's national examinations published as open data by the Ministry of Examination; answer keys agree across 31,312 duplicated question groups at 99.91%, with all 27 disagreements accounted for. A reviewed second pass withdrew 2,180 items whose stems depend on a figure the text does not carry; all scores use the remaining 253,674. tw-formosa-bench contains 1,696 difficulty-curated questions about everyday and contemporary Taiwan - the Taiwan that licensing examinations never ask about - generated from a community-curated corpus under a discipline in which no model writes a ground truth, and curated against a frozen seven-model pool so that the pool scored at the passing margin (46.9-74.6%, median ~54%); a leave-one-out experiment shows the selection preserves model ranking (near-zero bias). Within six weeks the frontier had cleared that band: of 108 models now on the public board, 22 score above its ceiling, the best 91.6%. We also document how much of a score comes from the apparatus rather than the model. On identical questions, switching answer extraction from pattern matching to an explicit \boxed{} answer moves accuracy from 20.8% to 93.9%; a single placeholder character in a system prompt moved one model from last (58.2%) to first (83.9%) on the same benchmark; doubling the thinking budget from 8k to 16k tokens bought 0.2% while shuffling which questions failed; and a three-judge validation panel proved to be one judge in disguise, two members approving 92-99% of everything shown. We release all datasets, per-item difficulty data, curation manifests and a leaderboard at https://opentwbench.ai --- ### VisibilitySplat: Ray-Traced Occlusion for Relighting with 3D Gaussian Splatting Authors: Sven Kluge, Oliver Staadt Published: 2026-10-14 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2610.19847v1 We address inverse rendering with 3D Gaussian Splatting (3DGS) by introducing explicit visibility modeling for relighting as well as material and light decomposition. Our approach augments the standard rasterized 3DGS pipeline with a sparse visibility oracle that estimates transmittance-weighted occlusion for Gaussian primitives from sampled lighting directions. This oracle is implemented using a point-based ray tracer accelerated by a bounding volume hierarchy (BVH) and queried sparsely within the inverse-rendering objectives, while the original 3DGS loop is retained for training efficiency, interactive visualization, and tooling compatibility. Shading follows a physically based rendering (PBR) formulation with a principled microfacet bidirectional reflectance distribution function (BRDF) and low-resolution high-dynamic-range (HDR) environment maps. We evaluate our method on the TensoIR synthetic dataset against baselines based on neural radiance fields (NeRFs), tensor representations, and 3DGS. The results show competitive performance and improvements over several earlier baselines for novel-view synthesis (NVS), albedo reconstruction, and relighting. Ablations indicate that explicit visibility modeling is an important contributor to relighting and material-illumination disentanglement, while pure PBR supervision can favor appearance fitting in NVS. Overall, the findings suggest that sparse, point-based visibility queries effectively complement rasterized splatting for inverse rendering while preserving the practical advantages of the 3DGS ecosystem. --- ### Memory-Efficient Subspace Optimization with Residual Correction: From Momentum SGD to Muon Authors: Sifan Yang, Hongyi Tao, Dingzhi Yu, Haomin Bai, Wei Jiang, Silin Gao, Pi Bu, Lijun Zhang Published: 2026-10-14 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.19844v1 Memory-efficient subspace optimization has emerged as a practical approach to reducing the memory cost of LLM training while preserving optimization performance. Previous algorithms typically rely on the leading singular subspace of stochastic gradients, yet the gradient noise may dominate the subspace in later training stages and can prevent convergence. To overcome this limitation, we adopt a residual correction framework, which maintains the optimizer states in the subspace and adds the orthogonal residual gradient to the parameter update. We first integrate this scheme into momentum SGD to develop SMRC, which attains an $O(T^{-1/4})$ convergence rate for a fixed orthonormal basis, matching that of full-space momentum SGD. Our analysis introduces a subspace virtual iterate to resolve the coupling between the momentum and the residual correction. Furthermore, we extend SMRC to a multi-stage variant which periodically recomputes bases to track the evolving dominant subspace and retains the same rate. Since each basis refresh breaks the consistency of the virtual iterates, we devise a boundary correction approach that aligns them across stages. Beyond momentum SGD, we incorporate our framework into Muon and propose PMRC, which applies the matrix sign to the projected momentum. Through a weighted momentum tracking analysis that accounts for the residual gradient, we establish an $O(T^{-1/4})$ convergence rate for PMRC, which matches the rate of full-space Muon. We also design a multi-stage PMRC with periodically refreshed bases, which maintains a convergence rate of the same order. Extensive experimental results confirm the effectiveness and efficiency of our algorithms. --- ### LAGO: Language Agents with Reusable Growing Options Authors: Yuran Wu, Mengkang Hu, Qionglin Qiu, Fanqing Meng, Qiguang Chen, Yuhang Zhou, Qiudan Zhang, Xu Wang Published: 2026-10-14 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2610.19843v1 Long-horizon tasks expose a weakness of monolithic tool-use loops: one agent must decompose, execute, and verify a task within a single trajectory. We introduce LAGO, which treats specialized language agents as reusable temporally extended options. A meta-agent retrieves options from a persistent library or spawns new ones, dispatches sub-tasks, verifies results, and admits successful novel options. The library grows across tasks without updating model weights. On 500 SWE-bench Verified tasks, frozen Qwen3.5-35B-A3B in both roles resolves 58.6% under single-attempt evaluation with the official Docker evaluator. On a fixed 150-task subset, we re-run mini-SWE-agent, Terminus 2, and LAGO with the same policy, temperature, task IDs, and evaluator; their resolve rates are 49.3%, 57.3%, and 60.3%, respectively. Cross-model experiments provide evidence consistent with a role for decomposition quality. A 50-task component ablation finds four fewer resolved tasks without decomposition, two fewer with shuffled reused content, and six fewer without the library. These results support reusable agent-options as a practical abstraction for task streams, while leaving component-level causality task- and model-dependent. --- ### EGCForest: Structured Agent Memory Organization for Enterprise Group Chats Authors: Lingxi Cui, Jinhao Ruan, Wenqing Wei, Guo Yi, Li Rao, Ke Chen, Lidan Shou Published: 2026-10-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.19836v1 Enterprise group chats record project progress, decisions, task ownership, and other organizational information valuable to enterprise agents. Reliable retrieval is challenging because evidence spans interleaved threads, channels, and time, with meaning and authority conditioned on the speaker. Neither RAG's independent chunk retrieval nor memory systems' summary-based consolidation can reliably recover such distributed evidence. We present EGCForest, a novel multi-view hierarchical memory framework for enterprise group chats. EGCForest organizes an immutable message log into three complementary forests: a Channel forest for temporal workflows, an Actor