# Research Papers — 2026-10 · bundle page 134 of 156

> Full-text markdown of papers #6651–6700 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/134
[← Previous bundle](https://aipod.dev/papers/archive/2026-10/page/133.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-10/page/135.md)

### F$^2$ SLAM: Turning Feed-Forward Geometry into Persistent Factors for SLAM

Authors: Zhisong Xu, Fan Zhu, Jiawei Qian, Ziyu Chen, Zhenjun Zhao, Javier Civera
Published: 2026-10-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.05207v1

Feed-forward 3D models provide strong multi-view geometric priors, while on- line simultaneous localization and mapping (SLAM) relies mainly on local mea- surements and can accumulate drift over long sequences. Existing attempts to combine the two typically treat feed-forward predictions as an external geomet- ric state that is aligned or fused with the online estimate after the fact, which keeps broader multi-view evidence outside the optimizer that refines the SLAM state. We present F2SLAM, which instead converts feed-forward geometry di- rectly into optimization-native target-weight measurements attached to a persis- tent dense factor graph. A high-frequency stream maintains local tracking con- straints and graph connectivity, while a low-frequency stream uses wider multi- view context to selectively refresh existing measurements after a state-consistency check. Both streams constrain the same poses, inverse depths, and optional cam- era intrinsics through a single dense bundle adjustment. Experiments on multiple benchmarks demonstrate consistently strong trajectory estimation and improved dense reconstruction in both calibrated and uncalibrated settings. Notably, the uncalibrated configuration reduces the average ATE RMSE from 0.030 m for the strongest feed-forward baseline to 0.002 m on the Replica dataset.

---

### Learning without Overwriting: A Theory of Self-Distillation and Supervised Fine-Tuning in Continual Reasoning

Authors: Shinichi Uemura, Taiji Suzuki
Published: 2026-10-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.05200v1

On-policy self-distillation (OPSD) of large language models (LLMs) has demonstrated the ability to improve reasoning capabilities while preserving previously acquired knowledge. Despite substantial empirical success, the dynamics of OPSD in continual reasoning remain incompletely understood. Modeling LLM reasoning as search over a directed acyclic graph, we provide a unified theoretical analysis of both the dynamics of post-training---OPSD and supervised fine-tuning (SFT) in continual learning---and the impact of pre-training on subsequent performance. Our findings establish three key insights with an optimization guarantee: (i) OPSD with hints from correct outputs enables continual learning without forgetting by sparse yet effective gradient descent updates induced by the hint structure. (ii) SFT on correct reasoning paths can lead to catastrophic forgetting due to dense updates along the training paths, which overwrite the information previously acquired. (iii) Diversity in pre-training is crucial for enabling a post-trained model to reach a correct output when a rollout starts from an intermediate state. Our results, supported by theoretical analysis, show that reliable continual reasoning depends on how post-training updates interact with the reasoning structure established during pre-training.

---

### Cross-Time Directional Selection in Diffusion Sampling

Authors: Dhia naouali
Published: 2026-10-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.05199v1

How strongly do the remaining diffusion-sampling steps amplify a perturbation at a late latent state? Standard measurements answer this question with newly sampled isotropic noise, even though perturbations encountered during sampling have already been transformed by earlier steps. We compare these two cases directly. For each trajectory, we transport a centered perturbation from an earlier step to a late state, then replay its direction at the same magnitude as a newly sampled isotropic perturbation; both then undergo the same remaining updates. Across the samplers we study, median paired shaped-to-fresh angular-gain ratios range from $1.14$ to $2.35$. Shaped angular gain exceeds its matched fresh counterpart in every trajectory in the original main cohorts. The same pattern appears when endpoint change is measured by latent RMS. The effect also appears in perceptual feature representations: earlier-sampling directions cause larger feature changes at the endpoint, even when the corresponding pixel-space change is comparable. Permuting shaped directions across trajectories weakens the effect, including within class, indicating that the advantage depends on alignment with the receiving trajectory as well as on shared directional structure.

