# Research Papers — 2026-09 · bundle page 9 of 266 > Full-text markdown of papers #401–450 of 13298 published in 2026-09, newest first. AI-readable mirrors of the full 13298-paper 2026-09 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-09/page/9 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/8.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/10.md) ### From Benchmarks to Production: Transferring Time Series Anomaly Detection Methods for Electricity Production Monitoring Authors: Nicolas Vautier, Paul Caron, Nardi Xhepi, Félicie Bizeul, Manel Boumghar, Christophe Degouy, Paul Boniol Published: 2026-09-30 Categories: cs.LG, cs.AI, cs.DB arXiv: https://arxiv.org/abs/2609.39257v1 Accurate forecasting of electricity production is essential for maintaining the operational efficiency and strategic planning of energy utilities. In industrial settings, such forecasts are generated daily to ensure supply-demand balance and optimal management of production assets. However, the increasing complexity of modern power systems and data flows poses significant challenges for ensuring the reliability and consistency of these forecasts. This paper addresses the problem of anomaly detection in short-term production forecasts at EDF, formulated as identifying atypical intra-day patterns that may signal data quality issues or operational irregularities. We introduce TAMIS, a scalable and interpretable system that analyzes daily production time series to automatically detect anomalous days based on deviations from historical patterns learned from past data. Designed for human-in-the-loop workflows, TAMIS surfaces top-ranked anomalies through an automated daily newsletter, enabling efficient expert review and continuous monitoring. An extensive experimental evaluation on real-world industrial data demonstrates that TAMIS achieves the best accuracy-efficiency trade-off compared to baseline methods. To foster further research and reproducibility, we publicly release the anonymized application datasets used in our study. --- ### Client and Training Data Selection for Computationally Efficient Synchronized Federated Learning Authors: Muzaffer Citir, Hiroki Nishikawa, Sangyoung Park Published: 2026-09-30 Categories: cs.LG, cs.DC arXiv: https://arxiv.org/abs/2609.39250v1 Federated learning (FL) is a promising paradigm of machine learning, which preserves user privacy by enabling learning without sharing raw data with a cloud server. Straggling clients have been a problem for FL as they introduce delays in aggregating the local models and hence, the convergence of the global model. Therefore, it is important to have a mechanism that ensures fast convergence of the global model as well as good FL participation rate. Another issue for the convergence of a model in FL is the non-independent and identically distributed (non-iid) data across the clients. Prior approaches based on probabilistic client selection do not work well under non-iid data especially when the number of clients is small. We show scenarios where such approaches fail and propose a joint client-training data selection algorithm for fast convergence of FL models. Our experiments on CIFAR-100 dataset show that convergence of the FL model can be significantly improved over prior works that can consider non-iid data and heterogeneous computation and higher model accuracy. --- ### Null-model treatment of the sensory-motor boundary changes an evolutionary connectome comparison Authors: Gyujeong Park Published: 2026-09-30 Categories: cs.NE, q-bio.NC arXiv: https://arxiv.org/abs/2609.39248v1 Randomised copies of a connectome are the usual baseline for asking whether measured wiring matters, and the answer depends on what the randomisation preserves. We evolved embodied foraging agents whose brains are a compressed adult Drosophila connectome (FlyWire v783; 512 cell-type groups and 1,000 Kenyon cells) alongside agents built on randomised wiring, in pre-registered experiments with ten seeds, four ecologies and 600 generations. Two standard randomisations, a column shuffle and degree-preserving edge swaps, route 10.6 to 10.7 % of olfactory output directly onto descending motor groups, against 0.012 % in the connectome. On the registered primary endpoint, fitness averaged over the run, no difference was detected; at the last common-garden probe the connectome was behind both controls (-0.22 and -0.20 fitness units on seed means). Against controls that keep every sensory-output and motor-input edge and rewire only the interior, the seed-mean difference lay within a +/-0.10 equivalence bound (+0.002 and -0.074, unchanged under a calibration that also matches activity spread), although per ecology the interior column shuffle was ahead by 0.26 in one of four ecologies at ten seeds, a lead that ten further pre-registered seeds did not replicate. Rewiring the connectome so that it acquires the shortcut raised its fitness by 0.44 (10 of 10 seeds) and its dependence on olfaction from 0.15 to 0.99; graded doses raised both in step; at comparable swap counts the full dose was ahead of an interior-only sham by 0.53 (10 of 10 seeds); and a sham that rewired the same boundary edges without creating shortcuts matched the connectome (+0.007) while the full dose was ahead of it by 0.60. What a null preserves at the sensory-motor boundary can decide an evolutionary connectome comparison, and sensory-to-motor path statistics belong next to the degree statistics a null is said to preserve. --- ### Trust the Critic More Authors: Kaiyue Wen, Luke Bailey, Arvind Mahankali, Tengyu Ma Published: 2026-09-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.39247v1 Standard language model RL algorithms credit every token of a long rollout with the same advantage determined by the terminal reward. Actor-critic methods can provide finer-grained credit assignment, but learned critics are generally considered too inaccurate to trust when training LLMs with RL. In recent works, even when a critic is present, it is used only for baseline estimation, so every trajectory must be rolled out to its terminal reward. We introduce Actor-Critic with Action Chunking (AC2) that removes the need to roll every trajectory to completion. AC2 instead assigns credit to action chunks: short continuations of prefixes of past trajectories. A learned critic scores the state reached at the end of each action chunk, allowing the policy to update without observing a terminal reward. We make critic-based credit assignment reliable through three design choices. First, we introduce local readiness which uses critic-based updates on a problem only when the critic is sufficiently accurate on that particular problem. Second, when available, we provide the critic with a reference solution from a previous successful rollout. Third, we assign credit over action chunks of 10k tokens rather than individual tokens, giving the critic a more meaningful portion of the trajectory to evaluate. We train Qwen3-4B on FineProofs-RL using AC2 and evaluate on IMO-ProofBench. AC2 exceeds GRPO's peak validation score of 18.5% using 2.5x fewer decoding FLOPs. This gain comes from two sources, (1) AC2 requires 25% fewer training steps to reach this score, and (2) each step generates fewer tokens because the policy does not need to continue every trajectory to completion. Conceptually, we demonstrate that we can remove the need to roll out every trajectory to completion, opening up a large previously unexplored design space for LLM RL algorithms. --- ### Right Answer, Wrong Mechanism: Detecting Pernicious Divergence in Causal Interventions Authors: Beiming Liu, Minjie Chen Published: 2026-09-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.39243v1 Causal interventions such as activation patching and distributed alignment search (DAS) are the main tool for making mechanistic claims about neural networks. Recent work showed that these interventions routinely push representations off the model's natural distribution, and that such divergence is sometimes harmless and sometimes pernicious: it can recruit pathways the model never uses on natural inputs, so that an intervention produces the expected answer through the wrong mechanism. No method currently tells the two cases apart. We make this question testable by planting hidden pathways inside pretrained language models; the pathways are silent on every benchmark prompt by construction, so which interventions depend on them is known exactly. Across 72 configurations and 100,800 interventions on GPT-2 small, we find three things. (i) Nearest-neighbour and local-PCA distances at the intervention site, as used in prior work, score below chance (AUROC 0.35-0.47) at picking out interventions that give the right answer through a planted pathway. (ii) Hidden-Pathway Contribution (HPC), a label-free test that clamps downstream units to the regime of natural runs with the same output and measures how much of the decision disappears, flags pathway-dominated interventions with AUROC >= 0.99 when the pathway shows up as unit-level out-of-regime activity, but fails when every unit stays within its natural range, which we identify as the open problem. (iii) Optimised interventions actively seek hidden pathways: on a gender task, DAS routes 90-95% of its successes through planted pathways for three of four families, and a downstream on-manifold penalty cuts this share to under 5% at a cost of 6-11 points of success rate. In unmodified GPT-2, successful interventions show almost no unit-level out-of-regime reliance. --- ### A differentiability framework for zigzag persistent homology via linear interpolation Authors: Enrico Maria Ferrari, Clemens Bannwart, Matteo Biagetti Published: 2026-09-30 Categories: cs.LG, cs.CG, math.AT arXiv: https://arxiv.org/abs/2609.39242v1 Persistent homology can be differentiated and incorporated into learning pipelines, but no analogous framework exists for zigzag persistence, which is needed when the underlying topological structure evolves non-monotonically over time. We develop such a framework for sequences of simplicial complexes obtained by thresholding time-dependent filtering values on a fixed complex. By assigning persistence diagram endpoints the real-valued times at which linearly interpolated filtering values cross the threshold, we transfer the continuity of the filtering values to the diagram points. This yields smooth local lifts of the resulting persistence-diagram-valued