forest for speaker-conditioned context, and an Artifact forest for deliverable lifecycles. Cross-view connections are enabled by a Placement Map and sparse structural bridges. Built on this memory backbone, EGCForest retrieves and assembles evidence by jointly leveraging message-level relevance, hierarchical context from forest summaries, and cross-view links, recovering distributed evidence. Experiments on three enterprise-chat benchmarks show that EGCForest consistently outperforms RAG and memory-system baselines, improving answer accuracy by up to 20.85 points over MemOS while supporting efficient online retrieval. --- ### Teaching Agents in their Own Style: Blackbox Teacher Distillation for Web Agents Authors: Md Farhan Ishmam, Kenneth Marino Published: 2026-10-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.19834v1 Frontier web agents using closed models have high inference and computational costs. Smaller open models can be an alternative, but to be performant, they require training supervision from a human or teacher model. Token-level teacher distillation is not an option for closed teachers as it needs access to the model's logits. The standard approach is to imitate teacher demonstrations offline, but it trains the student on states it has never visited, and in a style it does not write in. We introduce WebKD, where the teacher is the editor of the student's failures. Given a failed episode, the teacher finds the first point of mistake, and rewrites the student's reasoning traces, harness states, and actions from that point onward. The editing reveals that the teacher's corrections can be more surprising to the student than the student's own text. WebKD instead aims to edit minimally. In the data space, the teacher writes each correction in the student's style. In the objective space, the reasoning is weighted by its contribution to the action. A role-asymmetric KL anchor allows the corrected action to move freely while keeping the reasoning near the student's prior. On the TimeWarp benchmark, WebKD students gain about 5.5-10.7 pp over behavior cloning, outcome-reward RL, and teacher editing baselines. The performance transfers to unseen versions and to the live web in the OnlineMind2Web benchmark. WebKD opens a new way of distilling black-box models to improve the capabilities of open-weight web agents. --- ### Rent-Seeking Language Models: Reward Models Set the Prices, Frequent Audits Curb the Rent Authors: Zixiao Wang, Xingbo Du, Duzhen Zhang, Le Song Published: 2026-10-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.19832v1 Reward model overoptimization in RLHF is usually described as reward hacking. We recast it as rent-seeking: the policy, a firm, earns reward from a regulator, the proxy reward model, that true quality does not back. The lens turns overoptimization into measurable quantities, namely rent, a capture index and deadweight loss, and into testable predictions from the economics of regulation. In a fixed, version-controlled testbed with three model families, accuracy-matched proxy reward models and two gold reward models, RL turns 41% to 66% of its proxy gain into rent while gold reward plateaus. Rent follows each regulator's prices. Neither proxy verifies facts, but one pays for confident specifics and the other for displays of diligence, so RL policies learn to fabricate details about nonexistent entities (97% to 100% of probes) or to deflect factual questions (67% to 98%). Kinship between policy and regulator adds a fixed premium of about 0.1 standard deviations but gives the policy no extra leverage under optimization. At a fixed expected fine, frequent mild audits beat rare severe ones, and random audits are as efficient per audit as targeted ones. Bringing the bunching estimator of tax economics to RL training, we also find a first sign that policies learn to stay just below a targeted audit's threshold. --- ### CTIA-ODE: Continuous-Time Inter-Variable Attention for Long-Term Time Series Forecasting Authors: Chengyi Pan, Huangqimei Zheng, Hao Xue Published: 2026-10-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.19831v1 Although multivariate time series forecasting has broad application prospects, effectively incorporating exogenous variables remains challenging. Prevailing discrete-time architectures often impose rigid temporal alignment across heterogeneous variables, which may limit their ability to capture continuously evolving external effects. To address this limitation, we introduce CTIA-ODE, a continuous-time forecasting framework centered on Continuous-Time Inter-Variable Attention (CTIA). Specifically, CTIA is embedded within an ordinary differential equation (ODE) solver, enabling the continuously evolving endogenous trajectory to dynamically query a static exogenous context along the integration path without requiring explicit temporal alignment. To improve the stability of the continuous latent dynamics, we further introduce a dual-stabilization strategy: architecturally, a Linear Residual Augmentation (LRA) module provides a macroscopic trend anchor, while an Outlier-Robust Hybrid Loss (ORHL) mitigates the influence of heavy-tailed anomalies during optimization. Extensive experiments across eight real-world datasets demonstrate that CTIA-ODE achieves state-of-the-art forecasting performance across diverse datasets and prediction horizons, while maintaining a favorable accuracy-efficiency trade-off with a compact memory footprint and low inference latency, particularly under long-horizon forecasting settings. Anonymous code is available at https://anonymous.4open.science/r/CTIA-ODE-15A6/. --- ### DarKnight: Retrieval-Guided Agentic Framework for Breaking Dark Web CAPTCHA Gates Authors: Binghui Wu, Yeo Zi Yi, Darren Tan, Manit Baser, Levente Csikor, Dinil Mon Divakaran Published: 2026-10-14 Categories: cs.CR, cs.CV arXiv: https://arxiv.org/abs/2610.19830v1 Cyber Threat Intelligence (CTI) investigators who monitor dark web marketplaces for leaked credentials and breach listings must pass the diverse CAPTCHAs that operators deploy to block automated collection. Existing solvers either need unscalable per-site fine-tuning or rely on commercial Vision-Language Model (VLM) APIs, which surrender operational sovereignty: provider policies, Tor-exit blocking, government regulation, or model updates outside the investigator's control can halt or alter the solver overnight, and per-call costs recur with every session and retry. We present DarKnight, a self-improving agentic framework designed to run on a single workstation GPU inside an investigator's Tor crawler and solve CAPTCHAs with small, locally hosted open-weight VLMs that no provider decision can withdraw, without per-market training or third-party services. For each CAPTCHA, DarKnight retrieves successful and failed past attempts on similar images (dual-signal RAG), composes an image-specific preprocessing pipeline, and learns from the site's pass/fail verdict. In a case study on four real-world dark web marketplaces, agentic tool selection outperformed parameter scaling. A deployable open-weight VLM with DarKnight reached 83.2\% on the most heavily defended market, 37.2 percentage points above its base model, outperforming even the frontier Claude Opus~5 (44%). DarKnight recovered 48.2% of baseline failures at a 7.6% degeneration cost, indicating that selective tool use can avoid much of the degradation caused by uniform preprocessing. --- ### MAPLE: A Multi-Axis Parametric Knowledge Extraction Lens for LLM Evaluation Authors: Minsuh Joo, Youna Kim, Choonghyun Park, Soo Kyung Kim, Hyunsoo Cho Published: 2026-10-14 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2610.19827v1 LLMs absorb vast knowledge from training data, yet