# Research Papers — 2026-10 · bundle page 9 of 156

> Full-text markdown of papers #401–450 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/9
[← Previous bundle](https://aipod.dev/papers/archive/2026-10/page/8.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-10/page/10.md)

### Finite-Time Guarantees for Constrained Reinforcement Learning under Partial Observability

Authors: Valentina Zaccaria, Philip Jordan, Tingting Ni, Gian Antonio Susto, Maryam Kamgarpour
Published: 2026-10-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.21548v1

We study reinforcement learning in constrained partially observable Markov decision processes (CPOMDPs), where an agent maximizes reward subject to a cost constraint using only incomplete information about the underlying state. The lack of state observability may require optimal policies to depend on arbitrarily long observation-action histories, making planning and learning challenging. We leverage recent advances in finite-memory approximations of POMDPs and represent finite history windows as states of a constrained MDP. We then develop a primal--dual algorithm that provides the first non-asymptotic guarantees that jointly bound average reward suboptimality and constraint violation in the original CPOMDP. A key challenge is that this finite-window approximation affects both reward values and the set of feasible policies. Under a filter-stability assumption, we derive bounds relating optimality and feasibility in the finite-state model to those in the original CPOMDP, with approximation errors that decay geometrically with the window length. Experiments in partially observable gridworlds demonstrate the effectiveness of our approach.

---

### Federated Art Chase: Privacy Leakage and Data Poisoning in Federated Fine-Tuning

Authors: Vasileios Perifanis, Nikolaos Pavlidis
Published: 2026-10-15
Categories: cs.LG, cs.CR
arXiv: https://arxiv.org/abs/2610.21547v1

Federated learning (FL) is increasingly used to adapt a pretrained, centrally fine-tuned model to data that remain on user devices, beyond training a model from scratch. In this report, prepared for the 4th Federated Machine Learning International Summer School, we study the privacy and integrity of this approach with a reproducible pipeline. An ImageNet-pretrained MobileNetV4-Conv-Small model is fine-tuned centrally on ten Quick, Draw! classes (97.50% test accuracy) and then adapted with head-only FedAvg over ten non-IID clients, which raises client training accuracy from 90.34% to 91.49% while preserving global accuracy. We evaluate four adversarial scenarios. First, from a single one-step client update, an honest-but-curious server recovers the complete private label set, but its reconstructions follow class prototypes rather than the private drawings (mean SSIM 0.130). Second, from a one-round FedAvg aggregate, label-count recovery falls from 87.5% with one client to 75.0% with five and ten clients, below the 80.0% of an uninformed uniform guess. Third, under FedAvg, a backdoor injected by 30%, 50%, and 100% of the clients reaches an attack success rate (ASR) of 21.9%, 31.3%, and 54.7% at a cost of at most 0.8 percentage points of clean accuracy, whereas label flipping is effective only when most of the source-class data are relabeled. Fourth, FLTrust with a root set retained from centralized fine-tuning lowers the backdoor ASR to 1.8% and 4.0% at 30% and 50% malicious clients and the label-flipping ASR from 12.6% to 0.8% without measurable clean-accuracy loss, but provides no protection when every client is malicious. The report closes with a live session in which participants draw, fine-tune, and poison the model through Indigma's FedMaestro orchestrator. Code and executed notebooks, runnable on Google Colab, are at https://github.com/Indigma-Innovations/fl-summer-school.

---

### Reinforcement Learning-driven Diffusion Models: Language, Vision, and Beyond

Authors: Zhiyuan Ma, Jiabao Wei, Tianyu Wang, Hanqing Wang, Jiadong Pan, Haowen Xu, Liangliang Zhao, Ruixun Liu, Yuhan Wang, Yuwei Zhang, Liang Feng, Junhao Xiao et al.
Published: 2026-10-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.21539v1

Diffusion models (DMs) have steadily demonstrated outstanding performance in high-fidelity, controllable generation across diverse scenarios, following the "pretraining-finetuning" paradigm established in LLMs. Despite these advances, conventional DMs still face critical limitations in sophisticated reasoning, autonomous exploration of generation pathways, and adaptability to complex, human-aligned objectives. Inspired by RLHF's success in LLMs, RL has recently emerged as a pivotal post-training mechanism to iteratively refine DMs through reward-driven trajectory optimization. This paper presents the first comprehensive review of RL-driven DMs and an empirical analysis of how RL reshapes the diffusion process towards experience-centric, goal-directed generation. We propose a novel technical panorama elucidating RL's multifaceted roles in diffusion-based language, multimodal, robotic, and scientific models, with a granular focus on diffusion trajectory optimization and reward engineering. Through extensive experiments on multiple task-specific benchmarks, we systematically evaluate representative methods to intuitively highlight the advantages of different RL post-training strategies. Furthermore, we reveal and dissect three crucial bottlenecks that currently hinder the real-world deployment of RL-driven DMs: reward design fragility, exploration-exploitation trade-off in high-dimensional generation spaces, and training instability under sparse rewards. Based on these perspectives, we provide a principled roadmap for the integration of RL into DMs and outline promising future research directions for robust, interpretable RL-diffusion systems. We also construct a public repository to continuously track the latest developments in this rapidly evolving field: https://github.com/MAIR-Lab-HUST/Awesome-RL-for-Diffusion-Models.

---

### Agent Status Protocol (ASP): A Lightweight Specification for State Reporting in Multi-Agent Systems

Authors: Diego Gosmar, Deborah A. Dahl, Emmett Coin, Csaba Bolyós, Andreas Zettl
Published: 2026-10-15
Categories: cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2610.21538v1

The Agent Status Protocol (ASP) defines a lightweight way for heterogeneous AI agents to report their operational state to a status server, and for observers such as dashboards to receive that state as soon as it changes. Agents push small JSON events over HTTP POST; the server exposes the aggregated state to observers over Server-Sent Events (SSE). Because an agent that has crashed, hung or been compromised cannot be trusted to report its own failure, ASP does not rely on self-reports alone: the server infers liveness from missed heartbeats, can detect agents that are alive but no longer making progress, and accepts observations from supervisors, guardrails, operators and peers, some of which take precedence over what the agent says about itself while others are shown alongside it. ASP models state along independent dimensions (lifecycle, health, task, floor, governance), so that an agent can be, for example, online, degraded, working on a task and waiting for the floor at the same time. It reuses existing vocabularies: task states from the Agent2Agent (A2A) protocol, floor states from the Open Floor Protocol (OFP), and attribute conventions from the OpenTelemetry GenAI semantic conventions. This paper presents version 0.1 of ASP as a proposal, not as an approved standard. It is a working draft intended to open a discussion, and the authors invite comments, alternative proposals and independent implementations from the community.

---

### Functional Subnetwork Localization for Efficient Continual Learning in Large Language Models

Authors: Shuoran Jiang, Wentao Zhu, Yang Xiang, Dongfeng Li, Yunan Zhang, Mengchen Zhao, Yuhui Guo, Kai Chen, Youcheng Pan, Xiangping Wu, Qingcai Chen
Published: 2026-10-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.21537v1

Biological intelligence continually adapts to new information while retaining prior skills through localized plasticity. In contrast, continual learning in large language models (LLMs) remains vulnerable to catastrophic forgetting. A promising direction is to identify functionally specialized subnetworks within LLMs that enable targeted and resource-efficient adaptation. Using gradient-attribution profiling, we localize cognition-associated functional subnetworks exhibiting extremely low mutual overlap. Building on this finding, we propose Function-isolated Memory-Efficient Optimization (CiMEO), a continual learning framework that routes each training example to its corresponding functional subnetwork, restricting parameter updates and optimizer states to selected regions. Across 1.4 million sequential instructions, CiMEO achieves the highest average performance among the compared methods on five generative benchmarks spanning programming, examination-style tasks, and mathematical reasoning, while mitigating catastrophic forgetting. Subspace-overlap and principal-angle analyses further indicate that localized updates help preserve pre-trained representations, highlighting functional subnetwork localization as a practical approach to efficient and stable continual learning in LLMs.

---

### Activation-Adjacent Layer Normalization: Effects on Approximation Power

Authors: Yunhao Ni, Yuxin Guo, Jie Luo, Wenjun Wu, Lei Huang
Published: 2026-10-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.21527v1

Layer normalization (LN) and root mean square normalization (RMSNorm) depend on their inputs and remain nonlinear at inference. Inserting either next to an activation may therefore change the function a network represents. We study when shallow activation-normalized (AN) and preactivation-normalized (PN) networks can approximate a prescribed width-$N$ one-hidden-layer MLP. Viewing RMSNorm as input-dependent scaling, we use width augmentation to locally linearize normalization on compact feature sets. For AN networks, an unbounded activation range allows width $N+1$, while every continuous nonconstant activation admits width $N+r$ with error $O_f(r^{-1})$. For PN networks, affine parameters or, without them, degree-one positive homogeneity recover width $N+1$; general continuous activations admit width $N+r$ with error tending to zero. The corresponding LN constructions use centered coordinate pairs, yielding widths $N+2$ and $N+2r$, respectively. We prove that $N+1$ for RMSNorm and $N+2$ for LN are also the worst-case bound for approximations, and show that applicable universal-approximation theorems for ordinary MLPs transfer to these normalized architectures. Numerical experiments recover the predicted approximation rates for both normalizations across all five settings and illustrate the shifted-ReLU finite-width obstruction.