map, from which we derive differentials almost everywhere under mild regularity conditions on the parametrization of the filtering values. We prove local Lipschitz continuity outside an explicit measure-zero exclusion set; standard stochastic subgradient convergence guarantees therefore do not apply directly. We argue that, even without such guarantees, this exclusion set is small enough in practice to allow effective optimization. We test this empirically in two experiments: sensor network coverage optimization and dynamic graph classification. --- ### Evolutionary foraging in grids: Intermittent search dynamics emerge in finite, depletable landscapes Authors: Shailendra Bhandari, Alex Szorkovszky, Anis Yazidi, Pedro G. Lind Published: 2026-09-30 Categories: q-bio.PE, cs.NE arXiv: https://arxiv.org/abs/2609.39239v1 How search strategies evolve in finite, depletable landscapes remains a question in foraging theory. We study this problem with an evolutionary simulation in which agents forage on a two-dimensional toroidal lattice containing non-renewable resources distributed uniformly or as Lévy dust. Each agent carries a heritable genome encoding step lengths, velocities, and turning angles, and selection acts on a fitness function combining energetic gain, movement cost, and coverage efficiency. By allowing movement traits to evolve without imposing a prescribed power-law step-length distribution, we test whether evolved trajectories are better described by intermittent-search or Lévy-walk dynamics. Our results indicate that evolved search is more consistent with intermittent dynamics than with strict scale-free Lévy motion in the finite depletion-driven landscapes considered here. We characterize the dynamics by fitting second- and fourth-order displacement moments to intermittent-search and Lévy-walk models. While a Lévy-like random walk fits the evolutionary trajectories well (mean adjusted $R^2$ > 0.9 in most tested conditions), intermittent search achieves a closer fit (mean adjusted $R^2$ > 0.99) for all tested resource distributions. This preference holds across the tested grid sizes and resource densities. Five independent evolutionary runs per environment on a 503 x 503 grid at nominal resource density $ρ$ = 0.15 reproduce this preference for the uniform environment and five Lévy-dust environments. Evolution rapidly reshapes the movement genome toward short displacements while retaining a sparse tail of longer relocations, consistent with local exploitation punctuated by occasional transfer. The framework provides a controlled setting for studying how search rules emerge under resource limitation and may inform resource-constrained exploration in autonomous systems. --- ### 4MT-VLM: How Coarse Is a VLMs Cognitive Map? Authors: Markus Frey Published: 2026-09-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.39238v1 An agent that moves must recognise a place from a viewpoint it has never seen. We introduce 4MT-VLM, a dataset of procedurally generated landscapes, each rendered across five stimulus modes that remove appearance cues while holding layout fixed: shape and colour, shape only, colour only, bare terrain peaks with no objects, and a valley viewpoint that puts the peaks on the horizon. The last condition is commonly used in clinics to probe hippocampal function in human patients. We test this benchmark across sixteen different open and closed-source models and report 4AFC performance, a measure which is also used to grade human participants. We observe that models identify a place from the studied viewpoint but lose it once the camera moves, dropping below the 25% chance level at 135° where a human observer scores 85%. Frontier models (Gemini 3.8 Flash, GPT-5.6) answer only 39% and 31% of rotated trials correctly, recovering to 85% and 55% only when distractors are moved more than 30 meters apart. Our benchmark demonstrates that while current VLMs possess rudimentary cognitive maps, their spatial resolution remains fundamentally too coarse to maintain a stable, 3D understanding of the world once the viewpoint changes. --- ### The Planning Limits of Latent World Models Authors: Ali Alrasheed, Basim Azam, Naveed Akhtar Published: 2026-09-30 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2609.39235v1 World models offer a promising way to help robots understand how the physical world evolves and plan complex behaviours through imagination. Yet existing studies mainly demonstrate what these models can accomplish, leaving unclear when their predictions remain useful for planning and where they fail. We study this question using action-conditioned predictors built on five frozen self-supervised visual backbones: V-JEPA 2, V-JEPA 2.1, VideoMAEv2, VideoPrism, and DINOv2. We use frozen backbones to test representations intended to transfer across environments. We evaluate these models on diverse Meta-World manipulation tasks and real-robot interactions from BridgeData V2. We find that a world model guides action selection reliably only when the goal lies within, or slightly beyond, the trajectory it imagines during planning. With five-step rollouts, the length the predictor was trained on, the world model ranks actions reliably only for targets five to ten control steps ahead, whereas task goals lie 16 to 53 steps away. Neither an 81-fold larger predictor nor longer-rollout training extends this range; the encoder affects both range and closed-loop success, with V-JEPA 2.1 performing most consistently. More fundamentally, the limit persists under perfect prediction: using the real simulator, success falls from 92% to 41% as the target moves from five to twenty steps ahead of a five-step rollout. Planning therefore requires either longer imagined trajectories or closer subgoals. For distant goals, pure imagination succeeds in 23% of episodes, planning with feedback (MPC) raises success to 30%, imagining as far as the goal to 47%, and nearby expert subgoals to 76%. Used within its plannable range, a world model can also improve a vision-language-action (VLA) policy: choosing among eight actions the VLA proposes raises its success from 65% to 77% across 16 different tasks. --- ### What Streaming Anomaly Detection Finds (and Misses) in Industrial Time Series Authors: Magali Parrino, Antoine Ajenjo, Emmanuel Remy, Pierre Stephan, Paul Boniol Published: 2026-09-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.39232v1 EDF relies on continuous monitoring of its power plants to detect anomalies as soon as they occur. Given the absence of a universally optimal streaming method in unsupervised settings, we compare streaming methods with state-of-the-art TSAD models deployed online on a real nuclear power plant dataset. This work also evaluates Automated Anomaly Detection in a streaming context. Results show higher consistency for online TSAD and strong robustness from ensembling strategies. --- ### RAIM: Robust Aggregation of Inexpensive Models for Hallucination Detection Authors: Elia Onofri, Roberto Di Pietro Published: 2026-09-30 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.39229v1 Automatic evaluation of faithfulness increasingly relies on a large language model acting as a judge, yet the most reliable judges are proprietary frontier models, costly and ill-suited to high-throughput monitoring. We investigate whether a panel of cheap open-weight judges (4--9B) can be aggregated to stand in for a frontier one, what the substitution sacrifices, and when it is worth making. We propose RAIM, an aggregation scheme robust to the members' correlated errors, coupling a cross-fitted stacked logistic regression with an admissibility test that, read from the members' own outputs, identifies when aggregating them improves on their best member and stays within reach of the frontier judge. We instantiate RAIM with ten judges from disjoint families across eight faithfulness benchmarks. Against Claude Sonnet, the panel retains a median 93% of its Cohen's $κ$ and gives up only 2.9 points of balanced accuracy on average; read as paired differences, it clearly improves on one benchmark and clearly worsens on three (only two by a non-negligible margin), leaving four unresolved. At a sixty-fourth of the frontier's inference price, the operative expense is a one-time in-domain calibration on 50--100 labelled records. The panel is also competitive with purpose-trained detectors on their home benchmarks (within 1.3 accuracy points of GPT-4o and 1.9 of the LLM-AggreFact leader), and beats the strongest one we reran by 6 points on our grounded sets. Whether aggregation pays depends on the members themselves: where several capable members err on different items, the panel improves on its best judge and approaches the frontier; where one dominates, the stacker recovers the leader, and only there does the frontier remain materially ahead. Both conditions are read off the calibration set at no further cost, so a cheap panel can stand in for a frontier one wherever this audit admits it. --- ### Fyan: A Human--AI Harness with Semantic Auditing for Document-Level Formalization Authors: Wei Zhao, Yangshuo Zou, Chengxiang Ding, Yifan Wu, Xuchuan Wang, Zimu Mao, Lei Zhang, Tao Luo Published: 2026-09-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.39228v1 We present FYAN, a human--AI harness for document-level mathematical formalization. Rather than treating theorems in isolation, FYAN coordinates an end-to-end workflow spanning specification, proof planning, logical review, Lean proof construction, knowledge curation, and validation, with support for independent supervision and human guidance. A central component is evidence-grounded semantic auditing, which assesses whether formal statements faithfully preserve their informal specifications. A language model constructs structured evidence over local correspondences, omissions, scope, and logical relations, while a deterministic validator checks this evidence and produces reproducible judgments. When a substantive but admissible deviation is accepted, FYAN requires an explicit proof-transfer obligation connecting the formal statement back to a source-facing interpretation. With the same model (DeepSeek-V4.1-Flash) in every stage, FYAN proves 86 of 143 FormalTCS theorems under a strict Lean check, against 69 for a general agent harness, and raises the natural-language proof score from 0.501 to 0.851. On ConsistencyCheck, its semantic audit catches more