---

### Same Predictions, Different Harms: Causal Auditing of Patient World Models

Authors: Yicheng Qi, Xiyi Xiong
Published: 2026-10-04
Categories: stat.ME, cs.AI
arXiv: https://arxiv.org/abs/2610.05198v1

Patient world models used for clinical trial simulation can agree on transition kernels and arm-specific risks, yet disagree on the fraction of patients harmed by switching treatment---the counterfactual quantity that matters for intervention-aware reasoning. We audit this reliability gap in a two-stage shared-response SCM: a categorical intermediate health state is followed by common terminal care. Under independent stages, the sharp harm interval has closed-form endpoints for at most three intermediate states, with an exactness boundary at four states. Declared dependence and response-mismatch budgets yield calibrated outer bounds when stage independence or complete mediation is relaxed; in a symmetric three-state model the entire sensitivity frontier is sharp, $(0,\min\{1/2,1/3+(ρ+δ)/2\})$, and shows exactly how budgets erase the gain over endpoint-only bounds. Two eight-variable response LPs propagate interventional uncertainty for finite-sample audits. Exact witnesses verify attainability. On public clinical simulators (EpiCare; sepsis), native configurations show little resolved stage dependence and no additional joint-compatibility gain over pairwise transport---honest negative results for reliability claims. All experiments are locally reproducible; guarantees remain conditional on the stated causal model. The results provide a concrete protocol for deciding when a patient world model is safe to trust for counterfactual harm.

---

### From Scientific Observations to Mechanisms: Benchmarking Hypothesis Generation by AI Scientists

Authors: Xiaxun Xie, Qingqing Long, Meng Xiao, Wei Ju, Yuanchun Zhou, Xuezhi Wang, Hengshu Zhu
Published: 2026-10-04
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.05197v1

Data-driven mechanistic hypotheses are essential to scientific discovery because they explain how underlying processes produce observed phenomena. AI agents and AI scientists increasingly support scientific data analysis. However, their ability to turn empirical findings into mechanistic hypotheses remains insufficiently examined. To address this gap, we introduce MechHypoBench, the first benchmark for evaluating whether AI agents and AI scientists can generate such hypotheses from empirical data. It combines paper-derived mechanisms from 14 scientific fields with real-world datasets containing 17.98 million records. The construction retains the observational complexity of empirical data while providing a specified underlying mechanism. Agents analyze the observations and propose open-form hypotheses. We develop an evaluation framework that assesses open-form mechanistic hypotheses through their consequences under withheld conditions. Experiments with general agents and AI scientists reveal a substantial gap between generated hypotheses and the underlying mechanisms.

---

### Measuring Learned Monotone Temporal Aggregation at Matched Admissibility

Authors: Yew Lee Tan
Published: 2026-10-04
Categories: cs.LG, q-fin.RM, stat.ML
arXiv: https://arxiv.org/abs/2610.05196v2

Risk regulation imposes directional constraints on scores; we adopt their strict per-input form -- the score monotone non-decreasing in every exposure input -- as a normative commitment. Deployed pipelines -- monotone hand-crafted aggregates feeding sign-constrained gradient boosting -- already satisfy it by composition, so constrained-versus-unconstrained comparisons price a guarantee the incumbent has for free. We instead hold admissibility fixed on both sides and measure what learning the aggregation is worth. Our instrument is a recurrent network whose state is classical risk statistics (an exponentially weighted moving average and a high-water mark with learned transforms), monotone by construction in every input and per MC-dropout sample. The central finding, by functional regression, is a subsumption boundary: a learned monotone channel reproduces the geometrically weighted separable family of hand-crafted statistics, one channel per member, to Spearman $ρ\ge 0.996$, approximates window statistics with measurable ceilings, and fails at consecutivity ($ρ= 0.924$) and time localization (0.628), both structural, and at the exposure floor (0.829), a learnability boundary. One explicit admissible basis repairs each failure (rank correlation 1.000). In or near the separable family, learned and engineered aggregation are substitutes, and the learned channel is never statistically behind at full sample size and specified capacity. Its advantages are incumbent-specific: a committed grid pays up to 0.019 AUC in decay regions it leaves uncovered (the learned channel stays within 0.004 of the strongest engineered consumer at every swept point); the highest-dimensional comparator degrades fastest with scarce data; and beyond the training support, grid-fed tree-ensemble scores go flat while a strictly increasing head keeps ranking. No single incumbent is dominated on all three axes.