their inherently probabilistic nature offers no guarantee that this knowledge will surface in their outputs. To bridge this gap, Knowledge Extraction Enhancement (KEE) techniques such as activation steering, decoding adjustments, and prompting modify inference, potentially reinforcing existing predictions or surfacing less accessible answers. Yet their evaluations centered on aggregate accuracy, which obscures diverse effects by collapsing recovered failures and disrupted successes into a single score. We introduce MAPLE, a unified framework for characterizing how KEE techniques affect parametric knowledge extraction. Its diagnostic metrics disentangle these effects at the surface, probability, and beyond-sampling levels by measuring answer recovery and disruption, gold-token rank shifts on unrecovered failures, and recovery of answers missed by fixed-budget sampling. We evaluate six KEE techniques spanning decoding, activation steering, and prompting across three model families: OLMo2, Qwen2.5, and Llama3. Our analysis reveals distinct effects and trade-offs across techniques, highlighting the value of MAPLE for understanding and comparing KEE beyond aggregate accuracy. --- ### What Matters for World Modeling in Vision-Language-Action Models? Authors: Qisen Ma, Yixiang Chen, Yuan Xu, Peiyan Li, Jiabing Yang, Kai Wang, Jianhua Yang, Jianlou Si, Jun Huang, Jing Liu, Nianfeng Liu, Yan Huang et al. Published: 2026-10-14 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2610.19825v1 Integrating world models into Vision-Language-Action models (VLAs) has emerged as a promising direction, enabling policies to anticipate future dynamics beyond reactive observation-to-action mapping. However, existing approaches vary simultaneously in their world representations, integration paradigms, and policy backbones, making it difficult to determine what truly matters for effective world model integration. To disentangle these factors, we categorize existing efforts into four representative paradigms, namely Implicit Future Alignment, Explicit Future Query, MoT Future Expert, and External World Predictor. We instantiate each within a unified framework and systematically evaluate these paradigms with diverse world representations and policy backbones across in-domain, out-of-domain, long-horizon, dynamic, few-shot, and real-world settings. Our study yields four main findings: 1) world representation effectiveness is paradigm-dependent, whereas 2D semantic representations offer robust, cross-paradigm gains; 2) no single paradigm is universally optimal, yet the decoupled MoT Future Expert offers competitive overall performance, particularly in OOD robustness; 3) world modeling consistently benefits policies built on standard VLMs, while decoupled designs exhibit greater compatibility with pretrained VLAs; and 4) world modeling improves performance over action-only baselines across multiple settings, with notable gains on long-horizon and dynamic tasks. Project page and video demonstrations are available at https://dylanmqs.github.io/WM-in-VLAs/. --- ### PhyMetric: Diagnosing Physical Plausibility in Text-to-Video Generation via Scene-Level QA Authors: Siwei Meng, Xuerou Cai, Rui Hu, Ping Liu Published: 2026-10-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.19823v1 Text-to-video (T2V) generation models can produce visually realistic videos that nevertheless violate the physical consequences implied by the prompt and scene. Existing benchmarks largely rely on holistic plausibility scores or broad quality dimensions, leaving it unclear which physical behavior is being tested and why a model fails. We introduce PhyMetric, a scene-level diagnostic benchmark that recasts physical plausibility evaluation as verifiable, scene-grounded question answering. PhyMetric contains 1{,}115 scenes spanning 50 physical categories across six domains, paired with 8{,}920 answer-balanced binary questions over 12 evaluation dimensions. Each scene is associated with eight targeted yes/no questions and a structured physical prior specifying the governing law, expected temporal sequence, observable signatures, and common failure modes. At evaluation time, a vision-language model (VLM) judge answers each question from question-aware sampled frames conditioned on the prior, and correctness is hierarchically aggregated into scene, dimension, physical category, and model scores. Experiments on four open-source T2V models and three VLM judges show that scene-specific binary QA is a critical component of the protocol: when each targeted question is replaced by a single generic plausibility query, evaluator accuracy drops to the chance level. Structured physical priors offer a complementary signal that improves human alignment of the resulting scores, with effects that vary across VLM judges of different capacity. These findings establish PhyMetric as a benchmark that turns physical plausibility evaluation from opaque holistic scoring into interpretable, scene-level inspection. Our project page is available at: https://mengsiwei.github.io/PhyMetric/. --- ### JointServe: Serving Multi-Model Agents on Memory-Constrained GPUs Authors: Daijin Hu Published: 2026-10-14 Categories: cs.DC, cs.LG arXiv: https://arxiv.org/abs/2610.19822v1 LLM agents are evolving from a single model calling tools to planners that orchestrate multiple expert models whose capabilities live in distinct weights. This shift breaks a hidden assumption of today's serving systems: that the working set of models fits in GPU memory. On the memory-constrained GPUs typical of private and edge deployments, naive whole-model swapping serializes weight transfer with computation and, without host-backed KV restoration, discards session state at a switch. We present JointServe, a serving system that treats weight shards and KV blocks as residency objects competing for one unified memory budget. JointServe exploits three structural properties of agent workloads (directed calls, gapped execution, and dual-state residency) to prepare models before they are called: an intent signal parsed from the caller's own output stream triggers prefetch during generation, partial k* residency reduces switching to incremental layers, and a preemptive transfer scheduler protects live-session KV with a guaranteed bandwidth share. A carve-out control step adjusts the weight/KV allocation as workload demands change. Evaluations show that JointServe reduces session completion time by 21.7% over the strongest whole-model swap baseline and stays usable in a crash regime where every whole-model swap baseline fails to finish (a 46-fold gap). On replayed SWE-bench, tau-bench, and OSWorld traces, it cuts session completion time by up to 49% and lifts SLO attainment from 2.8-24.5% to 76.8-100%. --- ### ActionOPD: Distilling Decisions, Not Tokens Authors: Huining Yuan, Xiangmin Yi, Zelai Xu, Zixu Wang, Xinlei Chen, Xiao-Ping Zhang, Yu Wang, Chao Yu Published: 2026-10-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.19820v1 Distilling capable language-model agents into smaller models requires aligning the student's behavior with the teacher's. This raises a fundamental question: at which states and at what granularity should this alignment be performed? Offline imitation provides dense but token-specific supervision and can suffer from state-distribution mismatch. Token-level on-policy distillation (OPD) addresses this mismatch but typically requires teacher token probabilities and compatible tokenization. We argue that semantic actions provide a natural unit of supervision for agent distillation. We introduce ActionOPD, an action-level on-policy distillation method motivated by maximizing expected teacher-action likelihood at student-encountered