inconsistent statements than a direct LLM judge, both on labels verified against the source (recall 0.777 vs. 0.636) and on the original labels (0.873 vs. 0.820), and localizes each mismatch it reports to a specific hypothesis, conclusion, or scope. FYAN also built ODENumLib, a 9,355-line Lean library for the numerical analysis of ordinary differential equation. --- ### Emergent Multi-View Geometry Through Self-Distillation Authors: David Nordström, Thibaut Loiseau, Vincent Lepetit, Michael Felsberg, Guillaume Bourmaud, Fredrik Kahl Published: 2026-09-30 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.39227v1 Over a century ago, Henri Poincaré argued that a motionless observer cannot acquire the notion of space. Yet, most visual representation learning methods operate on individual images, while those that leverage multiple views rely on RGB reconstruction, entangling geometry with appearance. We propose Poincar3, a self-supervised method that learns representations from multiple views through self-distillation instead of RGB reconstruction. We combine masked patch and image-level distillation with a teacher that observes additional views, enabling training from scratch without explicit 3D supervision. Poincar3 outperforms both previous single and multi-view self-supervised approaches such as DINOv3, MuM, and Muskie on correspondence estimation, camera pose estimation, and 3D reconstruction. Using a lightweight Poincaré adapter, we also find that our learned features encode camera motion more accurately than existing self-supervised representations. --- ### Argument Structure Prediction in Online Conversations: A Comparative Study of Modeling Paradigms and Task Architectures Authors: Siddharth Bhargava, Sara Tonelli, Patricia Martín-Rodilla, Javier Parapar Published: 2026-09-30 Categories: cs.CL, cs.IR arXiv: https://arxiv.org/abs/2609.39225v1 Argument structure prediction (ASP) constructs complete argument structures from discourse by identifying argumentative units and their relations. While recent work has explored diverse approaches---including unified neural models, multi-step pipelines, and prompt-based large language models (LLMs)---their relative trade-offs remain under-explored, particularly in dialogical settings. We present a systematic evaluation of ASP under strict schema constraints, comparing supervised fine-tuning and prompt-based LLMs across single- and multi-step task architectures, generating complete argument structures from dialogical input end-to-end. We benchmark them on three diverse dialogical corpora adapted from Inference Anchoring Theory into bipolar argument structures. Under a shared evaluation framework, we assess predictive performance, cross-domain generalization, schema compliance, and computational efficiency. Our results show that ASP remains a challenging task, with identifying argumentative relations emerging as the primary bottleneck, largely due to the implicit and context-dependent nature of dialogical argumentation. To facilitate future research, we release our data processing pipeline and end-to-end modeling framework for computational ASP on dialogical corpora. --- ### QATFactory: A Versatile, Deployment-Aligned Framework for Quantization-aware Training and Distillation of LLMs Authors: Weili Xu, Jisen Li, Yuqing Jian, Chenxi Li, Zhizhou Sha, Yifan Yu, Qingyang Wu, Chenfeng Xu, Zhongzhu Zhou, Tianyi Zhang, Ben Athiwaratkun Published: 2026-09-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.39223v1 Large language model (LLM) inference is increasingly moving toward lower precision to realize the throughput of hardware accelerators, but aggressive post-training quantization (PTQ) can degrade model quality. We present QATFactory, an open-source framework for deployment-aligned quantization-aware distillation (QAD) and reinforcement learning (QARL). QATFactory simulates deployment-time quantization while performing matrix multiplications in BF16, allowing models to adapt to quantization noise without requiring training hardware that natively supports the target format; for example, it supports NVFP4 training on H100 GPUs, which lack FP4 Tensor Cores. The framework supports NVFP4, MXFP4, and llama.cpp's Q4_K format; dense and mixture-of-experts models; and both full-parameter and LoRA-based training. It exports checkpoints directly to vLLM and llama.cpp without an additional lossy conversion step or added inference overhead. With QATFactory, we conduct extensive experiments on models ranging from 8B to 230B parameters and evaluate exported checkpoints in production inference engines. Across models and formats, QAD consistently improves deployed-model quality over strong PTQ baselines. On Qwen3.5-9B, QAD achieves average benchmark accuracies of 68.9% under NVFP4 and 66.0% under MXFP4, outperforming the best PTQ results of 65.4% and 56.4%, respectively. Through our experiments, we found that although both FP4 formats quantize weights and activations at deployment, the best training strategy is format-dependent: NVFP4 generally performs better when only weights are quantized during training, whereas MXFP4 benefits from quantizing both weights and activations. At a fixed training token budget, training on fewer 32K sequences improves average accuracy by 1.9 points over training on more 4K sequences. We release the complete QATFactory training code and the resulting checkpoints. --- ### DC-SAE: Deep Compression Semantic Autoencoder for Faster Diffusion Convergence Authors: Xu Huang, Ye Huang, Zijun Liao, Yuwei Niu, Xiaojie Li, Menghan Zhou, De Wen Soh, Xiaotong Li, Daquan Zhou Published: 2026-09-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.39222v1 High-compression tokenizers are essential for scaling latent image generative models. However, aggressive compression creates a fundamental tradeoff between reconstruction fidelity and generation efficiency: high compression image encoder always increases the learning difficulty of diffusion training, resulting in slow model convergence. Recent representation autoencoders speed up the diffusion training by improving the latent feature's expressive capability by replacing VAE encoders with pretrained semantic encoders, yet they are typically limited to moderate compression and lose pixel-level details necessary for faithful reconstruction. To achieve both high compression and fast diffusion training, we propose DC-SAE, a Decoupled Compact Semantic Autoencoder designed for high-compression image generation with accelerated diffusion model convergence. DC-SAE consists of two key components: (1) a macro-level architecture design that leverages semantic encoders to enable higher compression ratios, and (2) a pixel-level encoder that preserves low-level details, ensuring high-fidelity image reconstruction. We empirically demonstrate that DC-SAE performs strongly on image generation tasks, achieving both compact latent representations and efficient training dynamics. Specifically, on the ImageNet dataset with $512 \times 512$ resolution, DC-SAE achieves $32\times$ spatial compression, with 29.79 PSNR and 3.37 gFID, substantially outperforming the previous state-of-the-art high-compression tokenizer baselines DC-AE by 13.5% and 54.9% on PSNR and gFID, respectively, maintaining comparable throughput and faster diffusion model training convergence. Beyond class-conditional generation, a $1.6$B-parameter DiT using DC-SAE achieves 0.84 on GenEval and 86.007 on DPG-Bench for text-to-image generation at $1024\times1024$ resolution. --- ### Learning Process Rewards via Reasoning State Propagation Authors: Kai Gan, Zi-Hao Zhou, Bo Ye, Jian Zhao, Min-Ling Zhang, Tong Wei Published: 2026-09-30 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.39220v1 Process reward models (PRMs) have demonstrated notable effectiveness in test-time scaling and reinforcement learning by providing fine-grained signals for evaluating intermediate reasoning states, but their training relies heavily on costly process annotations. A natural way to alleviate this dependence is to complement limited process supervision with scalable outcome supervision. However, existing PRMs often model reasoning prefixes independently, providing no explicit mechanism for effectively using final outcome to guide the learning of intermediate reasoning states. We introduce Reasoning State Propagation (RSP), which represents each reasoning prefix with a binary validity state and models transitions between successive states across the reasoning trajectory. Specifically, RSP predicts a break probability that a valid state becomes invalid and a repair probability that an invalid state returns to valid. By propagating these transitions, RSP connects intermediate states to the final state, allowing process annotations to supervise intermediate states while outcome labels supervise the final state and can provide learning signals to preceding steps. Across reasoning search, response selection, and reinforcement learning, RSP consistently outperforms representative PRM baselines, with average improvements over Qwen2.5-Math-PRM of 5.6% in beam search and 2.1% in reinforcement learning. --- ### In a Streaming World, Should You Stand Still? A Comprehensive Benchmark of Anomaly Detection in Streams Authors: Magali Parrino, Antoine Ajenjo, Emmanuel Remy, Pierre Stephan, Pierre Senellart, Paul Boniol Published: 2026-09-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.39215v1 Time series anomaly detection (TSAD) is increasingly deployed in streaming settings, where data arrive sequentially and may exhibit non-stationarity. As a result, several works from the recent literature propose streaming anomaly detection methods that rely on incremental updates to adapt over time. However, most of these approaches originate from the streaming outlier detection literature and largely ignore core characteristics of time series anomalies. Moreover, their empirical evaluation is typically conducted on synthetic or small-scale benchmarks with limited diversity, making it unclear whether streaming methods are truly advantageous in realistic TSAD scenarios. In this work, we carry out the first large-scale experimental study comparing streaming and static TSAD methods under a unified streaming evaluation benchmark. We consider a realistic setting in which an initial batch of data is available for model training, followed by online evaluation of both detection accuracy and computational efficiency. In