---

### CriticaLLM: Using LLMs as Autonomous Game Master for Tabletop Role-Playing Games

Authors: Gaëtan Berlaimont, Justin Vanwichelen, Benoît Ronval, Hélène Verhaeghe
Published: 2026-10-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.21525v1

Large Language Models (LLMs) have shown impressive capabilities across many tasks, including processing large amounts of text, following instructions, and generating ideas. This allows the use of such models in various contexts, including games and Tabletop Role-Playing Games (TTRPGs), such as Dungeons & Dragons. However, these games include many complex components, from crafting interesting stories to adhering to rules, while allowing some freedom in players' actions. In this work, we first highlight key components that LLMs should exhibit in the context of TTRPGs. Then, we introduce our framework, CriticaLLM, a fully automated Game Master that can run entire TTRPG games, from creating diverse and interesting stories to managing exploration and combat phases. We evaluate our framework with actual TTRPG players and examine the diversity of generated plots and antagonists across four LLMs of varying sizes. Overall, our framework appears to be a promising option for running entire TTRPG games.

---

### Hierarchical Interpretable Multitask Audio Representation Learning: An Analysis of Event-Scene Relationships through the Information Bottleneck

Authors: Claudia Montero-Ramírez, Alba Martínez-Serrano, Carmen Peláez-Moreno
Published: 2026-10-15
Categories: eess.AS, cs.AI
arXiv: https://arxiv.org/abs/2610.21520v1

Joint Acoustic Scene Classification (ASC) and Audio Tagging (AT) models traditionally rely on unconstrained multihead architectures. However, this design ignores the natural hierarchical dependency between sounds and acoustic scenes. In this work, we investigate a hierarchical (sequential) conditioning paradigm that predicts scene categories directly from intermediate event probabilities. Through a large-scale empirical benchmark with 66 full training runs across three state-of-the-art backbones (PaSST, PANNs, and BEATs) and different loss-weighting settings (beta in (0.0, 1.0)), we show that hierarchical conditioning achieves competitive classification performance while altering multitask optimization dynamics. Unlike multihead baselines, which sequentially solve the easier ASC task before optimizing AT, the hierarchical architecture enables synchronized dual-task learning for specific loss-weighting settings (beta in (0.6, 0.9)). Furthermore, we propose a multi-perspective interpretability framework that combines an analysis of the information bottleneck, manifold geometry, and Formal Concept Analysis (FCA) on a Term-Frequency Inverse-Document-Frequency (TF-IDF) event representation, providing complementary insights into event-scene relationships. Our findings reveal that hierarchical conditioning systematically yields lower conditional entropy, higher mutual information, and superior latent cluster separability (higher Silhouette scores), establishing a more structured and semantically faithful intermediate feature space.

---

### SCRIBE: Scalable Contextual Representations of Interpretable Brain-Grounded Semantics

Authors: Camila Kolling, Omer Moussa, Emin Çelik, Mariya Toneva
Published: 2026-10-15
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2610.21518v1

Understanding how the human brain constructs meaning from real-world language remains a fundamental challenge, as semantics depend on context that varies in natural settings. To enable the study of real-world linguistic meaning in the brain, we introduce SCRIBE, a framework grounded in a neuroscience-informed semantic space that leverages an ensemble of open-source large language models to generate interpretable, word-level semantic representations of arbitrary text. In a behavioral study with 921 participants, we show that human semantic feature judgments vary systematically with context, and that SCRIBE captures these shifts, reaching 75-81% of the estimated human noise ceiling. Using brain activity recorded while participants listen to naturalistic stories, we further demonstrate that SCRIBE predicts neural responses in language-selective brain regions, significantly outperforming non-contextual semantic representations. Variance partitioning reveals that SCRIBE explains unique brain-predictive information beyond syntactic features, suggesting that its representations capture aspects of linguistic meaning not accounted for by the measured syntactic features. Together, these findings establish SCRIBE as a scalable and interpretable foundation for studying natural language semantics in the brain.

---

### Poison Valleys: Diagnosing Path-Dependent Failure in LLM Code Repair

Authors: Veljko Skarich
Published: 2026-10-15
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2610.21514v1

When code-repair agents fail, final tests reveal that a patch is wrong but not which earlier commitment caused it or which software obligation failed. Poison Valleys traces this path in 1,844 model requests on two synthetic Python cases: PersistQueue adds atomic batch claiming to a disk-backed queue, while Dijkstra adds source-sensitive filtering to shortest-path search. We define plausible but incorrect software mechanisms, place each in a model's hypothesis, implementation plan, or both, and evaluate the generated code with an Oracle and targeted diagnostic coordinates. Moving the misconception from hypothesis to plan increased failure by 32.2% in PersistQueue and 28.9% in Dijkstra after matching the experimental mix. Different misconceptions produced distinct, model-dependent patterns of violated obligations, although several could converge on the same behavior. This creates a measured connection from upstream misconception to code mechanism and failure form. Code, data, and demo: https://poisonvalleys.org.

---

### QREF: Improving DeepSearch Agents by Aligning Search with Reasoning via Query Refinement and Evidence Filtering

Authors: Yujia Chen, Yuhui Wang, Junzhe Wang, Shihan Dou, Di Liang, Yujiong Shen, Yuhao Zhou, Zhiheng Xi, Ming Zhang, Senjie Jin, Jiayi Chen, Dingwei Zhu et al.
Published: 2026-10-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.21512v1

DeepSearch agents achieve strong performance on complex information-seeking tasks through iterative search and reasoning. However, they often issue intent-misaligned, under-constrained, or redundant search queries, resulting in poor evidence coverage and accumulating retrieval noise. To mitigate these limitations, we propose QREF, a plug-and-play Query Refiner and Evidence Filter. Specifically, the Query Refiner rewrites search queries according to the current reasoning intent while ensuring complementary coverage across each search batch. The Evidence Filter retains evidence relevant to both the current search batch and the reasoning objective, reducing distracting retrieval results. We initialize the Query Refiner with supervised fine-tuning and optimize it through reinforcement learning based on interactions with a real-world web search environment, reducing ineffective queries. Comprehensive experiments demonstrate that our approach improves the performance of DeepSearch agents across four challenging benchmarks, achieving average relative Pass@1 improvements of 33.55% on WebSailor and 11.04% on TongyiDeepResearch without modifying architectures or retraining their reasoning policies. Compared with the original DeepSearch backbone without QREF, the RL-trained refiner reduces the fraction of query batches that lack discriminative retrieval anchors by 95%. Compared with the SFT-trained refiner, it also lowers the filter-based ineffective query ratio.

---

### Decomposing Brain-LLM Alignment with Interpretable Semantic Representations

Authors: Camila Kolling, Mariya Toneva
Published: 2026-10-15
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2610.21508v1

Large language models (LLMs) predict neural responses during naturalistic language comprehension, but the linguistic information underlying this brain alignment remains difficult to interpret. We use SCRIBE, an interpretable contextual semantic representation spanning 65 neurocognitively grounded semantic properties, as a lens for decomposing the brain alignment of one LLM, LLaMA2-7B. Using variance partitioning between LLaMA2-7B and SCRIBE on naturalistic fMRI data from seven participants listening to narrative stories (Moth Radio Hour), we separate brain-predictive variance shared between the two representations from variance unique to each. We find that shared variance is the dominant component across the whole brain and language-related regions, while both representations also retain significant unique contributions. We then examine whether the concreteness of individual semantic properties relates to shared and SCRIBE-unique brain-predictive variance. Concrete properties show greater shared variance with LLaMA2-7B than abstract properties across the whole brain and most examined regions, whereas abstract properties do not show greater SCRIBE-unique variance. Finally, property ablations reveal that semantic contributions extend across multiple dimensions, with cumulative effects on both shared and SCRIBE-unique variance. Together, these results show that, for LLaMA2-7B on this dataset, a substantial portion of brain-LLM alignment is associated with interpretable semantic information, while revealing complementary brain-predictive semantic information beyond the LLaMA2-7B representation.