states. At each such state, ActionOPD samples actions from both the student and a black-box teacher, rewarding student actions according to their semantic agreement with the sampled teacher actions. Through policy optimization, ActionOPD aligns the student's action-level behavior with the teacher's decisions without requiring reproduction of teacher-written reasoning or access to teacher token probabilities. Training Qwen3-4B and Qwen3-8B with two teachers on diverse, curated tool-use tasks yields average gains of 3.3-6.9 percentage points across four out-of-distribution benchmarks. ActionOPD scales favorably with student size and teacher capability, without requiring the teacher and student to share a model family or tokenizer. On $τ^2$-bench, ActionOPD achieves competitive performance against offline distillation and token-level OPD. We further explore Self-ActionOPD with a same-model teacher and privileged context. These results establish ActionOPD as a promising approach to agent distillation. --- ### One Monitor Does Not Fit All: Formalism-Agnostic Runtime Verification for Agentic AI Authors: Angelo Ferrando Published: 2026-10-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.19818v1 Agentic AI systems combine model decisions, mutable state, tool calls, and delegation to external agents. Monitoring them requires observations from different execution boundaries, while prevention requires control before an operation produces its effect. We present AgenticRV, a runtime-verification architecture that separates these boundaries from the monitoring formalism. Adapters emit canonical events; each monitor receives its own projection and abstraction; and a decision policy uses normalised verdicts to select a reaction supported by the responsible adapter. We formalise when observations suffice, monitor replacement preserves decisions, and blocking prevents unsafe effects. We also distinguish rejected attempts from completed effects, avoiding the assumption that a blocked request must leave every monitor in a permanent violation state. The Python implementation supports LangGraph, MCP, and A2A. A controlled LangGraph experiment combines an external Reelay temporal monitor with a programmatic report monitor; ablations show why both are needed for the selected requirements. Differential checks and cross-adapter tests provide further integration evidence. An LLM-driven incident-response example illustrates the same enforcement path, while existing microbenchmarks isolate framework costs. The results support reuse of monitoring methods at explicit control boundaries, subject to the stated observation and deployment assumptions. --- ### Model vs. User: Whose Values Prevail? Inference-Time Value Alignment in Multi-Turn Conversations Authors: Enrico Liscio, Anne Arzberger, Aditya Shankar, Pradeep K. Murukannaiah Published: 2026-10-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.19817v1 Human values shape how we expect language models to behave. Dominant alignment approaches treat values as global objectives, although the appropriate value orientation is personal and contextual. Training-free alignment can steer models toward target values at inference time, yet has been largely evaluated in single-turn settings and with a single steering direction (e.g., toward safety). We evaluate four prompt- and activation-based steering methods in multi-turn conversations, where user and assistant models push toward the same or opposing, equally desirable values. We track alignment with a linear probe across three models and two value trade-offs. When assistant and user pull in opposite directions, the side matching the assistant's baseline bias often prevails, and effects that look successful early often fade or reverse after a few turns. Steering should therefore be evaluated over full conversations and in both directions of a value trade-off. --- ### When Does Depth Help? Understanding Layerwise Inference in Tabular Foundation Models Authors: Wenwen Gong, Haotian Gu, Zhen Yang, Jiaying Ma, Hanqing Zhang, Zhongshen Wang, Jingjun Wang, Shouyi Xu, Wei Wang Published: 2026-10-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.19814v1 Transformer-based tabular foundation models (TFMs) achieve state-of-the-art performance on small to medium-sized tabular prediction tasks while processing diverse inputs through a shared stack of layers. Recent layerwise analyses identify strong predictive performance in early TFM representations and substantial overlap in computation across layers. However, early predictive accessibility alone does not establish whether later layers are dispensable for every input, and aggregate accuracy can obscure which inputs benefit from additional computation. We study all 24 in-context-learning layers of TabPFN-3 across 272 classification datasets, combining representation geometry, prediction trajectories, truncation, and structural interventions, while also examining related representation dynamics in four additional TFMs. We uncover a pronounced expansion-compression trajectory, with stronger late dimensional contraction associated with larger increases in class-prototype separation. A targeted analysis of early-stabilizing samples shows that substantial representational changes persist after predicted classes stabilize, while locally ambiguous queries obtain larger accuracy gains from shallow to late layers than well-separated queries. Repeating a single pretrained block or perturbing layer order reduces predictive performance on average, constraining simple post-hoc substitutions in the frozen model. These findings distinguish predictive accessibility, class stability, and the benefits of continuing computation, supporting an input-dependent assessment of depthwise redundancy in TFMs. --- ### VaryST: Generalizable Spatio-Temporal Forecasting Beyond the Closed-World Setting Authors: Shengnan Guo, Jinjun Cheng, Xiaowei Mao, Jianhao Zhang, Haochen Lv, Yang Jiang, YiHeng Huang, Yan Lin, Youfang Lin, Huaiyu Wan Published: 2026-10-14 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.19813v1 Spatio-temporal forecasting is fundamental to many real-world systems, yet deployment environments are inherently varying: temporal distributions may evolve, spatial domains may change, and observation availability may shift from training conditions. Existing models are often tightly coupled to their training environments through node-specific representations, predefined spatial support sets, and reliance on consistently available observations, limiting generalization to changing environments. To this end, we propose VaryST, a compact spatio-temporal forecasting model trained from scratch that achieves strong generalization by dynamically constructing predictive context from available long-term observations. To accommodate temporal changes, VaryST derives node representations from long-term histories, capturing current behavior in the context of longer-term patterns. To adapt to spatial changes, it dynamically selects functionally relevant support nodes beyond predefined neighborhoods and integrates their information with recent and long-term target states and global context. To handle varying observation availability, VaryST selectively masks historical patches on which the model relies most during training, encouraging it to exploit alternative temporal and spatial dependencies for accurate forecasting when key observations become unavailable. Extensive experiments on six real-world datasets against seventeen baselines show that VaryST achieves strong in-domain forecasting accuracy, substantially improves zero- and few-shot generalization under spatial and temporal changes, and remains robust to varying observation availability. --- ### Calibration