addition, we propose a distribution-drift dataset of real time series, called TSB- drift, to isolate scenarios where streaming updates are theoretically justified. Our results show that, contrary to common assumptions, static TSAD methods significantly outperform streaming approaches in most streaming settings. Such finding highlights a critical gap between the design of existing streaming methods and the requirements of modern TSAD, and calls for a rethinking of how streaming capabilities should be integrated into TSAD. --- ### Minimax Additive Regression under Unknown Dependent Designs Authors: Baptiste Ferrere, Fabrice Gamboa, Jean-Michel Loubes Published: 2026-09-30 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2609.39212v1 We study additive regression under a potentially non-product random design on $(0,1)^d$, allowing the dimension $d$ to grow with the sample size $n$. We introduce coupled smoothness classes that separately control the regularity of the marginal densities and the density-weighted additive components. To handle dependence, we adapt a Riesz-basis construction for functional ANOVA models and establish compatibility bounds with constants independent of the dimension under uniform bounds on the joint density. We construct thresholded least-squares estimators and establish matching minimax upper and lower bounds for prediction with known or unknown marginal densities, under suitable dimension-growth conditions. When the marginal densities are at least as smooth as the weighted components, the unknown-density problem attains the known-density minimax rate. When the densities are less smooth, their regularity determines the minimax rate over the coupled class. Finally, we show that the centered additive components can be recovered at the same aggregate upper rate, without an additional order of error. --- ### UniAE-MoE: A Unified Audio Encoder via Mixture of Experts Authors: Shengbo Cai, Zhisheng Zhang, Zichao Nie, Jing Peng, Jingran Xie, Zhiyong Wu Published: 2026-09-30 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2609.39199v1 Large Audio Language Models (LALMs) rely on effective audio encoders for multi-task performance. We introduce UniAE-MoE, a unified audio encoder designed to model cross-domain audio representations and achieve outstanding downstream understanding performance via a Mixture-of-Experts (MoE) architecture. Specifically, we explore mainstream audio encoders and integrate those from Qwen2-Audio and Audio-Flamingo 3, which demonstrate superior downstream capabilities. To facilitate effective model fusion, we improve our encoder using SwiGLU with shared experts to decouple encoder networks, and we further introduce a two-stage instruction-tuning strategy to better adapt the model to diverse downstream tasks. Moreover, we propose the task-specific data scaling (TSDS) technique to enhance \tool's understanding capabilities. On the XARES-LLM benchmark, UniAE-MoE attains a score of 0.802, achieving state-of-the-art performance. It also delivers top-tier performance in the official Interspeech 2026 Audio Encoder Capability Challenge, further demonstrating robust generalization across diverse audio tasks. Together, these results validate the effectiveness of \tool for unified audio understanding across speech, music, and general audio domains. --- ### Uruqi: Learning Spatial Cognition from Visual Experience Authors: Shichao Li, Meiqi Wang, Fei Su, Zhicheng Zhao Published: 2026-09-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.39195v1 Spatial intelligence requires maintaining a coherent understanding of the world as the embodied agent moves. Like humans, the agent must use its own motion to interpret changes across observations and update object locations and spatial relations accordingly. Despite spatial post-training having substantially broadened the spatial intelligence of vision-language models (VLMs), they still struggle with two atomic spatial capabilities: tracking self-motion and mapping the surrounding world during motion. To address this gap, we provide dense multi-turn supervision over interleaved atomic capabilities within each training episode, mimicking the visual experience of a continuously moving agent that reasons as it observes. To scale this up, we synthesize 11,738 motif-driven camera trajectories over a broad range of 3D scenes, supporting self-motion tracking, persistent object mapping, and rich spatial operations within each visual experience. By training models to reason over these atomic questions, our URUQI$_{\mathrm{Syn}}$-8B improves accuracy from 15.84% to 47.73% on our Uruqi benchmark comprising 52k questions across 2.7k episodes. URUQI-SI-Mix-8B further reaches 50.41%, comparable to the 50.08% achieved by GPT-6 Astra. Trained solely on our synthesized data, URUQI$_{\mathrm{Syn}}$-8B achieves an average relative accuracy improvement of 17.13% over its InternVL3-8B backbone across three external spatial benchmarks. These results highlight continuous visual experience as a scalable source of supervision for developing spatial cognition in VLMs. --- ### Importance-Aware Feature Sparsification for Wireless Split Learning Authors: Bumjun Kim, Yoon Huh, Wan Choi Published: 2026-09-30 Categories: cs.LG, eess.SP arXiv: https://arxiv.org/abs/2609.39194v1 Wireless split learning (SL) reduces on-device computation by offloading upper layers to a server, yet transmitting high-dimensional intermediate features at each iteration remains a major communication bottleneck. Existing methods select features at the client side using task-agnostic criteria such as magnitude, statistics, or clustering, which increases client-side processing and often degrades accuracy under non-independent and identically distributed (non-i.i.d.) client data. We propose importance-aware class-balanced sparsification (ICS), a lightweight approach in which the server ranks feature channels using Grad-CAM-based scores obtained from the true-class logit during backpropagation. The per-class scores are aggregated into a class-balanced, label-agnostic importance vector that mitigates head-class bias under label skew, and each client reuses this vector in the next round to retain the top-$N$ feature channels, incurring no additional client-side forward or backward passes. We further derive a non-asymptotic convergence bound that isolates the sparsification-induced error and characterizes how the sparsification ratio and mini-batch size jointly affect convergence under a fixed communication budget, and we analyze the communication and computational overhead of ICS against representative baselines. Beyond sequential CNN-based SL, we extend ICS to parallel split learning and to transformer-based models. Experiments show that ICS consistently outperforms the baselines, with larger gains under severe non-i.i.d. partitions. --- ### Dynamics to decision: A mathematical theory of Lyapunov spectra and decision boundaries in deep classifiers Authors: Shirin Panahi, Amirhossein Nazerian, Ali Pezeshki Published: 2026-09-30 Categories: cs.LG, eess.SY, math.DS arXiv: https://arxiv.org/abs/2609.39190v1 A deep classifier is defined not only by the decision it produces, but also by the sequence of transformations through which that decision is formed. Treating this evolution as a dynamical system across layers provides a natural framework for asking how decision geometry emerges through depth and how far back we can trace a boundary's dynamical signature. We model a feed-forward classifier as a finite, nonautonomous discrete dynamical system, with layers playing the role of discrete time steps. We study the Finite-Time Maximum Lyapunov Exponent (FTMLE) of the data samples' dynamical trajectory through depths of the classifier. The FTMLE measures the rate of convergence/divergence of nearby trajectories. We move the observation endpoint backward from probabilities to logits and then to hidden representations. For Gaussian classes, we prove that probability-level FTMLE carries a clear geometric signature of the decision boundary, with its dominant direction aligned with the boundary normal. Moving one step backward to the logits, we prove this relationship is no longer universal but depends critically on how the classifier is trained, particularly on the choice of loss function. Moving further backward to the hidden representation, the connection becomes more conditional: boundary-related FTMLE can persist, but only under identifiable structural conditions. We propose geometry-aware fine-tuning for restructuring the classifier's hidden FTMLE, and propose conditions for guaranteed concentration of high hidden FTMLE near the decision boundary. Through our numerical results, we show the generality and validity of our theoretical results. Understanding the evolution of data samples as traveling through the layers of classifier provides a principled foundation for identifying where boundary-relevant sensitivity emerges and for developing layer-aware regularization strategies. --- ### ViLegalExpert: A Large-Scale Benchmark for Vietnamese Legal Retrieval and Question Answering from Real-World Consultations Authors: Dat Tien Nguyen, Nghia Hieu Nguyen, Anh Thi-Hoang Nguyen, Dung Ha Nguyen, Kiet Van Nguyen, Ngan Luu-Thuy Nguyen Published: 2026-09-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.39189v1 Trustworthy Legal AI requires systems that can answer legal questions while grounding their responses in authoritative sources. However, existing Vietnamese legal benchmarks provide limited coverage of real-world legal consultations. We introduce \textbf{ViLegalExpert}, a large-scale benchmark constructed from authentic citizen--lawyer consultations, containing over \textbf{172K} questions across \textbf{34 legal domains}, together with professional answers and expert-verified legal evidence. ViLegalExpert supports legal information retrieval, extractive QA, and abstractive QA. Experiments with representative retrieval methods and language models reveal substantial challenges in evidence retrieval and grounded answer generation. While pretrained models perform strongly on QA, hybrid retrieval achieves the best retrieval performance. These results demonstrate the difficulty of mapping naturally expressed legal questions to authoritative provisions and establish ViLegalExpert as a challenging benchmark for reliable Vietnamese Legal AI. --- ### Attention Function as an Intrinsic Inductive Bias: How