---

### FilterFusion: Prior-Guided Adaptive Filter Fusion for Efficient Video Denoising

Authors: Wenlong Yang, Weihang Yuan, Canran Jin, Jiahao Li, Henrik Turbell, Lifeng Sun
Published: 2026-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.21505v1

Real-world video denoising for communication systems must handle mixed degradations such as sensor noise, compression artifacts, and motion-induced inconsistency while remaining deployable under tight latency budgets. Purely deep models often achieve high accuracy but come with significant computational cost, whereas classical filters are robust and efficient but insufficiently adaptive. We present FilterFusion, a prior-guided multi-frame denoising framework that combines temporally-aware learned features with an interpretable bank of denoising branches. The model predicts a low-cost guidance signal and uses it to adaptively mix a compact set of denoising responses at the original resolution. The lightweight design uses only 109K parameters and explicitly injects temporal variance and spatial variance cues into the low-resolution controller. On CRVD (real sensor noise), it reaches 34.72 dB PSNR and 0.9330 SSIM with only 0.18 GFLOPs (network-only). Because the filter-bank operations are simple and regular (Gaussian blur, median, weighted sum), a straightforward compiled C implementation of the synthesis path achieves 17.9ms per frame (55.9 FPS) on a single CPU thread at 1080p---exceeding real-time and 122--252 times faster than lightweight CNN baselines that require over 2 seconds per frame. The results demonstrate a strong quality-efficiency-speed trade-off and a practical route to real-time denoising through low-resolution control and explicit filter-based synthesis.

---

### ISW-Agent: Integrating LLM-Driven Dialogue with n8n Workflow for Internal Solitary Wave Remote Sensing Image Processing

Authors: Hao Zhang, Hengrui Liu, Lina Sun, Junmin Meng
Published: 2026-10-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.21502v1

Internal solitary wave (ISW) remote sensing requires task parameters and spatial information to be transferred across image acquisition, detection, stripe extraction, and propagation prediction. Here, we present ISW-Agent, which integrates large language model (LLM) interpretation with n8n workflows and independent scientific models through structured task constraints, geospatial transformations, and stage-specific output validation. In tests of 120 Chinese instructions per backend, GPT-5.6 Sol and DeepSeek both achieved a strict task-match rate of 94.2%, with all intents and execution decisions matching the reference. Sentinel-1 cases demonstrated continuous processing from dialogue requests to wavefront prediction for the specified scene. Of 50 timed scenes, 39 completed detection, extraction, and prediction with a median turnaround time of 48.04 s; 11 stopped after empty extraction. Across 3,408 controlled fault-injection runs, retries recovered 234 transient-failure conditions and output validation rejected 234 structural defects, while 61 provenance or completeness errors indicated the need for content-consistency checks. Overall, ISW-Agent thus connects natural-language requests to traceable spatial processing chains for multimodel ISW analysis.

---

### When the KV Cache Is Slower Than the GPU: Scaling Remote KV Tiers for Context-Parallel Prefill

Authors: Muhammad Ibrahim
Published: 2026-10-15
Categories: cs.DC, cs.LG
arXiv: https://arxiv.org/abs/2610.21500v1

Reusing the attention KV cache across requests is a standard way to cut prefill cost in long-context LLM serving, and production systems increasingly back the per-engine cache with a remote tier shared by every engine. We study such a tier in a disaggregated deployment of GLM-5.3, an FP8 mixture-of-experts model with multi-head latent attention (MLA), on 8xB300 nodes running prefill context parallelism (PCP8). Enabling the remote tier (LMCache with a Valkey store) left median time-to-first-token unchanged but raised the 16k-token p99 from 3.96 s to 17.3 s. Replaying a production request stream on an isolated engine, we find that a remote hit took 0.88 s against 0.31 s to recompute the prompt, and that synchronous loading turned a hit-heavy stream into an unstable queue: p99 83.32 s with the GPUs 7% busy. A two-term cost model explains both: a hit pays off only if the tier delivers more than B* = sR (2.53 GB/s for this model and GPU), and a fixed per-hit engine cost (T0 ~ 0.33 s) means that hits on prompts shorter than about 17k tokens cannot beat recompute at any bandwidth. Guided by the model, we (i) shard the MLA KV store across PCP ranks, with a proof that the existing minimum-over-ranks lookup returns the longest cached prefix and a load protocol that can never desynchronize collectives; (ii) partition the remote tier by rank, one server instance per rank with no coordination, which raises GET bandwidth 6.3x to 10.76 GB/s; (iii) add asynchronous loading to the sharded store; and (iv) fix three client bugs that caused unbounded stalls. On the hit-heavy stream, with 98.5% of prompt tokens served from the remote tier, p99 falls from 83.32 s to 0.67 s. The sharded store raises prefill throughput by 14%, and by 34% together with an upstream kernel fix. All changes are submitted upstream to LMCache.

---

### GRASE: Geometry-native Real-to-sim Agentic Scene Modeling from Video

Authors: Zhaorui Lin, Haohan Liu, Zhen Chen, Xiangru Huang
Published: 2026-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.21498v1

Real-to-sim conversion aims to turn a captured video of a real environment into an editable 3D scene while preserving the geometry and layout of what was observed. Existing methods often follow a one-pass, loosely coupled paradigm: each stage receives only limited feedback from previous stages, allowing errors to propagate without reliable correction and leaving the final scene inconsistent. We present GRASE, an agentic framework that closes this loop by treating the captured multi-view video observations as a standing reference throughout scene modeling. Instead of committing to intermediate estimates, GRASE revises its current hypothesis whenever rendered evidence disagrees with the capture, overcoming the fixed intermediate assumptions of conventional pipelines. Specifically, GRASE first fits the architectural shell and its openings from depth and multi-view cues. An agent then places generated assets in a shared coordinate frame while checking their spatial relationships. Finally, each asset's geometry and placement are refined iteratively to improve agreement across the observed views. By coupling these steps through feedback, GRASE localizes structural discrepancies and revises only the responsible components, while preserving cross-view consistency. The resulting 3D scenes are faithful to the input, consistent across views, and suitable for simulations. In our experiments, GRASE substantially outperforms other state-of-the-art methods, including a direct real-to-sim conversion using GPT6-Astra.

---

### OPRD: On-Policy Reminder Distillation for Long-Horizon Coding Agents

Authors: Yuechen Luo, Zhiyi Lai, Miao Ziqi, Zihang Xu, Jingxuan Xu, Songwei Yu, Wenqiang Zhu, Weihao Li, Junhao Fan, Haoyang Huang, Yanan Wu, Ken Deng
Published: 2026-10-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.21496v1

Reliable repository-level coding requires agents not only to generate correct code but also to preserve constraints and respond to tool feedback across long interactions. However, our diagnostic analysis shows that agents often fail to act on relevant information already available in context, while final Pass/Fail outcomes provide only sparse process supervision. We introduce On-Policy Reminder Distillation (OPRD), which combines Multi-Scope Reminder supervision with outcome-based routing on reminder-free student rollouts. Successful rollouts provide autoregressive self-imitation targets, whereas failed rollouts receive Reminder-conditioned reverse-KL supervision from a teacher that re-evaluates the same student-generated prefixes. A Global Reminder converts final-test diagnostics into trajectory-level guidance, while Turn-local Reminders apply only to the next decision following the relevant environment observation. The teacher and student share a two-stage initialization from Coding SFT and Instruction-Following (IF) SFT. At inference, the student operates without Reminders. On SWE-bench Verified, SWE-bench Pro, and SWE-bench Multilingual, OPRD improves the benchmark-averaged task resolution rate by 11.3 points over the open-source Qwen3.5-4B base model. Under the same diagnostic protocol, it reduces the aggregate error-event count from 446 to 222, a 50.2% reduction.

---

### Phase Kernel Lifts Capacity of Dense Associative Memory

Authors: Yifei Zhao, Ying Tang
Published: 2026-10-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.21493v1

Dense associative memory underlies modern attention mechanisms; however, Modern Hopfield Networks (MHNs) with linear kernels yield overlapping attractor basins and spurious states under high memory load, limiting their theoretically exponential storage capacity in practice. We construct a class of nonlinear phase kernels that modify the energy landscape and retrieval dynamics, and prove that these kernels preserve exponential storage capacity and local fixed-point convergence under given conditions on kernel smoothness, memory separation, and memory distributions. The framework is instantiated by the Sigmoidal Phase Hopfield Network (S-Hop), which guarantees monotone energy descent and mitigates practical capacity loss. S-Hop has $8.3\times$ and $4\times$ gains in one-step noisy retrieval load over Uniform Hopfield Networks (U-Hop) on CIFAR-10 and TinyImageNet respectively, and reaches a $50\times$ gain in first-failure load for ImageNet. The results demonstrate that phase kernels provide a principled route to robust dense associative memory.