and Risk-Budgeted Decisions with System One Models Authors: Soundouss Messoudi, Youness Mansar Published: 2026-10-14 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2610.19811v1 LLM workflows and agents rely on a set of binary decisions like allow/block an input, or discard/retain a retrieved document. When human deferral is unavailable, uncertain cases must still receive an action. We study System One decision scores in this setting by defaulting to a conservative fallback when uncertain, and controlling the false omission risk within the subset of inputs assigned the utility-maximizing action. Across six datasets covering moderation, safety, and reranking, we compare general System One models with task baselines and a local open-weights fine-tuned System One model. We show that naive baselines for threshold selection exceed the target risk in roughly half of settings with defined test risk, compared with 7.8\% for Learn Then Test (LTT), which leverages finite-sample statistical guarantees. Our results show why relying on a probability-like interface is insufficient for deployment decisions and how risk-budgeted selection trades useful action against observed error. --- ### ReproBAIT: Can coding agents build their own biological AI tools? Authors: Shiv Muthupandiyan, Tolga H. Dur, Mac Walker, Timo Flesch, Mahmoud Ghanem, Steph Suddell, Giles Harper-Donnelly, Sophie Rose, Jasper Götting, Coleman Breen, Jake Pencharz Published: 2026-10-14 Categories: cs.AI, cs.CY, cs.LG arXiv: https://arxiv.org/abs/2610.19810v1 Large language models are increasingly competent at leveraging scientific knowledge and existing computational tools to execute complex workflows. At present, little information exists on their ability to reconstruct tools when given limited descriptions of such tools. We introduce an evaluation titled ReproBAIT (Reproducing Biological AI Tools), which measures the ability of coding agents to design, implement, and train biological AI tools taken from published research across a range of information access conditions. The coding agent is securely sandboxed without internet access and receives training data, a fixed time and compute budget, and limited information about the tool to replicate. We then score the reproduced biological AI tool based on its performance (tool-specific metrics) on held-out data. We evaluated a set of biological AI tools of varying complexities: ProteinMPNN, an inverse protein folding tool, RFdiffusion3, an all-atom generative diffusion tool, and a closed-source molecular design tool. We institute a methodology to check for memorisation, as the open source tools are likely to be included in models' pretraining corpus. Across a range of leading closed- and open-source coding agents, we find substantial reproduction capability for some selected tools, though limited capability for a highly complex tool. We find moderate evidence consistent with memorisation, varying across coding agents. These results suggest that tool developers need to be increasingly cautious when releasing information about the tools publicly; re-creation of the tool based on such information could undermine a tool's commercial value or invalidate dual-use managed access strategies. --- ### Efficient contextual partial monitoring with general function approximation Authors: Kapilan Balagopalan, Hao Qin, Kwang-Sung Jun, Chicheng Zhang Published: 2026-10-14 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2610.19804v1 We study finite stochastic partial monitoring (PM) games with side information, a paradigm of sequential learning with partial feedback. On each round $t \in (T)$, both player and environment observe a context and player chooses an action and environment simultaneously chooses an outcome. The player neither observes the outcome nor the loss; instead, they only observe a feedback symbol which is partially informative about the outcome. We utilize the Estimation-to-Decisions (E2D) meta-algorithm of Foster et al.(2021) to design E2D.PMSide, a computationally efficient framework for contextual partial monitoring, which uses an online regression oracle to efficiently estimate the outcome distributions based on historical (context, action, feedback symbol) tuples. Since the exploration rule given by the original E2D algorithm is intractable to compute, we propose two computationally efficient exploration rules that achieve optimal regret orders in $T$: in the globally observable setting, our exploration rule is based on $ε$-greedy, while in the locally observable setting, our exploration rule uses inverse gap weighting (Foster & Rakhlin, 2020), which was previously only known to be effective in the bandit setting. We show that a variant of E2D.PMSide named OE2D.PMSide can be combined with offline regression oracles to give an efficient algorithm with optimal regret when the contexts are drawn independently from a fixed distribution. We evaluate our algorithm on a synthetic label-efficient prediction game and an LLM routing task, in which a learner decides from prompt, uncertainty, and internal state features whether to escalate a query from a weak model to a strong one. We show that our method has superior performance to prior approaches. --- ### Improving Category-Aware Active Domain Adaptation via Uncertainty-Guided Region Coverage Authors: My Tra Nguyen Huynh, Viet Cuong Ta Published: 2026-10-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.19803v1 Active domain adaptation researches focus on alleviating the annotation cost, which comprises source data and target data labelling, as well as enhancing the performance of unsupervised domain adaptation. However, optimizing the adaptation model based on the average accuracy can lead to the drop in performance of some difficult categories. To overcome this issue, a point-wise selection strategy built upon the influence function can be used to improve domain adaptation performance. In our work, we first address the sensitive and redundant aspects of point-wise selection, which can lead to overfitting of the acquisition function. We thus introduce a region-based approach that ensures the improvement of the adaptation model by maximizing a positive manifold coverage. An uncertainty score is further introduced to the selection mechanism to learn a better decision boundary for the target domain. In comprehensive experiments, our proposed method surpasses the first category-aware active domain adaptation baseline as well as existing active domain adaptation methods across multiple domain adaptation benchmarks. Our implementation is available at: https://github.com/nhtm2702/WHO IS NEXT. --- ### Asymptotically Exact Negative Guidance of Diffusion Models via Positive-Unlabeled Learning Authors: Hirohane Takagi, Masashi Sugiyama Published: 2026-10-14 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2610.19802v1 Negative guidance of diffusion models generates samples that avoid an undesired condition, specified either by reference samples or by a conditional score alongside an unconditional model. Existing methods inject repulsive terms derived from local information at each sample, so the resulting sampler does not target an explicit density, and its bias cannot be systematically reduced by increasing computation. We instead present a negative-guidance method that samples from an explicit target density, which uniformly handles both reference-sample and score-based specifications and suppresses probability mass near the undesired condition with an avoidance strength that parametrizes the target density itself. Realizing this target requires estimating, at each diffusion timestep, how likely each sample is to belong to the undesired condition. We cast this estimation