Models' Behavior Diverges in Novel Contexts Authors: Dong Gyun Kang, Megha Thukral, Kwangsoo Kim Published: 2026-09-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.39188v1 Developmental psychology holds that certain priors are given to infants prior to experience rather than induced from data, and that the influence of such priors is suppressed under strong, well-constrained conditions but reasserts itself under weak ones. We ask whether an analogous principle holds for the Transformer: can the activation function given to attention heads serve as an intrinsic inductive bias? We propose Mixture of Function Attention (MoFA), a parameter-free modification to multi-head attention that fixes a ratio of softmax and sigmoid heads before training. Across five ratios, a 124M-parameter GPT-2 model, and five seeds, we find that this given ratio has little effect in-distribution -- differences between ratios are statistically negligible for moderate mixtures and remain small even at the extremes -- but its influence re-emerges sharply under zero-shot distribution shift across 15 out-of-distribution domains. Perplexity gaps between ratios widen by more than an order of magnitude on several domains, and the best-performing ratio tracks a single axis of domain structure, separating short, informal text (softmax-favoring) from technical, long-form text (sigmoid-favoring), that explains 78.3% of the variance in domain response. This reorganization is visible at the head level: sigmoid heads show an accelerating drop in attention entropy as their ratio increases, while softmax heads respond more modestly, yielding a consistent division of labor between the two head types. Our results suggest that activation choice functions as a given prior whose influence is masked in-distribution and re-emerges out-of-distribution. --- ### Low-Discrepancy Dither for Quantized Recurrent State Caches Authors: Snigdha Chandan Khilar Published: 2026-09-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.39185v1 Mamba-style and hybrid language models compress their past into a fixed-size recurrent state that is rewritten at every generated token. Storing this state in low precision saves memory bandwidth, but every rounding error is fed back into the next update and can accumulate over long generations. Production systems round the state stochastically; we ask which rounding rule such caches should use. We find that a deterministic golden-ratio Weyl dither, which needs no random numbers, consistently brings the quantized model closer to the full-precision one than stochastic rounding, across pure and hybrid models, storage formats, and long decoding horizons, at no extra cost. Round-to-nearest behaves differently: because it discards small updates, its error keeps growing, so it can look best in short evaluations yet falls far behind over long generations. A discrepancy analysis explains this ordering, and we document implementation pitfalls that silently remove the benefit. --- ### Fiber-Resolved Microstructure Quantification from Multi-Shell Diffusion MRI using Detection Transformers Authors: Sebastian Endt, Marcus Wirth, Johannes Reinhold Schlund, Marion Irene Menzel Published: 2026-09-30 Categories: cs.CV, cs.LG, physics.med-ph arXiv: https://arxiv.org/abs/2609.39184v1 Fiber orientation and compartmental microstructure are central to the characterization of white matter tissue in diffusion MRI, yet existing methods either resolve fiber orientations without quantifying microstructure, or quantify microstructure while assuming a fixed number of compartments and a single fiber direction. Nonparametric approaches that recover both require tensor-valued diffusion encoding and computationally expensive Monte-Carlo inversion of an ill-posed inverse Laplace transform. We propose to reframe this problem as an object detection-like task, adopting the Detection Transformer (DETR) architecture to jointly predict mean diffusivity (MD), fractional anisotropy (FA), main fiber direction, and signal fraction for a variable number of compartments per voxel from standard multi-shell diffusion MRI with linear encoding. Hungarian matching during training resolves permutation invariance across compartments. We introduce mean Average Precision as a reproducible benchmark metric. Evaluated on synthetic test data with up to five compartments per voxel, our model achieves $R^2=0.95$ for MD, $R^2=0.88$ for FA, and a median angular error of 4.2°, with performance scaling naturally with compartmental signal fraction. --- ### Aligning Thoughts with Answers: Probability Rewards to Tame Thinking Drift Authors: Pengzhan Sun, Shiu-hong Kao, Shijie Li, Yongyi Su, Junbin Xiao, Arjun Reddy Akula, Angela Yao Published: 2026-09-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.39183v1 This paper studies \textbf{thinking--answer consistency} in vision-language models. We focus on Visual Intention Grounding, where a model infers a target object based on a human intention query and predicts a bounding box. We reveal that previous IoU-based reinforcement learning (RL) frameworks suffer from ``thinking drift'', where the model produces a correct bounding box, despite having an incorrect reasoning process pointing to a different target object. Thus, we propose \textbf{Rita} (\textit{ReInforcing Thinking--Answer consistency}) as a novel RL paradigm to tame the drift. Specifically, Rita introduces two reasoning-label-free RL rewards, constructed from the conditional probability of reference answers: a \textbf{thinking reward} and a \textbf{consistency reward}. It also adopts a difficulty-aware \textbf{data filtering} strategy that selects informative easy-to-medium samples for RL using rollout error rate and reward variance. Extensive experiments on EgoIntention and the new RefEgo-Int benchmarks show that Rita performs consistently superior to the supervised finetuning approaches and vanilla RL-finetuned frameworks. --- ### MEND: Label-Free Detection, Localisation, and Correction of Latent Hallucination in World Models Authors: Ali J Alrasheed, Aryan Yazdan Parast, Basim Azam, James Bailey, Naveed Akhtar Published: 2026-09-30 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.39182v1 World Models are appearing as the next major frontier in computer vision. However, their robustness is currently largely unexplored. We identify the phenomenon of hallucination in latent World Models: given a state and an action, the predicted next latent can decode to a scene that never occurs. Because the prediction is statistically ordinary and is fed back autoregressively by the model, the error is both silent and compounding. We study whether such latent hallucination can be detected, localised, and corrected at inference time, on a frozen self-supervised world model in the absence of ground-truth error labels. We introduce Masked Empirical-Bayes Neural Denoising (MEND), a single conditional score network trained by denoising score matching on real transitions, whose score field serves three roles: its magnitude detects hallucination, its per-token field localises it to specific image patches, and it defines an inference-time correction direction. On two navigation environments MEND detects hallucination with an AUROC of up to 0.80 without using actions, exceeding a single-Gaussian density baseline while also localising the error (per-token AUPRC up to 0.87) and correcting it, all from one score field. Our correction reliably reduces single-step latent error and improves predictions. We identify that a part of the error is tangent to the data manifold, hence, we focus on detection and localisation while highlighting promises of the correction. --- ### Exploiting Vulnerabilities: Universal Adversarial Attacks on Vision-Language-Action Models in Robotics Authors: Songhua Yang, Ziyu Liu, Yuanwei Liu, Xuetao Li, Xuanye Fei, He Huang, Zheng Wang, Miao Li Published: 2026-09-30 Categories: cs.RO, cs.CR, cs.CV arXiv: https://arxiv.org/abs/2609.39178v1 Recently, Vision-Language-Action (VLA) models have revolutionized robotic manipulation by seamlessly integrating visual perception, language understanding, and action generation in an end-to-end learning framework. However, since these models are designed to interact directly with the physical world and humans, their security is critical, and even small vulnerabilities can lead to catastrophic failures. In this work, we propose the Universal Adversarial Object, a sphere with optimized surface texture that significantly degrades task success rates when placed within the robot's field of view. Specifically, our approach introduces a multi-level attack framework that jointly disrupts trajectory planning, task execution, and action control. We validate our method in both simulated and real-world robotic settings. Experimental results demonstrate that the adversarial object reduces the average task success rates by 31.2%-39.9% for two representative VLA models (Pi0 and RDT), with success rates dropping to near zero in complex scenarios. Index Terms--Vision-Language-Action models, adversarial attack, robotic security, universal adversarial object --- ### Whitening Improves Robustness to Spurious Correlations in Linear Probes Authors: Floris Holstege, Bram Wouters, Noud van Giersbergen, Cees Diks Published: 2026-09-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.39177v1 Deep neural networks tend to rely on simple features that may be spurious and thus fail to generalize. We study this problem in the setting of linear probes, where a (generalized) linear model is fitted on the representations of a (pretrained) model. We use the connection of these models to the max-margin classifier, and show they favor directions associated with large eigenvalues of the covariance matrix. Whitening removes this preference by equalizing the eigenvalues of the covariance matrix. This observation motivates whitening as a preprocessing step that can reduce reliance on spurious correlations without requiring prior knowledge of their presence or labeled data. We examine the effect of whitening on a synthetic data-generating process and standard spurious correlation benchmarks, and find that it improves robustness. We also find that whitening can improve robustness when added to existing approaches. --- ### Asymptotic Properties of Support Vector Machines in High-Dimension, Low-Sample-Size Settings under a Spiked Model Authors: Yugo Nakayama Published: 2026-09-30 