---

### MetaExp: Learning to Self-Improve through Experience via Verifiable Cross-Task Environment Scaling

Authors: Renhao Li, Xinjie Shen, Yang Su, Jianhong Tu, Derek F. Wong, Dayiheng Liu, Min Yang
Published: 2026-10-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.21492v1

Language-model agents can accumulate interaction feedback, but reliably turning that feedback into reusable experience remains challenging. Existing methods either optimize external experience scaffolds or train experience-related behavior on specific task distributions, leaving open whether experience learning itself can become a transferable model capability. Training such a capability calls for supervision beyond isolated tasks, which mainly support in-episode problem solving rather than revealing what knowledge remains useful across episodes. In this work, we introduce MetaExp, a scalable framework that trains this capability through verifiable task families with controlled cross-task structure. Each family preserves a reusable factor while varying task-specific realizations, enabling transfer without direct solution reuse. We propose two complementary designs: Shared-Tool families keep black-box tools fixed across tasks to elicit operational experience, while Shared-Workflow families preserve latent procedures across changing realizations to elicit procedural experience. We scale environments under both designs, collect and filter sequential interaction trajectories, and fine-tune Qwen3.5-122B-A10B on 4,956 trajectories from 1,000 task families. With parameters frozen during downstream evolution, MetaExp improves by +8.5 points on SpreadsheetBench, peaks at +2.3 on APEX-Agents, and improves by +14.8 on AutomationBench. The gains persist under domain-excluded training, supporting experience learning as a transferable capability for continued non-parametric improvement after deployment.

---

### FlashAttention with Statistics: Low-Overhead Attention Features for Compact Hallucination Detectors

Authors: Andrei Volodichev, Maksim Savichev, Nikita Sviridov, Artem Yuliy, Dmitry Simakov, Alexey Zaytsev
Published: 2026-10-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.21483v1

Large language models can produce fluent answers that the supplied context does not support. A compact frozen proxy model can detect such answers by reading the context and another model's response, even from a proprietary generator. Attention-based detectors use summary statistics of the proxy's attention weights, but standard pipelines materialize the attention matrix, whose memory grows quadratically with sequence length. We compute these statistics without materializing attention, by accumulation in the FlashAttention pass, sparse lookups after it, or a second tiled pass over the scores, and classify them by this path into nearly free and costlier ones. On an H100, the statistics of five published detectors add 16% to the latency of a Qwen3-8B forward at 2K tokens, falling to 1.4% at 35K, and store 22.5 KiB per response token. On three benchmarks, probes trained on frozen Qwen3 proxies of 0.6B to 8B parameters prove strong detectors: a 4B proxy outperforms the strongest of nine zero-shot 4-9B LLM judges in F1 on two of the three, the proxies match or outperform specialized grounding checkers of up to 7B parameters, probing each proxy beats prompting it as a judge, and adding attention features significantly improves F1 in half of the 12 benchmark-proxy pairs, never significantly lowering it.

---

### AI-Driven Disaster Response and Displacement Monitoring

Authors: Noora Al-Emadi, Muhammad Imran, Yin Yang, Ingmar Weber, Fabjan Lashi, Gaia Rigodanza, Ivana Hajzmanova, Ferda Ofli
Published: 2026-10-15
Categories: cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2610.21482v1

ARTIFICIAL INTELLIGENCE (AI) has demonstrated its potential across a wide range of humanitarian tasks, offering scalable and data-driven solutions to some of the world's most pressing challenges. For instance, in addressing climate change, AI-powered models are being used for faster and more accurate global weather forecasting, control and design of renewable energy, and monitoring deforestation. Machine learning algorithms analyze satellite imagery and socioeconomic data to predict poverty and promote sustainable development. AI has also transformed disaster response and conflict monitoring, providing innovative solutions for assessing damage and urgent needs and tracking displacement.

---

### Kolmogorov-Arnold Networks: Curse of Dimensionality and Structural Bias

Authors: Yunhao Ni, Yuxin Guo, Jie Luo, Wenjun Wu, Lei Huang
Published: 2026-10-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.21480v1

Kolmogorov-Arnold networks (KANs) have a dimension-independent approximation exponent when the target admits a sufficiently smooth representation by univariate edge functions. We ask whether this favorable scaling belongs to the architecture or to the assumed target class. For arbitrary-depth standard spline-KANs, we prove a worst-case lower bound on isotropic Sobolev balls: below a dimension-independent accuracy threshold, the required number of spline coefficients grows at least exponentially with input dimension. Existing composition-matched MLP results, by contrast, show that favorable exponents on low-arity targets are not exclusive to KANs. We also revisit empirical comparisons. On four scaling-law targets, spline-KAN approximants constructed from known decompositions transfer exactly to MLPs with the cubic ReLU activation $σ(x)=(\max\{0,x\})^3$, although their full dense parameter counts are larger. In controlled ridge-profile scans, KANs have a strong advantage when each nonlinear component depends on one input coordinate. When a component couples multiple input coordinates, this advantage may narrow sharply. At tight budgets, interacting targets often favor MLPs. In the random-label test on MNIST, ReLU-MLPs fit the randomized training labels more efficiently than spline-only KANs. Together, these results locate favorable scaling in target structure and a compatible inductive bias, not a general KAN-specific escape from the curse of dimensionality.

---

### Tool-Augmented Large Language Models for Reliable Medical Calculation from Patient Notes

Authors: Yang Zhong, Ling Luo, Xuanlyu Zhu, Yanhua Wang, Yuanyuan Sun, Jian Wang, Hongfei Lin
Published: 2026-10-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.21477v1

Medical calculators translate raw patient observations into clinically actionable values and scores. However, applying these calculators directly to free-form patient notes requires precise variable extraction combined with the exact execution of complex formulas, scoring rules, and output conventions. Relying solely on direct large language model (LLM) prompting is unreliable in this context, as rule recall, parameter extraction, arithmetic reasoning, and formatting become entangled within a single generative step. To address these limitations, we propose a tool-augmented LLM framework for reliable medical calculation from patient notes. The framework retrieves and structures calculator specifications, generates reusable executable tools, and uses a constrained extractor to map each patient note to calculator-ready inputs. The tools then perform deterministic calculation, separating clinical language understanding from rule execution and arithmetic. Evaluated on the MedCalc-Bench dataset, our method achieves 86.73% final-answer accuracy, outperforming the one-shot prompting and supervised fine tuning-only baselines by 24.0 and 17.27 percentage points. Ablation and error analyses show that these performance gains are primarily driven by rule-grounded tool synthesis and schema-constrained extraction, whereas remaining failures are concentrated in clinical-semantic extraction and benchmark-specific output contracts. By grounding calculator logic in executable tools, the proposed approach alleviates arithmetic hallucinations and improves the computational reliability of the final clinical outputs.

---

### Cross-Prompt Inference Mitigates Rare-Class Suppression in Imbalanced VLM Finetuning

Authors: Emanuel Ben Baruch, Sivan Biham, Alon Shoshan, Yochai Zvik, Avi Ben-Cohen
Published: 2026-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.21470v1

When a vision-language model is finetuned on class-imbalanced data, rare-class recall can fall well below the model's own zero-shot performance. In this regime, we uncover a surprising matched-prompt penalty whereby the standard choice of reusing the descriptive finetuning prompt at inference can yield lower rare-class recall than using a different descriptive prompt. We call this inference-time strategy cross-prompt inference. We evaluate diverse VLMs across six datasets and find that cross-prompt inference consistently recovers rare-class recall, with varying trade-offs in frequent-class recall. The effect reflects a train-eval prompt interaction rather than prompt quality alone, and does not arise with non-descriptive prompt changes. It is strongest when imbalance and visual confusability produce substantial rare-class suppression, and is weak or absent when such suppression does not occur. Using Tuning Contribution (TuCo), which decomposes a model's computation into pretrained and finetuning parts, we find that cross-prompt inference reduces reliance on finetuning-induced computation and shifts the model toward its pretrained component. Reducing that finetuning contribution also substantially reduces the cross-prompt advantage. These results show that rare-class knowledge suppressed by imbalanced finetuning can remain accessible under a different inference prompt.

---

### Can LLMs Tell Stories Out of Order? A Corpus and Benchmark for Nonlinear Narrative Generation

Authors: Syed Rifat Raiyan, Md. Tariquzzaman, Md Farhan Ishmam, Tenghao Huang
Published: 2026-10-15
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2610.21468v1

Every story has two orders: the order in which its events happen and the order in which they are told. A story is nonlinear when the two differ. We introduce a benchmark of 83 published works that measures whether language models can tell nonlinear stories. For each work, we annotate one list of events in both orders, together with a story graph of causal dependencies, character knowledge, and the questions the telling raises and resolves. Given events in chronological order, all 19 models tell them, on average, more chronologically than the published works do; asked for a specific structure, they land within the human range about half the time. We then compare a model's stories of the same events under different conditions, using both an automated judge and 71 human readers. Both prefer the chronological story a model writes by default to the nonlinear one it writes on request, which readers find harder to follow in 81% of decisive judgments. Readers also prefer stories written from the story graph to stories constrained to the published telling order (72% of decisive judgments), a difference the judge does not detect. Our results suggest that following an instruction to reorder a story is not yet the same as telling it well out of order.