as a Positive-Unlabeled learning problem that admits lightweight online training along the diffusion trajectory, using condition samples as positives and diffusion particles as unlabeled data. Because the guided particles drift from the unconditional marginal, we further correct the residual mismatch via Sequential Monte Carlo, yielding a sampler that is asymptotically exact in the particle limit and that turns any existing negative-guidance method into its proposal kernel. Empirically, our method approaches the ground-truth target on Gaussian mixtures and Pareto-dominates existing methods on trade-offs between avoidance and generation quality, distributional bias, and diversity, including in an image-generation setting with a pretrained score network. --- ### Delta Tokenizer: Reference-Identical Tokenization of Session Deltas and Segment-Parallelism for Long Prompts on Multicore CPUs Authors: Zhenyu Zhang, Zhichao Cao Published: 2026-10-14 Categories: cs.CL, cs.DC, cs.PF arXiv: https://arxiv.org/abs/2610.19801v1 An agent that drives an LLM sends the model the same conversation again and again, and each turn adds only a little text at the end. Inference engines reuse the KV cache of the shared prefix, so only the new tokens pass through the model. However, tokenization has no such shortcut. The CPU front end of the serving engine converts every request back into token IDs from its first character, which lengthens the time to first token (TTFT) and consumes CPU on every turn. We present Delta Tokenizer, a CPU tokenization front end that tokenizes only the delta between a request and the previous request of the same session. It retains the earlier token sequence, encodes again only the appended text and the short tail whose tokens the append could affect, and joins the two only at a position the tokenizer's splitting rules themselves cannot move, which keeps the result exact. For long requests with no state to reuse, it cuts the text where practical tokenizers already keep neighboring pieces independent, encodes the pieces on several cores at once, and concatenates the outputs into the reference encoding, exactly. A shared CPU pool schedules these chunks together with the short incremental updates, so an update runs between two chunks rather than behind an entire long job. The incremental path shortens the tokenization of a session turn by roughly 40x relative to the Hugging Face reference tokenizer, and on 16 cores the chunk-parallel path encodes a four-million-character request 8.2x faster than a serial encode and 1.6-2.1x faster than LoPT. Inside SGLang, Delta Tokenizer reduces the median TTFT through the chat interface by 59% at 100K tokens and brings the P99 TTFT of agent sessions down 9.5x under load and 23x when long requests tie up the front end. Every output we checked matches the reference, among them 41.8 billion documents encoded by its fast encoder. --- ### Evolve Together, Fall into Place: How Social Scaffolding Shapes Self-Evolving Multi-Agent Systems Authors: Seojin Hwang, Youngmin Choi, Hwanhee Lee Published: 2026-10-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.19799v1 Recent work lets LLM agents evolve their own harness, up to the team itself. Yet in human groups, the same abilities achieve different outcomes under different social conditions. Borrowing the notion of scaffolding from developmental psychology, we investigate whether the social scaffolding of a self-evolving multi-agent system (MAS), namely its team composition and structure of interdependence (e.g., collaboration, conformity, or competition), shapes how the team evolves. We present AGORA (Agents Growing through Organization and Relational Arrangements), a framework that varies the two axes independently across three evolution mechanisms. Across web search, codebase understanding, and document QA, we find that (1) evolution alone rarely helps, while the right scaffolding surpasses a strong agent evolved alone by up to 25 points; (2) it does so by moving authority to the most capable member while the others step back; and (3) this member, having grown within the team, outperforms the same model alone. Designing a self-evolving MAS thus requires designing its social scaffolding, which shapes not only how its agents learn, but who gets to lead. --- ### Learning Perception to Action Rules through Reinforcement Learning for Theory-of-Mind Reasoning Authors: Soyoung Oh, Nursulu Sagimbayeva, Nicholas Jennings, Paulina Hussein, Mehwish Alam, Vera Demberg Published: 2026-10-14 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.19796v1 In Theory-of-Mind (ToM) reasoning, large language models may correctly infer the agent's mental state but fail to use that inference when predicting or judging the agent's subsequent actions. In this work, we investigate whether explicitly connecting perception, belief, and action with rules improves ToM reasoning. We generate concise \textit{if--then} rules that express relations between perception to action and use Group Relative Policy Optimization (GRPO) to train Qwen2.5 and Llama3 models across four ToM benchmarks. GRPO with rule generation outperforms prompting, supervised fine-tuning, and think reasoning. Moreover, rules generated by larger models ($\geq$3B) provide transferable knowledge that improves downstream performance of GPT-4o-mini. These findings suggest that explicit rules help models bridge the reasoning gap in ToM and support knowledge transfer across models. --- ### StateCraft: Augmenting Video World Models with Abstract-State Reasoning Authors: Lorenzo Venturoli, Nedko Savov, Xi Wang, Marc Pollefeys, Luc Van Gool Published: 2026-10-14 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.19795v1 Video world models aim to simulate complex environments with realistic appearance and dynamics. Maintaining consistency over long interactions requires tracking past actions and understanding how those actions affect the environment. Video world models can only generate partial observations of the entire world at a time. Remembering past observations alone may not be sufficient in every scenario, as they may no longer reflect the world after a sequence of actions. We introduce a paradigm that decouples a persistent, updatable abstract state from the visual state. The abstract state keeps track of the entities' changes as the world evolves, and is used to condition the visual state, which represents the current view. We propose StateCraft, a novel architecture that pairs a language model with a video diffusion model to evolve the dynamic world. We evaluate our approach on generative interfaces, which pose a substantial challenge because a single action may change parts of the state that are not currently visible. To support training and evaluation, we develop a data collection pipeline that produces informative, densely annotated trajectories at scale without human or agent supervision, together with a benchmark measuring generation quality, memory, and controllability. On this benchmark, our approach improves surpasses the state-of-the-art baselines. We demonstrate that StateCraft maintains high self-consistency and strong generation quality over long trajectories. Because the abstract state is explicit, it can be edited directly, and generation follows edits to states never observed in the data. Finally, a proof-of-concept 3D experiment, in which actions change the illumination of an unobserved room, shows that the paradigm can also be applied to spatial environments. Project page: https://insait-institute.github.io/StateCraft/. --- ### JetSpec++: Foresight Parallel Drafting with Self Refinements Authors: Zhaoxiang Feng, Lanxiang Hu, Haoran Yuan, Yu-Yang Qian, Jihui Yang, Peng Zhao, Yibo Zhu, Tajana Rosing, Hao