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2609.39173v1 In this paper, we consider asymptotic properties of the support vector machine (SVM) in high-dimension, low-sample-size (HDLSS) settings under a spiked model. The existing theory of the SVM in the HDLSS context relies on the geometric representation of HDLSS data, which requires that the eigenvalues of the covariance matrices are not dominant. We first show that the geometric representation does not hold under the spiked model. We show that the Gram matrix of HDLSS data converges in distribution to a random matrix, namely, the HDLSS data converge to a random configuration in a finite-dimensional space whose dimension is given by the number of the spikes. We show that the misclassification rates of the SVM do not tend to zero, that is, the SVM does not hold the consistency property. We also show that the bias-corrected SVM (BC-SVM) does not give preferable performance in this setting because the bias term itself should be modified. In order to overcome such difficulties, we propose a spike-corrected SVM (SC-SVM). We show that the SC-SVM holds the consistency property when the sample size goes to infinity, and that the growth of the sample size is essential in the sense that any projection-based procedure fails when the sample size is fixed. Finally, we check the performance of the classifiers by numerical simulations. --- ### A Width-Matched Comparison of Hybrid Quantum-Classical Self-Supervised Learning for Fingerprint Recognition Authors: Maria S. Edwards, Kidwell Dlamini, Pin-An Lin, Wen-Hsien Hsu, Wen-Chieh Fang Published: 2026-09-30 Categories: quant-ph, cs.LG arXiv: https://arxiv.org/abs/2609.39172v1 Fingerprint recognition is a widely deployed biometric, but supervised training requires large labeled enrollment sets. Self-supervised learning (SSL) removes this requirement, and hybrid quantum-classical models have been proposed to enrich the learned representations. Prior quantum SSL studies consider a single contrastive objective, so it is unclear whether reported benefits depend on the objective or can be attributed to the quantum circuit. We insert the QuFeX quantum feature-extraction module into three SSL frameworks, the contrastive SimCLR and MoCo v2 and the non-contrastive BYOL, and compare each hybrid with its classical counterpart at matched representation width (8 features, equal to 8 qubits) on the SOCOFing fingerprint dataset, with a CIFAR-10 control, using k-nearest-neighbor identification on encoder features. In single-run experiments the hybrid scores clearly higher for both contrastive objectives, whereas for BYOL a multi-seed analysis shows no reliable difference, suggesting that any benefit depends on the SSL objective. A hardware-efficient circuit (QNet) does not show the same gain. We examine whether the gains can be attributed to the quantum circuit, considering circuit architecture, trainable parameter count, nonlinearity, and the classical simulability of 8-qubit circuits. --- ### Reinforcing Multimodal Reasoning via Token-Level Perception-Grounded Advantage Estimation Authors: Zhihan Zhang, Lizi Liao Published: 2026-09-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.39168v1 Reinforcement Learning with Verifiable Rewards (RLVR) has improved the reasoning capabilities of Multimodal Large Language Models (MLLMs), yet existing frameworks rely on coarse, sequence-level reward signals that lack the fine-grained supervision over the visually-grounded steps within a multimodal reasoning chain. We investigate this gap through the lens of two token-level metrics: visual dependency (i.e. how much a token's prediction relies on the input image features) and predictive entropy. Our empirical analysis reveals two key findings: (1) correct reasoning chains exhibit a markedly sharper entropy reduction as visual grounding intensifies, compared to incorrect ones; (2) pivotal tokens, those whose misprediction triggers reasoning collapse, are statistical outliers in the joint distribution of visual dependency and predictive entropy derived from correct chains. Motivated by these findings, we propose token-level perception-grounded advantage estimation (TPAE), which estimates token-level advantages by measuring each token's statistical consistency with the vision-entropy patterns of correct rollouts. TPAE leverages this granular score to modulate the sequence-level advantage, producing a fine-grained supervision signal that can be integrated into various RLVR frameworks. Extensive experiments on seven benchmarks show that TPAE consistently outperforms leading strong baselines, yielding more stable and efficient optimization for multimodal reasoning. The code is publicly available at https://github.com/Zhihan72/TPAE. --- ### Beyond the Remembered World: Predictive 4D Belief for Persistent Navigation in Evolving Worlds Authors: Mingjian Gao, Zhaocheng Li, Haoyang Huang, Wenqiao Zhang, Yingjie Niu, Hao Zhou, Chao Li, Juncheng Li, Siliang Tang, Yueting Zhuang Published: 2026-09-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.39166v1 Persistent spatial memory enables embodied agents to navigate familiar environments across repeated visits. However, targets may move while unobserved, including during navigation, making remembered locations unreliable by the time an agent arrives. Despite advances in memory retrieval and state prediction, accounting for continued hidden world evolution and revising beliefs under limited visibility remain challenging. We study Evolving-World Navigation, where agents infer target locations from intermittent observations, predict their states at inspection time, and revise beliefs using visual evidence. We propose EvolvingNav, which constructs a time-indexed belief from timestamped 3D object histories through a structured persistence-relocation model. The belief distinguishes persistence at the last observed location from relocation to alternative locations and retains probability mass outside the known candidate set. An event-driven filter propagates the current belief as time elapses, forecasts target occupancy at candidate inspection times, and incorporates new RGB-D evidence. Negative observations downweight location hypotheses according to calibrated, visibility-conditioned detection probabilities, while evidence tracking prevents repeated use of the same observations. A frozen, zero-shot vision-language controller uses the updated belief to choose actions and replan. We further introduce EvoWorld-Bench, a benchmark grounded in human activity traces, comprising 54 scenes and 803,680 tasks with controlled changes before and during navigation. In simulation and real-robot experiments, EvolvingNav improves navigation success and search efficiency over the evaluated baselines. Paired experiments show the clearest gains under learnable temporal patterns, while ablations demonstrate the value of preserving uncertainty and incorporating visibility-aware evidence. --- ### QuanVI: Score-based Variational Inference via Quantum Maximally Mixed States Authors: Yuchen Cong, Zerui Tao, Chao Li, Zhe Sun, Qibin Zhao Published: 2026-09-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.39164v1 Score-based variational inference (VI) provides an alternative to Kullback--Leibler (KL)-based VI by minimizing the Fisher divergence between the variational distribution and the target. A prior score-VI approach formulates this optimization as an eigenvalue problem, with the variational distribution constructed from low-energy eigenstates. However, this eigenvalue-based formulation faces two high-dimensional obstacles: an intractably large parameter count due to exponential scaling and non-uniqueness of individual eigenvectors in degenerate or nearly degenerate low-energy subspaces. We propose QuanVI, a scalable quantum-inspired algorithm that combines a mixed-state density-operator formulation with a quantum tensor network (QTN) parameterization using the matrix product operator (MPO) structure. In degenerate low-energy subspaces, the density-operator formulation represents the subspace by its maximally mixed state rather than relying on a non-unique individual eigenvector, while the QTN parameterization compresses the density operator to avoid exponential parameter growth. Experiments and ablations show that QuanVI agrees with exact solutions in low dimensions and scales to high-dimensional synthetic and Bayesian posterior-approximation benchmarks, including challenging non-Gaussian targets. --- ### Training-Free Affinity Fusion of Neural and Embedding-Based Speaker Diarization Authors: Yehoshua Dissen, Joseph Keshet, Eduard Golshtein Published: 2026-09-30 Categories: cs.SD, cs.LG arXiv: https://arxiv.org/abs/2609.39162v1 Speaker diarization systems based on speaker embeddings and neural diarization exploit complementary forms of speaker information, but their intermediate representations are not directly compatible. We introduce Training-Free Affinity Fusion (TFAF), which integrates the speaker structure inferred by a neural diarizer into an embedding-based diarization system. The neural speaker partition is used to condition local speaker representations, from which we construct a continuous affinity matrix and combine it with the embedding-based acoustic affinity before a single global clustering step. The method requires no additional training, shared embedding space, speaker-label alignment, or hard transfer of the neural diarizer's speaker count. Experiments on AMI and CALLHOME show consistent DER improvements over both constituent systems; on AMI, fusion also improves speaker-attributed transcription. Ablations show that the neural speaker partition accounts for most of the gain, while retaining the continuous embedding-based affinities provides additional benefit over hard partition fusion. --- ### TripleFlow: Training-Free Video Object Removal by Bridging Residual Editing and Native Generation Authors: Songhe Wang, Lifu Wei, Shuolin Xu, Charles A. Kamhoua, David Miller Published: 2026-09-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.39157v1 Video object removal presents a uniquely difficult editing challenge. Because a removal prompt specifies only what to erase rather than what to generate, the model must infer and reconstruct a highly specific occluded background entirely from the surrounding context. Existing training-free methods struggle with this because their editing mechanisms act primarily as localized