---

### DuET: Note-Frame Dual Encoding for Piano Performance-to-Score Transcription

Authors: Wei Zeng, Ye Wang
Published: 2026-10-15
Categories: cs.SD, cs.LG, eess.AS
arXiv: https://arxiv.org/abs/2610.21467v1

Transcribing expressive piano performances into scores requires interpreting individual note timings within an underlying metrical structure. However, score attributes are associated with notes, whereas beats may occur without coincident note onsets. We introduce DuET, a Dual-Encoder Transformer that jointly learns note-level performance MIDI-to-score (PM2S) transcription and frame-level beat and downbeat tracking. Bidirectional cross-attention connects note and frame encoders, while an autoregressive decoder alternates between their representations to predict structured score attributes. We further introduce TimeRoPE and Time-Pitch Rotary Positional Encoding (TPRoPE) to establish a shared performance-time reference and explicitly encode relative temporal and pitch relationships. Evaluations on ASAP, a classical piano dataset, and our curated Gangqinpu dataset, which spans multiple genres with a focus on popular piano music, demonstrate improvements in score timing and notated duration. Compared with the strongest baseline on each dataset, DuET reduces MUSTER mean error from 6.56% to 3.64% on Gangqinpu and from 11.30% to 11.22% on ASAP. Ablations support the benefits of frame-level context, time-based positional encoding, and decoder-history masking. Code, weights, and demos are available at https://github.com/wei-zeng98/DuET.

---

### Ontology Refinement with Embeddings and LLMs: A Case Study on CASTON

Authors: Hui Yang, Ziyu Li, Xuan Liu, Anders Jarfors, He Tan, Jiaoyan Chen
Published: 2026-10-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.21466v1

Ontologies are widely used to represent and organize complex knowledge in domains such as biomedicine and healthcare. However, constructing reliable ontologies remains challenging, as class hierarchies, whether manually or automatically constructed, may contain subtle subsumption errors that require careful refinement. We study this problem in CASTON, a casting-domain ontology, and present a lightweight but scalable refinement workflow that combines a fine-tuned ontology embedding model with Large Language Models (LLMs). The embedding model is used to extract a limited number of candidate axioms for refinement together with possible replacement candidates, and an LLM then returns repair suggestions. In a small expert evaluation, the default configuration using a CASTON-fine-tuned OnT embedding model and Qwen3-8B produced reliable high-confidence repairs: all six high-confidence replacements were accepted by both domain experts. The implementation is available at https://github.com/HuiYang1997/OntRefine.

---

### Trajectory-Level Speculation with Semantic Verification for Tool-Using Agents

Authors: Zilin Wang, Yinhong Liu, Chao Chen, Qun Liu, Zhijiang Guo
Published: 2026-10-15
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2610.21463v1

Large language model agents solve tasks through long sequences of tool calls, and the prevailing design has a single strong model generate every step, although many steps are routine enough for a much smaller model. Existing ways of sharing this work keep the strong model as the generator: routers and collaborative agents decide which model handles each query or step, and speculative methods check a small model's drafts one step at a time, usually against the strong model's own action. We introduce SpecAgent, a collaboration protocol that turns the strong model from the author of each step into a reviewer of steps drafted by a weak model. The weak model executes read-only tool calls as it drafts, so that every step is grounded in real observations, and holds the first action that would modify the environment. The strong model then verifies the drafted segment in a single prefill pass, commits the longest prefix it judges semantically valid, and repairs the first rejected step. Because verification replaces autoregressive decoding with parallel prefill, the strong model decodes only short verdicts and occasional repairs rather than every step. On $τ^2$-Bench, SpecAgent comes within one point of the strong model's success rate while roughly halving memory traffic and wall time, and on AutomationBench and VitaBench it recovers 44-75% of the quality gap while lowering both. In an edge-cloud deployment on MCP-Atlas with three cloud models, it closes 53-75% of the weak-strong quality gap while the strong model generates at most half as many tokens. These results suggest that a strong model need not author every step of an agent: reviewing grounded drafts retains most of its quality while cutting both latency and memory traffic.

---

### Can Visual Generation Expand What Unified Multimodal Models Know?

Authors: Wenkai Li, Wenyi Hong, Zhuoyi Yang, Jie Tang
Published: 2026-10-15
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2610.21459v1

Unified multimodal models (UMMs) receive image-generation supervision that exposes them to visual information not fully documented in text. Can learning to generate images expand what pretrained models know? We introduce Knowledge Transfer Probing (KTP), a controlled protocol that supplies new knowledge through image-generation training and tests its accessibility through text-only question answering. Across seven knowledge categories and three UMMs, we observe direct but uneven transfer from visual supervision to language. Motivated by these observations, we successively introduce Textual Alignment and Interleaved Image--Text Alignment, which connect generation and answering through shared knowledge and interleaved responses, respectively. Guidance on selected entities can improve knowledge access on other entities without QA supervision, with additional gains from interleaved alignment. Further analysis shows that knowledge correctly reproduced in images is often more accessible through text, although substantial gaps remain between the two forms of access. These findings support visual generation as a source of knowledge beyond textual supervision, and motivate joint investigation of training data design and model architecture to make this knowledge more broadly accessible.

---

### Translation Circuit Discovery and Targeted Optimization for Low-Resource Multilingual Translation

Authors: Atai Waris Khan, Abdullah Mazhar, Raghu Kumar, Md Shad Akhtar
Published: 2026-10-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.21456v1

Recent multilingual large language models achieve strong translation performance, yet the internal mechanisms responsible for low-resource multilingual translation remain insufficiently understood. In this paper, we study translation circuits in multilingual decoder-only LLMs for Hindi-to-Urdu and Hindi-to-Sindhi (Devanagari). We propose TITAN, a mechanistic framework that combines causal intervention, sparse feature decomposition, and targeted preference optimization to identify and optimize crucial translation components in the transformer. Unlike conventional full-parameter fine-tuning, TITAN restricts optimization to sparse, causally important circuits, enabling scalable and parameter-efficient adaptation while updating fewer than 5% of model parameters. Experimental results show that TITAN achieves BLEU improvements of 33.75% on Hindi-to-Urdu and 45.86% on Hindi-to-Sindhi over the strongest multilingual baselines. Human expert evaluation further confirms substantial gains in adequacy and fluency across both language pairs. Additional analyses reveal that multilingual translation is implemented through sparse, structured circuits operating over a shared semantic subspace rather than through an English-centric pivot representation. Overall, our findings demonstrate that mechanistic circuit discovery can directly improve low-resource multilingual translation while providing interpretable insights into multilingual transformer behavior.

---

### CarryOn: A Dual-Loop Harness for Personalized and Reliable Robot Assistance

Authors: Zixuan Wang, Yuqi Liu, Yuxin Chen, Sengqiao Yang, Jinhui Ye, Pengguang Chen, Changsheng Lu, Shu Liu, Bei Yu, Jiaya Jia
Published: 2026-10-15
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2610.21453v1

While generalist vision-language-action (VLA) models have enabled diverse open-world manipulation, real-world robotic assistance requires two critical capabilities they currently lack: personalization and reliable execution. First, executing an instruction like "make me a sandwich" requires grounding subtask decomposition in persistent user preferences rather than relying on a single generic solution. Second, reliable deployment demands explainable safety assurance that proactively prevents hazards and gracefully recovers from occasional physical failures. To address these gaps, we present CarryOn, a dual-loop harness designed to augment a frozen VLA policy. The planning loop maintains persistent user-level and scene-level context that is continually grounded against new observations and revised through interaction, enabling personalized task selection and execution grounding across conversations and changing scenes. The execution loop actively supervises policy rollouts, shielding actions from predicted hazardous contact. When execution fails, the system invokes reusable control-based recovery skills that restore task progress and are refined through reflection on earlier failures. On a real robot and in simulation, CarryOn dispatches preference-consistent subtasks across users and scenes, reduces the violation rate of an already safety-finetuned VLA from 52.6% to 6.1%, and increases recovery success from 13% to 80% when refined skills are reused.