Zhang Published: 2026-10-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.19792v2 Speculative decoding's effectiveness is governed by two quantities: the acceptance rate of drafted tokens and the cost of producing them. We show the two objectives can be co-optimized with algorithm-system co-design, and present JetSpec++, which retains a strong learned draft model while hiding its cost almost entirely. JetSpec++ combines three components: intra-block self refinement, which trains the draft model to iteratively correct its own parallel predictions within a block of tokens; inter-block foresight drafting, which begins the next block before the current one is verified; and pipelined drafting and verification, which overlaps the two stages so drafting's marginal wall-clock cost approaches zero. In comparison with state-of-the-art speculative decoding methods, JetSpec++ attains a wall-clock speedup of up to $7.45\times$ over autoregressive (AR) decoding and $1.54\times$ over DSpark, with up to 1,361 tokens per second for a single request on GB200, and an average acceptance length of 8.94 across seven benchmarks, while preserving the target model's output distribution. Our code and models are available at https://github.com/hao-ai-lab/JetSpec. --- ### One Agent per Zone: Decentralised Active Inference under Partial Observability for Multi-Zone HVAC Control on Edge Hardware Authors: Panagiotis Kasnesis, Lazaros Toumanidis, Christos Chatzigeorgiou, Amalia Contiero Syropoulou, Miguel De Prado Published: 2026-10-14 Categories: cs.MA, cs.AI arXiv: https://arxiv.org/abs/2610.19790v1 Multi-zone HVAC control is a shared-resource problem: zones on a floor share one fan and cooling coil, so each zone's demand affects its neighbours and the building's peak power. One controller per zone scales well and isolates faults, but each controller then observes only its own zone, not the shared air loop. In this work, we present a decentralised controller that assigns each zone an independent active-inference agent, which plans by minimising expected free energy and learns its zone dynamics online. The agents exchange no messages, so none depends on peers or a coordinator; each accounts for the unobserved coupling through a latent disturbance and a congestion signal derived from the metered power of the other floors. Fifteen agents are evaluated in EnergyPlus on a Sinergym office building against three rule-based controllers and three MADDPG fleets, one given the same floor meters. On five noisy weather years unseen during training, the fleet attains the lowest mean building peak (88.3 kW, 3 to 17 % below the baselines) and staggers the floor peaks better than any baseline, with a coincidence factor (building peak over the sum of the floor peaks) of 0.929 versus 0.936 to 0.994. Compared with a reactive rule at similar comfort (0.912 versus 0.916), it lowers the sum of monthly peaks, on which demand charges are billed, by 33 kW (4 %) in every year, at the cost of about 10 % more energy. It costs 9% less per year than the proactive rule (at lower comfort) and 1% less than the MADDPG fleet given the same floor meters, in every test year. The whole fleet runs on a single low-cost Raspberry Pi 5, closing the observation-to-action loop over MQTT in 442 ms at p95, far below the 15-minute control step. --- ### More Methods, Better Agents? A Reality Check on Self-Distillation in Agentic Reinforcement Learning Authors: Linhao Zhong, Bozhen Fang, Xuehao Wang, Duochao Shi, Zekai Luo, Guangming Yao, Yi Yuan, Hao Chen, Jingdong Chen, Chunhua Shen Published: 2026-10-14 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2610.19789v1 Self-distillation in agentic reinforcement learning has produced a growing number of methods. However, existing evaluations often reuse published baseline scores under differing experimental conditions, provide few direct comparisons among contemporaneous methods, and give limited attention to training stability and computational cost. These limitations obscure the source of reported gains and the practical strengths and weaknesses of competing methods. Costly agent training further motivates a common basis for comparison. To address these gaps, we compare ten representative methods against GRPO on ALFWorld, ScienceWorld, Search-QA, and WebShop across three model sizes. Our study comprises 132 training runs totaling 12,124.4 recorded H800 GPU-hours, with repeated evaluations over eight rollout seeds for the pretrained backbones and all eleven trained methods. Beyond final task performance, we examine training progress, stability, and measured computational cost. Our evaluation yields three key findings. First, gains over GRPO remain limited in scope, with no method consistently outperforming it across settings. Second, strong final performance can mask unstable training. Third, additional training cost does not consistently translate into better performance. We establish this benchmark to support fair, comprehensive comparison and guide future research toward reliable and cost-effective improvements in agent training. Project page: https://aim-uofa.github.io/Self-Distillation-AgentRL/ --- ### LiFi: LiDAR Generation from Multi-View Images via Geometric and Semantic Collaborative Guidance Authors: Sizhuo Zhou, Xiaosong Jia, Fanrui Zhang, Qifeng Li, Junjie Li, Zirui Wang, Yukang Feng, Yu Hong, Shaofeng Zhang, Wenlong Liao, Tao He, Juyong Zhang et al. Published: 2026-10-14 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2610.19786v1 Generating LiDAR point clouds from multi-view camera images is a valuable task with applications in controllable data synthesis, cross-modal simulation and various perception tasks. However, most existing methods are not specifically designed for this task, and the quality of their generated LiDAR remains limited. Moreover, these methods typically focus only on semantic cues in images or generate LiDAR from a monocular camera image. In this work, we introduce LiFi (LiDAR From images), a dedicated framework for generating visually and geometrically aligned LiDAR scenes from multi-view camera images. LiFi guides the latent diffusion process through two complementary branches: geometry and semantics. The geometry branch constructs scene features from images through a reverse sampling algorithm and an uncertainty-aware geometric encoder combined with DepthAnything3, whereas the semantic branch provides high-level semantic representations via a cross-view interaction module. We further introduce a dual-branch balanced classifier-free guidance (CFG) strategy, which enhances the model's conditional generation capability while preserving the independent learning and collaborative controllability of the two branches. Extensive experiments demonstrate that LiFi outperforms state-of-the-art methods in generating high-fidelity LiDAR scenes. The code will be publicly available at: https://github.com/szzhou88/LiFi. --- ### FPV-CRASH: A Dataset for Offline Crash Moment Localization in Drone First-Person-View Videos Authors: Jifan Zhang, Tingyu Wang, Qian Liu, Zhedong Zheng Published: 2026-10-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.19785v1 Crash Moment Localization aims to localize the major physical impact that interrupts controlled flight in an onboard first-person-view (FPV) video recorded by a drone, thereby providing a temporal reference for retrospective crash analysis in aerial robotics. However, existing crash-video datasets predominantly target surveillance or dash-camera footage, and their annotation schemes and task formulations are not designed for temporal localization of the major physical impact in UAV onboard FPV videos. To address this gap, we present FPV-CRASH, a dataset and fixed-protocol