erasers. They fail to actively synthesize the missing background details and often leave behind ghosting artifacts. To solve this, we propose TripleFlow, a training-free framework that tightly couples erasure and generation. It coordinates a source flow, a residual flow, and a synthesis flow throughout the entire process. By reusing a single target prediction, the residual flow isolates and suppresses the object, while the synthesis flow independently reconstructs the occluded background. Crucially, TripleFlow injects this newly synthesized background back into the editing trajectory at every step. This continuous feedback loop ensures that the generated structures actively guide the removal process, achieving seamless completion that is spatiotemporally consistent with the unedited scene. Extensive evaluations across five challenging benchmarks demonstrate that TripleFlow establishes a new state-of-the-art, significantly outperforming existing baselines in both reconstruction fidelity and temporal consistency. --- ### DAGent: Evaluate-then-Grow Planning for Deep Research Agents Authors: Hanwen Liu, Yuanfu Sun, Qiaoyu Tan Published: 2026-09-30 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.39154v1 Deep research tasks require agents to navigate large knowledge spaces, synthesize evidence across many sources, and adapt their plans as findings emerge. Directed acyclic graph (DAG)-based multi-agent systems suit this setting because they support parallel execution and isolate each sub-task within a focused dependency context. Yet existing DAG-based agents instantiate a task-level plan before execution and repair the graph only after failures or missing evidence are observed. This Plan-then-Patch strategy is brittle for deep research: the system commits most strongly when its evidence is weakest, and later revisions waste computation on branches that should not have been planned. We propose DAGent, a DAG-based multi-agent framework with Evaluate-then-Grow incremental planning: an Orchestrator grows the task graph one batch at a time, conditioning each expansion on confidence and uncertainty signals from completed nodes. A hierarchical context layer propagates compact QueryDocs by default while preserving full execution traces for on-demand recall. The recorded DAG topology admits structural RL signals that outcome-only recipes cannot define; DAGRPO, a GRPO adaptation, injects topology-conditioned credit on Executor rollouts and a structural compliance regularization on Orchestrator plans. Across BrowseComp-Plus, GAIA, and xbench-DeepSearch, DAGent surpasses the strongest open-source baseline by 5.3 / 5.8 / 2.0 points at the Qwen3-235B-A22B scale, and the lead replicates across four open-source backbones and extends to GPT-5 at 327K context. At the Qwen3-8B scale, DAGRPO improves over a same-budget outcome-only GRPO baseline by 3.0 average Pass@1 points. A same-architecture comparison shows that evidence-conditioned planning reaches higher accuracy at lower per-task token, tool-call, and step footprints than its Plan-then-Patch counterpart. Code: https://github.com/hanwenliu6825/DAGent --- ### Linear Recurrent Memory Suffices to Distil a World-Model Policy for Robot Air Hockey Authors: F. Olivia Fan, Oliver Obst Published: 2026-09-30 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2609.39151v1 Does memory-dependent control need nonlinear recurrent dynamics? We study simulated air-hockey defence under temporary loss of puck tracking. A DreamerV3 teacher outperforms a memoryless policy under tracking loss, while resetting the teacher's recurrent state sharply reduces performance, which demonstrates that the task requires memory. We distil this teacher into compact recurrent policies with a 64 dimensional state, with a combination of a diagonal linear recurrence and an optional rank-$k$ nonlinear innovation while retaining nonlinear observation encoders and action heads. Across five matched seeds, the purely linear recurrent model ($k=0$) matches both the GRU baseline and the teacher throughout the tested range of tracking loss. Increasing nonlinear innovation rank providing no measured benefits. This result is obtained on a fresh test split, which will be only opened after all models and analyses are frozen. The linear model requires fewer recurrent parameters and less computation than GRU, but performs comparably. These results suggest that, for this memory dependent control task, nonlinear representation learning around a simple linear memory mechanism can be sufficient, and that nonlinear recurrent dynamics are not necessarily required. These conclusions are limited to the simulated task, teacher, state dimension, and blackout horizon considered here, and to policies whose observation encoder and action head remain nonlinear. --- ### OP-CAD: On-Policy Clean-Audio Distillation for Robust Audio-Visual Reasoning Authors: Xingming Shui, Dapeng Chen, Bowei Liu, Jingqi Tian, Minfu Li, Kun Yi, Jiapeng Hong, Yansong Tang Published: 2026-09-30 Categories: cs.CV, cs.SD arXiv: https://arxiv.org/abs/2609.39150v1 Omni-modal large language models deployed in real-world environments encounter external noise that can interfere with their perception and understanding of multimodal inputs. We study their robustness in audio-visual understanding, focusing on question answering under environmental noise and competing speech. The challenge is to resist acoustic interference while preserving useful audio evidence. On-policy distillation provides dense teacher feedback on student-generated responses, but uniform token weighting does not explicitly prioritize positions affected by acoustic interference. We introduce OP-CAD (On-Policy Clean-Audio Distillation), a curriculum-based privileged self-distillation framework for robust audio-visual understanding. Training progresses from mild to severe environmental noise and competing speech, with selective token-level supervision at each stage. The student generates responses from corrupted audio-visual input, while a frozen teacher uses clean audio and the verified answer to supervise the same response prefixes. To allocate this supervision, OP-CAD compares teacher predictions under clean, corrupted, and visual-only contexts without revealing the answer. These matched comparisons measure sensitivity to audio removal and corruption; a bounded weighting rule emphasizes positions identified by either signal while retaining supervision throughout the response. OP-CAD outperforms the compared methods across all evaluated noise conditions. Paired analyses further show improved preservation of clean-correct answers under strong interference, with no observed aggregate clean-accuracy penalty. These results demonstrate the value of directing clean-teacher supervision toward acoustically sensitive predictions for robust audio-visual reasoning. --- ### Rep2Skill: Representation-Guided Skill Self-Evolution for LLM Agents Authors: Kaixing Zhang, Changming Li, Yingdong Shi, Zheng Zhang, Kaitao Song, Wenjie Shi, Jingang Wang, Kan Ren Published: 2026-09-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.39149v1 Textual skills enable large language model (LLM) based agents to accumulate reusable procedural knowledge without updating model parameters. Yet existing skill evolution remains largely confined to the text space: an optimizer must diagnose success and failure patterns, and revise skills solely from long execution trajectories and sparse task outcomes. This text-only paradigm leaves the agent's internal representations, which contain rich records of its evolving execution state, outside the skill optimization loop. We ask whether an agent can improve its external textual skills by reflecting on its own internal representations. We introduce Rep2Skill, a representation-guided framework for self-evolution on agent skills. Specifically, upon the collected agent rollouts, Rep2Skill models their internal model representation trajectories to localize turns that deviate from successful execution dynamics, and it further interprets these signals alongside the execution contexts as actionable textual feedback for targeted skill revision. Experiments on two agent environments with two open-source LLMs show that Rep2Skill consistently outperforms text-only approaches in the self-evolution setting, where the same LLM serves as both executor and optimizer without a stronger external model. This establishes a promising direction moving agent self-improvement beyond text-only reflection. --- ### Do Self-Evolving Skills Generalize to Held-Out Tasks? Authors: Xihao Piao, Zifeng Wang, Zhen Chen Published: 2026-09-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.39148v1 AI agents can externalize what they learn from past tasks into reusable \emph{skills}, such as procedures, checklists, code, or other executable artifacts, that can be retrieved and reused when solving new tasks. Self-evolving skill methods keep rewriting these skills after each round of practice on training tasks, and the skill is then used on new tasks of the same kind. We ask a question: does the improvement a skill shows on its training tasks carry over to new test tasks? We test five self-evolving methods and a one-shot skill on six benchmarks, with the same model, the same agent, and the same train/test split for every method. Of the 21 skills that improve on their training tasks, 5 keep all of that improvement on the test tasks, 13 keep part of it, and 3 keep none of it. No existing method is best everywhere. When we read the skills, the ones that carry over badly often fix details that should depend on the task, such as column names and output files, or turn a fix for one failure into a rule for every task. An LLM judge that reads the skill content can often see this: it ranks finished skills the same way the test results do in 86\% of pairs. But it predicts the effect of a single edit poorly, so edits still have to be tested by running them. Based on these findings, we describe Generalizable Skill Optimization (GSO), which keeps only a guide for writing skills and writes a new skill for each task; it scores highest on all six benchmarks. --- ### MindWorldBench: Evaluating Mental-State-to-Behavior Reasoning in Image-to-Video Generation Authors: Ruiqi Li, Xuanyi Liu, Sijia Li, Haofeng Wang, Yuxin Liu, Feng Xie, Songchao Tan, Shiqi Wang, Hanwei Zhu, Yizong Wang, Chuanmin Jia, Siwei Ma Published: 