---

### Full-Duplex Interaction with Speech, Expressions and Gestures

Authors: Siyin Wang, Wenyi Yu, Terumi Chiba, Xianzhao Chen, Xiaohai Tian, Jun Zhang, Lu Lu, Chao Zhang
Published: 2026-10-15
Categories: eess.AS, cs.AI, cs.CV, cs.SD
arXiv: https://arxiv.org/abs/2610.21452v1

Human face-to-face conversation requires coordinating speech, gestures and expressions across both speaking and listening. We present ELLSA 2, an end-to-end full-duplex dialogue model that jointly optimizes speech interaction and streaming gesture-expression generation. An autoregressive, chunk-wise synthesizer combines pretrained acoustic features with distinct listening and speaking hidden states from the dialogue backbone and speech synthesizer, enabling continuous non-verbal generation even when the model is verbally silent. To translate dialogue understanding into vivid semantic gestures, we introduce contextual semantic calls and template guidance, separating whether to invoke an available semantic gesture from how to realize it. We also establish a curated data and evaluation pipeline for dialog-aware co-speech gesture generation and investigate reference-based multimodal large language models (MLLMs) as automatic judges. Experiments show that ELLSA 2 remains highly competitive with open-source full-duplex speech interaction models and outperforms cascaded baselines across dialog-aware gesture and expression metrics. Semantic template guidance further significantly improves semantic gesture quality. Strong system-level correlations with human judgments support these reference-based scores as useful preliminary metrics for full-duplex and semantic gesture assessment. Together, these results advance dialogue modeling from spoken responses toward coordinated multimodal interaction.

---

### PET Quantification-Preserving Registration for Longitudinal Whole-Body PSMA PET/CT

Authors: Fryderyk Kögl, Anna Reithmeir, Daniel M. Lang, Emily Chan, Rickmer Braren, Julia A. Schnabel
Published: 2026-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.21451v1

We adapt the diffeomorphic coarse-to-fine LapIRN architecture for longitudinal whole-body PSMA PET/CT registration in the Learn2Reg 2026 PSMAReg challenge. The method combines affine pre-registration, multi-modal deformable registration, and test-time instance optimization. We further introduce PET biomarker preservation losses for metabolic tumor volume (MTV) and total lesion glycolysis (TLG), including Jacobian-based constraints, and a per-structure rigidity regularization for skeletal structures. The submitted configuration achieved 81.0% DSC and 6.17 mm HD95, with MTV and TLG errors of 3.3% and 3.3%, respectively, on our evaluation protocol. Code is available at https://github.com/koegl/psmareg.

---

### X-Fly: Learning to Reach and Stop in Full-Chunk Aerial Vision-Language Navigation

Authors: Ruibin Ju, Ruifeng Cai, Min Xu, Lin Wang
Published: 2026-10-15
Categories: cs.RO, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2610.21450v1

Aerial vision-language navigation (VLN) agents built on large vision-language models are expensive to query. Executing a complete predicted action chunk before replanning amortizes this cost, reducing model inference from 195 to 42 ms per executed waypoint for our policy. It also moves the states at which the policy is queried away from expert demonstrations, which supervise neither recovery from these states nor termination at the learner's own arrival. On OpenFly test-seen, no-stop failures account for 47.78% of full-chunk behavior cloning (BC) outcomes. We present X-Fly, a staged training framework for full-chunk aerial VLN. Recovery DAgger labels learner-visited decision states with smooth chunks that reconnect to future expert segments and with STOP at the first in-region state. Flow-GRPO then jointly refines the chunked flow controller and a Bernoulli STOP policy from same-task closed-loop outcomes, supplemented by outcome-verified stopping supervision. With eight controls per decision, X-Fly reaches 74.18% SR on test-seen and 51.73% on test-unseen, compared with 16.45% and 18.43% for full-chunk BC and 32.04% and 29.46% for DreamFly.

---

### Incentivizing Tool-Use Reinforcement Learning for Post-Arrival Emergency Care Prediction

Authors: Pengfei Hu, Chenwei Wu, Qiao Jin, Jun Deng, Zhiyong Lu, Liyue Shen, Yue Ning
Published: 2026-10-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.21449v1

Large language models (LLMs) can reason over both structured measurements and free-text records, which makes them attractive for emergency department (ED) prediction. However, most existing LLMs still fall short of conventional ML methods like trees on EHR-based prediction tasks. Our controlled analysis traces this gap to two weaknesses: LLMs do not select informative features, and they misjudge what numerical values imply for risk even when given the right features. We propose TIR-EC, a tool-integrated reinforcement learning framework that addresses both. TIR-EC exposes EHR feature groups as tools the LLM can call. It trains the LLM with rewards from a gradient-boosted tree teacher, which provides a reference set of informative tools and a graded risk target. TIR-EC also distills task-specific clinical skills into the model weights through a reverse curriculum that gradually removes the skills from the prompt during RL process. Evaluation on three clinical prediction tasks shows that our 4B agent achieves the highest macro F1 of all compared models, outperforms conventional ML baselines, and is competitive with much larger frontier LLMs. Further analysis shows that TIR-EC selects more useful evidence with fewer tool calls and combines measurements more effectively.

---

### V-SHARE: Provable Convergence Guarantees for Advantage-based Algorithms

Authors: Kintan Saha, Hamed Masoudi, Xinyi Sheng, Dominik Baumann, Joni Pajarinen, Arsenii Mustafin
Published: 2026-10-15
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2610.21448v1

In reinforcement learning, advantage-based value-learning methods, unlike standard Q-learning, share information across actions by decomposing the action-value function into a state-dependent value component and action-specific advantages. While this mechanism has proven effective in both tabular and deep reinforcement learning, its theoretical understanding remains incomplete. We introduce V-SHARE, an advantage-based value-learning algorithm that combines cross-action value sharing with an importance-weighted Bellman-residual correction. To our knowledge, we provide the first complete theoretical characterization of an advantage-based algorithm, including both asymptotic convergence and non-asymptotic finite-sample guarantees. We identify a regime in which V-SHARE mitigates the rare-action bottleneck of asynchronous Q-learning and uncover a contraction--variance tradeoff between stronger deterministic contraction and increased importance-weighting noise. Motivated by this tradeoff, we develop decreasing residual-preconditioning schedules that combine faster early contraction with lower asymptotic noise. We further develop a two-timescale analysis that removes the single-timescale residual-weight threshold while preserving convergence guarantees. Experiments on discrete Markov decision processes (MDPs) and deep reinforcement-learning benchmarks corroborate our results.

---

### SITAR: A Situational Distortion Metric for Automatic Speech Recognition Evaluation

Authors: Mingzhe Lu, Jinhao Liu, Yunpeng Li, Hang Su, Lichun Fan, Jian Luan
Published: 2026-10-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.21440v1

In automatic speech recognition (ASR), transcription errors with similar lexical or semantic discrepancies can have markedly different consequences for the situation conveyed by speech. Capturing these differences requires not merely contextual assessment, but an understanding of what the spoken discourse describes, establishes, or seeks to bring about. However, relying on LLM judges introduces computational cost and scoring variability. We introduce SITAR, a situational distortion metric for ASR, realized through a comprehensive end-to-end construction framework. Specifically, this framework aggregates situational severity and cumulative extent into a unified score via a bounded recursive formulation. Using targets derived from this formulation with limited offline LLM support, we train SITAR as a lightweight BERT-family regressor that scores reference-hypothesis pairs in a single forward pass, entirely free of any prohibitive runtime costs. Recognizing that introducing a new metric demands rigorous justification, we formalize a principled validation protocol spanning both extrinsic validity, assessed at macro and micro levels, and intrinsic scorer reliability. The former, evaluated across diverse datasets and models, demonstrates that SITAR reliably tracks broad capability scaling while providing orthogonal diagnostic utility, whereas the latter, examined on a purpose-built controlled benchmark, confirms the operational soundness of the scoring instrument itself. Through systematic validation, we demonstrate that SITAR holds strong potential as a practical, lightweight complement to existing ASR metrics. We will release the full recipes (code, model weights, dataset, etc.) after the internal review to support community research.

---

### Each Reward to Its Relevant Tokens: Reward-Specific Token-Level Credit Assignment for Multi-Reward RL

Authors: Skylar Zhai, Haonan Wang, Zhining Liu, Linxin Song, Xuwei Ding, Jingcheng Liang, Jian Kang
Published: 2026-10-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.21439v1

Language models are increasingly trained against several verifiable rewards at once, such as the correctness and the format of a tool call, or the individual constraints of a complex instruction. Reward-decoupled normalization (GDPO) normalizes each reward separately so that different reward combinations keep distinct advantages, but it still spreads every reward's advantage evenly over the whole response, although each verifier checks only a few positions. We propose MRTPO, which assigns the advantage of each reward to the tokens relevant to it, using the information its verifier checks, without auxiliary models or token-level annotations. For each reward, the policy replays its own response with and without that reward's verifier information, and the per-token Jensen-Shannon distance between the two next-token distributions measures each token's relevance and reassigns the advantage. On text-to-SQL, multi-constraint instruction following and tool calling, MRTPO converges faster and achieves better performance than the compared methods.