reference evaluation for offline Crash Moment Localization in drone FPV videos. FPV-CRASH contains 1,052 drone FPV clips (526 Crash and 526 Normal); each Crash clip has a single-frame reference annotation for the Crash Moment, and every clip is paired with four English captions automatically generated from sampled frames and the known Crash/Normal label. Normal clips carry no timestamp target and provide training-time background supervision. The captions support an auxiliary Text-to-Video Retrieval task, whereas localization inference remains video-only. We further provide a heatmap-based reference model that estimates a continuous Crash Moment timestamp from sparsely sampled frames. Under the fixed, non-source-disjoint clip-level protocol, the reference model reduces MAE from 1.12 s for the strongest fixed timing-prior baseline to 0.56 s (a 50% relative reduction) and achieves a median absolute error (MedAE) of 0.33 s; the fraction of clips localized within 0.5 s rises from 37.14% to 65.71%. The release includes annotations, available source video identifiers and URLs, clipping metadata, fixed split lists, and preprocessing code so that the reportable portion can be reconstructed without redistributing source footage. At submission time, all source-compilation URLs remained accessible. --- ### Reinforcement Learning via Advantage Guidance Authors: Zhiyuan Zhou, Sergey Levine Published: 2026-10-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.19783v1 Reinforcement learning (RL) holds the promise of learning a policy that can outperform what is shown in the data. However, in practice, such systems suffer from instability and hyperparameter sensitivity. In contrast, supervised learning provides a stable and scalable training objective, but is fundamentally limited by the quality of the demonstrated behavior. In this paper, we ask whether we can perform policy optimization with something as simple and stable as supervised learning but as performant as RL. Unfortunately, naively training the policy with supervised learning and conditioning on future rewards or advantages typically underperform dedicated RL methods. We introduce a new policy extraction method, Advantage Guidance, that retains the simple supervised learning structure with advantage conditioning while outperforming prior RL methods through effective conditional training and contrastive diffusion guidance during sampling. We show that Advantage Guidance can significantly improve a model's ability to respond to conditional advantage signals, and the contrastive guidance during sampling can use the learned advantage-conditioned policy to target the KL-regularized optimal policy. Empirically, we find that Advantage Guidance significantly outperforms prior state-of-the-art RL methods on 26 long-horizon, sparse reward tasks across datasets with varying degrees of optimality. --- ### Learning Who Benefits Most: Multi-Treatment Causal Ranking for Population Health Stratification Authors: Rocco Zaccagnino, Martina Girolamo, Alberto Lombardi, Delfina Malandrino, Donatello Telesca, Alessia Ture Published: 2026-10-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.19782v1 Population health stratification frameworks, such as the Italian DM77, organize patients by clinical need and care pathways but offer limited guidance on which care changes to prioritize under constrained resources. We present PROMETHEUS (Proactive Resource Optimization through Multi-treatment Effect-based Targeting in Healthcare Environments Using Stratification), a framework that formulates population health stratification as a multi-treatment causal ranking problem. Its objective is to order eligible patient-treatment opportunities by expected incremental benefit rather than obtain perfectly calibrated individual treatment-effect estimates. Each clinically admissible care intensification is compared with maintaining the patient's current pathway. Treatments are learned jointly to produce a globally comparable ranking across patients and care profiles, within domains sharing a reference condition, outcome, follow-up horizon, and benefit scale. This separates clinical need, treatment benefit, and resource-constrained allocation. PROMETHEUS combines doubly robust causal signals with a Siamese neural ranking model and contrastive representation pretraining. The shared representation captures similarities across care transitions, supporting prioritization under capacity constraints. Synthetic experiments and semi-synthetic experiments using real administrative covariates from ASL Benevento evaluate ranking quality, allocation value, robustness, and failure modes. The results support the framework's ability to recover generated benefit orderings and prioritize care opportunities in the evaluated settings. PROMETHEUS provides a preclinical approach to actionable stratification; validation with observed treatment-outcome data is required before clinical use. --- ### SNACK: A Sequential Notation Framework for Probabilistic Graph Generation Authors: Hohyun Kim, Hyesung Kim, Min-hwan Oh, Seunggeun Lee Published: 2026-10-14 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2610.19781v1 We introduce SNACK, a string representation for probabilistic graph generation that enables sequence models to generate and model graphs with discrete node and edge features. SNACK linearizes graphs by encoding the nonzero entries of the lower-triangular adjacency matrix, establishing a bijective correspondence between valid sequences and ordered adjacency matrices. This design enables invalid logit masking to enforce structural constraints--such as chemical valence and ordering rules--guaranteeing 100% valid generated sequences. SNACK also enables principled string-based GFlowNet training by explicitly accounting for node-ordering symmetries. Across standard graph-generation tasks and molecular distribution-learning benchmarks, SNACK achieves competitive sample quality, while substantially improving the throughput of GFlowNet training relative to graph-based generation. Probing analyses further show that models trained on SNACK encode meaningful local and global graph structure despite receiving only sequential supervision. These results position SNACK as a practical framework for probabilistic graph generation with deep sequence models. --- ### LabOPBench: A Multimodal Benchmark for Evidence-Grounded Laboratory Decision Making Authors: Jingyuan Li, Yujie Liu, Yijie Dai, Xiaoyu Yuan, Nian Ran, Huajie Niu, Ming Zhu, Shuwen Zhao, Chenxi Li, Fenghao Lu, Jiahao Li, Xinyu Gu et al. Published: 2026-10-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.19780v1 Laboratory experiments involve more than following predefined protocols; they require adaptive decision-making as the experimental state changes. Existing scientific benchmarks rarely assess such evidence-based decisions in laboratory settings. Here we present LabOPBench, a multimodal benchmark of 756 expert-authored, independently reviewed questions in organic synthesis and materials science. Each item pairs laboratory evidence with procedural context and an open-ended judgment, evaluated using a question-specific scoring rubric. Eight multimodal models obtain overall normalized scores of 28.8-45.8%, leaving substantial room for improvement. On a controlled 100-question subset, the strongest models outperform undergraduate participants on average but remain below the average performance of PhD participants. Expert analysis of responses from the three leading models identifies Evidence Misreading and Evidence-Decision Conflict as the dominant error patterns. These results reveal that current models still struggle to turn multimodal perception into reliable laboratory decision-making. ---