2026-09-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.39147v1 Current image-to-video models achieve visual realism and physical plausibility, but reasoning about mental states remains unexplored. Actions are driven by belief, desire, and perception, requiring inference beyond explicit instructions. We introduce MindWorldBench to evaluate mental-state-conditioned video generation. We formalize this as mental-state-to-behavior reasoning, where models generate actions from a world state and latent variables without explicit action prompts. MindWorldBench utilizes Zero-Action Prompting and a counterfactual design with 744 prompts to isolate the causal effects of mental states. An automated pipeline evaluates video quality, commonsense plausibility, and mental-state consistency. Evaluations of 11 models show that despite visual fidelity and physical reasoning, models fail to align behaviors with latent mental states. We identify a failure mode, termed Omniscient Bias, where models default to the objective world state rather than human's subjective belief. These results demonstrate a disconnect between visual generation and cognitive reasoning, suggesting a need for explicit mental-state modeling in video generation systems. Project website: https://richard2049-lee.github.io/MindWorldBench/ --- ### MADBench: Benchmarking the Security of Multi-Agent Debate Authors: Yuwan Liu, Jiaming Zhang, Yue Huang, Sisi Duan Published: 2026-09-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.39146v1 Multi-agent debate (MAD) can improve large language model (LLM) reasoning by allowing multiple agents to exchange and critique their answers to the same task. However, the interactions that enable agents to correct mistakes can also spread adversarial errors and steer the agents toward an incorrect answer. Although some efforts have been made to examine particular attack types on MAD, systematic evaluation of MAD under diverse attacks remains limited. A central question is whether debate mitigates adversarial influence or amplifies it. In this paper, we present MADBench, a benchmark for evaluating the security of MAD. We organize attacks into a layered taxonomy following the MAD workflow, incorporating both established attacks and new strategies tailored to debate. We evaluate six attack families over 356 source tasks and 3,958 test cases, examining their effects on the final answer and the propagation of adversarial influence. Our results show that, under attacks, MAD does not necessarily improve LLM reasoning. Compared with a single-agent baseline, MAD can mitigate attacks on answer accuracy in question-answering tasks while amplifying unauthorized reads or writes in both question-answering and workspace tasks. Moreover, even when three out of five agents collude, the attack changes the final answer from correct to wrong on only 28.30\% of tasks answered correctly without attack, while only 3.26\% of initially correct honest agents switch to wrong answers during debate. --- ### Blackout vs. Freeze: Analyzing Physical Failure Modes of VLAs under Camera Faults Authors: Heejae Suh, Jongwook Han, Zahra Gholami, Yohan Jo Published: 2026-09-30 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2609.39145v1 Unreliable visual inputs can harm task performance and cause potential physical safety risks for vision-language-action (VLA) models. We analyze how $π0.5$ and GR00T models act under input faults such as image blackouts and freezing. We find that blackout and freezing produce distinct physical failure modes even when task-success rates are similarly low: freezing causes more extreme joint behavior, whereas blackout after gripper closure can cause more object drops, most markedly without proprioception. Selective intervention studies reveal that proprioception (current robot state) partly compensates for the removed robot depictions and reduces non-target contact. However, it cannot sufficiently restore task success when wrist-view object information is removed, even when aided by the remaining scene view. We then evaluate two mitigation approaches: camera-blackout training and training-free replacement of faulty visual embeddings. Both improve task success in selected conditions, but can increase unintended contact or disturbance to surrounding objects. Real-robot trials further show that successful execution under camera faults can still involve unintended physical interactions. These findings motivate designing VLA policies that use the robot and object information still available under camera faults to limit hazardous motion. --- ### Sharp Stationary Gaussian Approximation for Constant-Stepsize SGD Authors: Junghoon Seo Published: 2026-09-30 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2609.39144v1 We prove a sharp Gaussian approximation for the invariant law of constant-stepsize SGD with bounded additive noise generated by an exogenous uniformly ergodic Markov chain. For a smooth, strongly convex objective with a Lipschitz Hessian and nondegenerate long-run noise covariance, the centered iterate normalized by the square root of the stepsize is $O(\sqrtα)$-close in 1-Wasserstein distance to its limiting Gaussian. The proof combines blockwise Gaussian comparison with long-run contraction. A four-state example gives a matching lower bound although the one-time noise marginal is symmetric and every nonzero-lag autocovariance vanishes. In this example, an adjacent third-order mixed moment produces the leading correction. --- ### RefCon: Iterative Refinement and Contrastive Memory Extraction for Context-Evolving Agent Authors: Ubaidillah Ariq Prathama, Bo Liu, Yeo Boon Hong, Yu-Xuan Huang, Yangkai Ding, Tao Yu Published: 2026-09-30 Categories: cs.AI, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2609.39143v1 Long-horizon agent interactions generate useful but noisy experience, and retraining models to absorb it is expensive. Context-evolving agents therefore need memory extraction methods that improve with more test-time compute without relying on gold labels. We propose RefCon, which combines sequential self-refinement with parallel self-contrast to extract higher-quality memories without gold labels. Evaluated on AppWorld and BFCL-V3 across multiple context-evolving agent frameworks, RefCon delivers strong and consistent gains, including relative improvements of 21.6% on ACE and 16.6% on ReMe over no-scaling baselines, while a diversity-focused variant (DivCon) achieves a 35.5% gain on ReasoningBank. RefCon consistently outperforms existing baselines without ground-truth labels, and generalizes across model scales and to software engineering tasks, where it surpasses even ground-truth baselines. We further analyze the accuracy-token trade-off and scaling behavior, showing RefCon maintains favorable efficiency and continues to improve as more trajectories are used, unlike diversity-only scaling which saturates earlier. --- ### When Can Text Replace Vision? Structural Bottlenecks in Diagram Reasoning Authors: Yunbei Zhang, Janet Wang, Jihun Hamm, Chandan K Reddy Published: 2026-09-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.39142v1 Can structured text replace vision for diagram reasoning? A wrong answer after textualization can arise because the representation omits information the question needs, or because the solver fails to use information that is present. We introduce a diagnostic protocol to distinguish these explanations. Using the same solver model and generation settings, we compare three input conditions: the original image, question-blind structure extracted by a vision-language model, or gold structure derived from the diagram source. Validity-triggered recovery tests truncation and schema failure, question-relevant fidelity measures preservation of answer-critical structure, and matched edge interventions test the effect of error location. On a reserved holdout of 240 public FlowGen diagrams, evaluated under a frozen protocol, gold structure reaches 87% accuracy while direct vision and learned text both remain below 30%. The aggregate comparison includes source-derived relation labels that may not be printed in the image and uses different learned and gold graph encodings, so it does not isolate extraction error alone. Retrying only invalid extractions makes nearly every public representation schema-valid yet leaves accuracy essentially unchanged. The public learned-text deficit relative to gold more than doubles with structural difficulty. Question-relevant topology predicts correctness better than whole-graph topology. In an exposed intervention study, a single answer-relevant edge edit reduces the primary solver's original-answer accuracy to near zero, while matched irrelevant edits largely preserve it. Supplied structure requires fewer solving tokens than vision, but learned acquisition removes this advantage at single use. These comparisons motivate evaluating acquired text by the answer-relevant evidence it preserves and by the solver's ability to use that representation. --- ### Schema: Discovering Unknown Environments via Agentic Program Induction Authors: Guanning Zeng, Jiani Wang, Wenjie Ma, Shaofeng Yin, Chenyang Wang, Shichen Liu, Angjoo Kanazawa, Wode Ni, Xiuyu Li, Andrea Zanette, Haiwen Feng Published: 2026-09-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.39140v1 Learning to complete tasks in unfamiliar environments with unknown rules remains a key challenge for LLM agents. Current LLM agents often record their discoveries in prose, which may not provide a compact, explicit account of how the environment works. Inspired by how scientists organize observations into testable, predictive theories, we introduce Schema, an agent harness that organizes learning and action through interactive program induction. The LLM agent decides what to investigate and how to act, expressing its evolving understanding of the environment as executable programs. The harness consists of a persistent program workspace and a small set of interfaces for checking these programs against the interaction history, planning within them, and executing plans under step-by-step verification. Schema raises ARC-AGI-3 RHAE from 58.7% to 99.2% with the same base model, solves 100% of the public DiG-bench games, and reaches the median performance of the top-50 human players on MazeBench. Extensive analysis shows the effectiveness of Schema in unknown mechanism discovery, and ablations confirm the contribution of each component. ---