---

### RLDF: A Region-Level Deepfake Dataset and Benchmark for Partial-Face Manipulation Detection

Authors: Shukesh Reddy, Abhijit Das
Published: 2026-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.21438v1

Existing deepfake detection models are built upon manipu- lated images that are tampered with either exclusively fully swapped or fully synthesised faces, which leads us to an open question: Can off-the-shelf deepfake models detect manipulation effectively while tampering is confined to a local facial sub-region? To fill this gap, we introduce RLDF (Region-Level Deepfake), the first dataset for region-level deepfake evaluation. Employing the proposed region-aware partial swap synthesis model, we generate over 2M par- tial face-swap images by using eight face-swapping meth- ods. Altogether, we considered seven face regions, among which there are four discrete regions (eye, nose, mouth and eyebrow) and four composite facial regions (eye and nose; eye, nose and mouth; eye, nose, mouth and eye- brow; and full face). In addition, we define three evalu- ation protocols and benchmark 12 state-of-the-art detectors across the five popular standard cross-dataset evaluations, DF40, and the proposed RLDF, providing a comprehen- sive audit of where and why existing detectors underper- formed. Our evaluation reveals that existing detectors fail to generalize consistently across partial facial regions, re- sulting in an overall drop of 10.5% AUC and 10% accu- racy under region-level evaluation. Further, we propose a mask-guided cross-attention model as a baseline approach that can effectively detect region-level manipulation. The proposed dataset, code, and checkpoints are available at https://github.com/RLDF-Dataset/RLDF.

---

### HyCo: Hybrid Drafting for Cost-Efficient Mobile-Cloud Speculative Decoding

Authors: Hanbin Bae, Heejin Choi, Joohyung Lee, Byoung Jin Choi, Sangjun Park, Hoon-Young Cho
Published: 2026-10-15
Categories: cs.CL, cs.DC, cs.LG
arXiv: https://arxiv.org/abs/2610.21436v1

Device-cloud speculative decoding reduces server computation, but growing a deep draft tree with a small language model (SLM) requires repeated passes on a mobile neural processing unit (NPU). We present HyCo, which assigns depth to the server model's native multi-token prediction (MTP) head, executed on the device, and alternative branches to one SLM pass. The server returns the hidden state, input embedding, and key-value entries needed by the head instead of executing its sequential steps. Quantization, a restricted vocabulary, and a 1K-token window fit both drafters to the NPU. An ε-threshold rule additionally relaxes exact preservation of the verifier's sampling distribution. In single-client runs with a Galaxy S26 Ultra over LTE/5G, HyCo reduces server GPU time per output token relative to server-side MTP self-speculation by 38.6% on Spec-Bench and 29.2% on 32K-token summarization. With the same acceptance rule, three Spec-Bench runs per system show 9.0 percentage points more saving and 1.9x delivery speed than an SLM-only drafter. HyCo differs from Cloud+MTP by +0.2 judge-score points (paired 95% CI: -0.9 to +1.3); exploratory translation favors SpecEdge-ε. Without relaxation, HyCo exact saves 27.7% and 11.9% on the two datasets.

---

### Policy-Aligned Predictive Verification for Adaptive VLA Action-Chunk Execution

Authors: Minkyu Kim, Junhoo Lee, Seungyeon Kim, Suhyun Jeon, Baekseung Kim, Donghoon Han, Nojun Kwak
Published: 2026-10-15
Categories: cs.RO, cs.LG
arXiv: https://arxiv.org/abs/2610.21434v1

Vision-language-action (VLA) policies generate action sequences that reduce repeated inference, but deciding how much of each sequence to execute is critical to task success. Existing adaptive methods make this decision using generation stability or prediction agreement, yet these signals do not establish whether executing a candidate prefix preserves the ability to complete the task. We introduce a policy-aligned predictive verifier (PAV) that anticipates the consequences of candidate action prefixes and evaluates their compatibility with successful continuation before execution. Rather than using future prediction to generate actions, our method evaluates existing proposals in the VLA's internal task-conditioned representation space. To learn local judgments from terminal task outcomes, we combine trajectory-level survival supervision with a localization prior that preserves useful behavior within failed rollouts. The resulting validity scores guide execution-horizon selection. Evaluations with pi_0 and pi_0.5 across LIBERO, RoboTwin 2.0, and real-world manipulation show improved success-query trade-offs. These findings point toward a different role for future prediction in robotics, using it to assess how far to trust a policy's proposed actions rather than to generate new ones.

---

### ManiFusion: Unlocking the High-Throughput Generation via Superposition in Manifold Space

Authors: Minkyu Kim, Baekseung Kim, Junhoo Lee, Jangho Kim, Nojun Kwak
Published: 2026-10-15
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2610.21433v1

Diffusion models achieve high-quality image generation but remain computationally expensive due to iterative denoising across many timesteps. Existing acceleration methods mainly reduce per-sample latency, but gains along this axis are becoming saturated. We instead explore an orthogonal throughput-oriented direction by processing multiple samples within a single denoising evaluation. To this end, we propose ManiFusion, a backbone-agnostic framework for multi-sample generation through fused-space computation. ManiFusion jointly processes multiple samples by fusing them before the denoising backbone and separating them afterward through unfusion. We provide a geometric perspective on how multiple samples can share a fused representation while retaining the information needed to guide their individual generation trajectories. To better align fusion allocation with denoising stages, ManiFusion uses Trajectory-Fusion Scheduling (TFS), which dynamically adjusts fusion factors throughout sampling. ManiFusion generalizes across diffusion families, including both U-Net and transformer backbones in pixel and latent spaces. We further show that ManiFusion composes with existing acceleration methods and reaches throughput regimes unattainable by prior approaches with minimal quality degradation.

---

### Learning from Interaction Experience via Localized Context Distillation

Authors: Zhezheng Hao, Yongkang Yang, Xilin Xia, Jiarui Yu, Yi Liu, Fanjunduo Wei, Peijie Dong, Tianfu Wang, Qiang Lin, Can Wang, Hande Dong, Jiawei Chen
Published: 2026-10-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.21427v1

Learning from interaction experience is essential for enabling large language models to continually improve during deployment. Context distillation offers a promising path: privileged information extracted from experience is provided to a teacher, whose behavior is then distilled into a student model that has no access to it. However, both existing forms of context distillation have limitations. Off-policy context distillation trains the student on teacher-generated trajectories and thus suffers from exposure bias; whereas on-policy context distillation trains on the student's own rollouts, whose states are often uninformative and fail to convey behaviors the student cannot yet produce. To resolve this dilemma, we introduce Localized Context Distillation (LoCD). LoCD first localizes the critical spans of a student trajectory that require revision. The teacher then regenerates only these spans from the student's own prefix, and the student is trained on the regenerated segments. LoCD thereby concentrates learning on the most informative states while keeping exposure bias low. Extensive experiments across math reasoning, code generation, and agent tasks demonstrate that LoCD consistently outperforms strong baselines and achieves more stable training with smaller and sparser parameter updates.

---

### Do Agents Need a New Kind of Paper? SPRA: Structured Paper Representation for Agents

Authors: Yutong Leng, Haojiong Chen, Fukai Shang, Xiaoyang Wang, Mindong Liu, Runyuan Ma, Jiantao Qiu
Published: 2026-10-15
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2610.21424v1

Scientific agents must connect research problems, methods, and findings dispersed through narrative articles. We introduce SPRA (Structured Paper Representation for Agents), a paper-level representation of persistent research objects and typed relations. Its empirical-AI profile organizes Problems, Contributions, Components, ExperimentSetups, Measures, and Findings for querying, traversal, and reuse. Selected paper-level citation relations record dependencies, component use, and comparisons with prior work; source locations support verification. We instantiate SPRA across more than one million AI papers, with 19.95 million research units and 24.07 million internal relations. Evaluations access SPRA through Schema-RAG with task evidence fixed before inference. Across seven subfields, SPRA improves source-conditioned scientific QA by 0.381/5 over passage retrieval while remaining close to Full Compact (0.078/5 lower on average). In directed cross-paper reasoning, qualification improves by 0.184/5 over passage retrieval; Top-5 synthesis shows mixed quality effects. Across all paired RQ2 tasks, including Top-5, input+output tokens decrease by 28.5% relative to passage retrieval and 95.3% relative to Full Compact. In idea generation, a 0.067-point lower Overall score than Full Compact accompanies 93.7% fewer input+output tokens. Together, these results support SPRA as a usable representation of scientific content and a foundation for research workflows that connect, inspect, and reuse paper-level research objects. The SPRA resource is accessible through the SciVerse scholarly-data platform.

---

### Where, How, and When: Query-Guided Grounding for Video Understanding

Authors: Yogesh Kumar
Published: 2026-10-15
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2610.21422v1

Understanding video content requires reasoning at multiple levels of granularity, from identifying objects to interpreting their interactions and localizing when specific actions occur. This thesis studies three query-guided grounding tasks that answer where key objects are (object-level grounding), how they interact (relationship-level grounding), and when specific moments occur (moment-level grounding). For object-level grounding, we present QDETRv, a query-guided extension of the Detection Transformer for one-shot localization of unseen objects in videos, which combines query-context fusion, a memory module for temporal consistency, and unsupervised pretraining on synthetic object trajectories. We further propose the Temporal Object-Aware Vision Transformer (TOViT) for few-shot video object detection, which builds on a language-aligned open-set vision encoder and propagates high-confidence object features across frames. For relationship-level grounding, we introduce few-shot referring relationships in videos: given a (subject, predicate, object) query and a few support videos sharing the predicate, the entities are localized by optimizing a T-partite random field using a meta-learned relation network with query-conditioned translational embeddings, Global Semantic Aggregation, Local Localization Aggregation, and belief-propagation-based message passing. For moment-level grounding, we propose the Moment Alignment Transformer (MATR) for video-to-video moment retrieval, which uses dual-stage Dynamic Time Warping for pre- and post-fusion alignment, learnable queries for boundary prediction, and self-supervised pretraining with temporal augmentations; MATR also extends to text-to-video moment retrieval with performance comparable to, or better than, the state of the art. These contributions advance query-guided video understanding across spatial, relational, and temporal grounding.

---

### What Does History Add? Calendar Controls and Information-Timing Audits for University Trajectory Forecasting

Authors: Zepei Cao
Published: 2026-10-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.21419v1

We audit the predictive value of historical summaries in a rule-based university trajectory simulator. Seventeen ridge specifications and persistence separate current plans, past-state and past-plan summaries, and calendar-only history-length indicators. Across training, validation and two family-held-out evaluations, we reconstruct 16,750 routes and 804,000 monthly records. On the original 40-family set, six-month history lowers six-step normalized RMSE from 0.159234 to 0.151522, but its difference from a length-only control is -0.000895 (descriptive paired 95% interval (-0.001957,0.000248)). Fixed weights on 30 families unused in identified prior tasks reproduce this pattern: 0.156480 to 0.150074 versus current-state prediction, but -0.000558 (-0.001783,0.000728) versus the length control. These uncertain comparisons do not generalize to all-history summaries, which improve on their own calendar control. Exploratory decomposition finds clearer preparation-index and funds benefits, whereas fatigue dominates the six-month model's loss and has an uncertain length-controlled benefit. Moreover, 28.20% of its six-step fatigue predictions violate the simulator's (5,90) support. We document family dependence, prior exposure, strict temporal indexing, matched recursive references and independent numerical replay. The task conditions on recorded future plans; it does not evaluate real-student forecasts, causal action effects, autonomous planning or language-model memory. This is an evaluation audit, not a new memory architecture.

---

### Learning to Forecast on Multiple Spatiotemporal Hierarchies

Authors: Valentina Moretti, Cesare Alippi, Andrea Cini
Published: 2026-10-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.21414v1

Hierarchical forecasting exploits aggregation structures that expose multiple views of the same underlying spatiotemporal forecasting problem, while ensuring coherence among forecasts. Individual series provide fine-grained information, while progressively coarser aggregates reveal temporal and spatial patterns at different scales. In the associated deep learning architectures, the hierarchy determines which aggregate series are available and how they are processed together with individual series (e.g., through reconciliation or message-passing operators). Different hierarchies thus provide distinct learning signals and inductive biases for forecasting the same collection of time series. Nonetheless, existing architectures are typically trained on a single, often fixed, structure. In this work, we propose a graph deep learning framework that leverages variations across hierarchies as multi-task regularization. We show that jointly learning across these structures can reduce over-specialization to any single hierarchy and improve forecasting performance. Indeed, training across hierarchies provides an inductive bias toward representations that are useful across different structures, and as such, generalize better. Making forecasts coherent with the aggregation constraints for each sampled hierarchy is computationally expensive: to complement the framework, we propose a novel operator-based on a top-down approach-that produces coherent forecasts with linear time and space complexity w.r.t. the hierarchy size. Experiments show that our approach improves forecasting accuracy over training on a single structure and is competitive with current state-of-the-art methods.

---

### JevAgentHarness: Benchmarking, Deploying and Training Decision Models That Share Control with LLMs

Authors: Kunlun Zhu, Tao Feng, Xu Han, Heng Wang, Ling Yang, Xiangru Tang, Jiaxuan You, Heng Ji
Published: 2026-10-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.21412v1

Large language model (LLM) agents now fix software, operate computers and serve customers, but their harnesses, the programs that run them, call a large LLM at every step, which makes long tasks slow and costly. Most of these calls end in a multiple-choice decision, such as which tool to call next. Decision models such as Jev answer these questions directly, at a fraction of an LLM call's time and price. We ask how a harness can delegate these decisions to a decision model with little loss of success. To evaluate decision models in agentic tasks, we build AgentDecisionBench, which tests them from isolated questions up to control of a running agent, on public benchmarks and our DecisionGym environment. The decision model most accurate on isolated questions solved only 69.5% of agent tasks, and without a fitted confidence threshold, delegating tool choices lowered success by 19.0 points. Building on these findings, we then design JevAgentHarness, which fits this threshold for each choice on the agent's own trajectories and lets the LLM decide below it. Because existing decision models never see the states an agent reaches after its own mistakes, we train AgentDecision-4B, an open 4B model, on such states with Jev's answers as labels. On tasks unlike its training data, the agent solved 91.5% of them with AgentDecision-4B and 82.0% with Jev. On tasks like their training data, 4B models trained this way made agents 81.1-89.0% cheaper and up to 2.5 times faster, without losing 3 or more points of task success. The models, data, and harness will be released at https://github.com/JevAgentHarness/JevAgentHarness.

---

### Jev-LiteMAS: Separating Decisions from Generation in Multi-Agent Workflows

Authors: Kaixiang Wang, Zhaijiacheng Zhou, Jiong Lou, Jie Li
Published: 2026-10-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.21411v1

Multi-agent LLM systems rely on generative models for expert execution, workflow planning, and artifact review. Yet many coordination operations require only bounded decisions, such as selecting the next expert or judging artifact quality. Profiling three representative MAS frameworks, we find that routing and review account for 31.7-43.5% of generative-LLM tokens. However, replacing these operations with low-cost decision models introduces two interface gaps: generative planners produce execution plans and handoff instructions (planning gap), while reviewers provide actionable feedback for repairing flawed artifacts (review gap), which bounded decisions alone cannot provide. We introduce Jev-LiteMAS, a multi-agent framework that bridges both gaps by combining a lightweight decision model (Jev) with generative execution and feedback. To address the planning gap, Jev selects experts dynamically from the task and prior expert outputs, using accumulated context to ground subsequent execution without a pre-generated trajectory. To address the review gap, Jev screens intermediate artifacts against task criteria: passing artifacts proceed directly, whereas flagged ones undergo LLM re-review for acceptance or corrective feedback. Across four benchmarks and two backbones, Jev-LiteMAS reduces generative-LLM tokens by 12.7-54.6% over LAS, maintaining accuracy within 1.34 percentage points and lowering latency in seven of eight settings. Grounding routing in substantive expert outputs prevents up to 18.0 points in accuracy loss.

---

### CLAD: Keypoint Matching Using Global Line Correspondences

Authors: Masaki Satoh
Published: 2026-10-15
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2610.21409v1

Traditional keypoint descriptors, such as SIFT (Scale-Invariant Feature Transform) and ORB (Oriented FAST and Rotated BRIEF), are computed from local image patches. They may be unreliable in scenes with repetitive patterns or weak textures, where patches at different locations can look similar. We propose the Contextual Line-Assisted Descriptor (CLAD), a keypoint matching method that addresses this problem by using global geometric context from line correspondences. CLAD represents each keypoint with a vector whose elements indicate its proximity to matched lines. It can therefore use the keypoint's spatial relationships to the lines in the scene. We use HOME (Hough-space One-dimensional Matching of Extrema) to detect both clear and weak linear structures and to establish enough line-to-keypoint associations to represent this context. Evaluations on the TUM RGB-D SLAM dataset and outdoor video sequences show that CLAD provides geometrically consistent matches that complement those obtained with traditional local descriptors. In repetitive scenes, where local descriptors may not distinguish similar patches, CLAD uses global structure to improve matching reliability. The method is computationally lightweight and practical to implement.

---