---

### Long-MDR: Long-Context Reinforcement Learning for Multimodal Deep-Research Agents

Authors: On Tai Tang
Published: 2026-10-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.05195v2

The next generation of multimodal research agents must reason over long-lived research histories rather than short model completions. During a single task, an agent may repeatedly search the web, inspect visual evidence, revisit earlier hypotheses, and accumulate tens of thousands of tokens of multimodal context. Despite this trend, online RL for multimodal research agents remains largely confined to shorter contexts and interaction horizons. We push online RL training to 128k context and 75+ tool-interaction turns. To our knowledge, this is the first online multimodal deep-research RL study trained at 128k context, and the first trained with a 75 tool-turn horizon. Scaling to this regime exposes several practical limitations of conventional RL training. Early in training, weak policies make poor use of large interaction budgets, causing expensive rollouts with little reward improvement. Later, policy entropy can collapse before performance has saturated, prematurely ending useful learning. We introduce Long-MDR, a three-component training recipe designed specifically for this setting: On-Policy Distillation Warmup, Progressive Horizon Expansion, and Entropy-Triggered Rescue. Together, these techniques improve both the learning efficiency and stability of long-horizon RL, enabling continued gains in a regime where direct training is slow and costly. At a 50-turn evaluation budget, our RL-trained Long-MDR-9B ranks first on five of six benchmarks among the compared 7B-9B agents.

---

### Order Matters: Competition-Guided Query Ordering for RNN-Based Object Detection

Authors: Shengjian Wu, Li Sun, Yu Shangguan, Qingli Li
Published: 2026-10-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.05191v2

DETR-style detectors use one-to-one bipartite matching during training to assign object queries to ground-truth objects, enabling end-to-end set prediction without non-maximum suppression (NMS). However, without an explicit de-duplication procedure, multiple queries can still produce highly similar hypotheses for the same object, making training unstable and predictions less decisive. Inspired by the sequential ordering of NMS, we propose DETRNN, a plug-and-play module that turns unordered object queries into a competition-aware sequence for recurrent refinement. DETRNN builds an explicit confidence-and-similarity based order from prior predictions, then refines queries with an RNN along this order to model competition inside the decoder. This ordered recurrent refinement reduces redundant predictions, stabilizes optimization, and improves final detection accuracy. Experiments on multiple DETR-style detectors show consistent gains with comparable efficiency. Code repository: https://github.com/nigelwoo2008-coder/DETRNN.

---

### FORGE: Verification-Gated Behavioral Repair for Generative Language Models

Authors: Hsin-Ling Hsu, Min-Yu Chen, Nai-Chia Chen, Yan-Ru Chen, Yi-Ling Chang, Fang Yu
Published: 2026-10-04
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2610.05190v1

Generative large language models (LLMs) inherit undesirable behaviors from pre-training, including demographic bias and toxic generation, that often emerge only after deployment and affect a small subset of inputs. A repair should eliminate the identified defect, preserve the model's overall functionality and, ideally, provide correctness guarantees. Existing approaches address this only partially: gradient-based fine-tuning lacks per-instance guarantees and becomes unstable with few defect samples; model editing assumes explicit knowledge replacement rather than behavioral correction; and constraint-based repair is largely restricted to discriminative models with unique target outputs. We present FORGE, a framework for targeted behavioral repair of generative language models that separates defect localization, weight editing, and behavioral verification into independent stages. Its core is a repair abstraction that converts localized defective generation into explicit optimization objectives, enabling verification-oriented repair techniques to operate on autoregressive generation. FORGE is editing-mechanism agnostic: we instantiate it with (1) a constraint-based quadratic optimization method that provides per-sample repair certificates and (2) a null-space projection editor that minimizes interference with the original model distribution, both under the same localization and verification protocol. On five open-source LLMs, FORGE consistently achieves larger reductions in bias and toxicity than gradient-based fine-tuning with minor perplexity degradation. The two backends exhibit complementary performance across architectures, which a lightweight causal probe traces to where toxicity-related signals concentrate. FORGE also remains effective with only a handful of defective examples, where conventional fine-tuning often oscillates or fails to converge.

---

### On prediction from expert advice with more than five experts

Authors: Jeff Calder, Nadejda Drenska
Published: 2026-10-04
Categories: math.AP, cs.GT, cs.LG, math.OC
arXiv: https://arxiv.org/abs/2610.05186v1

We prove that no single rank ordered adversary strategy is globally optimal for the prediction with expert advice problem with six or more experts, in both the geometric stopping and finite time horizon settings. The proof is based on establishing a leading order correction when one expert moves far ahead of the others. This allows us to connect optimal strategies between $n$ and $j<n$ experts and utilize recent results on the exact optimality set for the five expert problem.

---

### Recurrent Latent Visual Search for GUI Grounding

Authors: Kaiyu Wu, Beichen Zheng, Weiyao Huang, Keze Wang
Published: 2026-10-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.05185v1

GUI grounding is a critical capability for GUI agents powered by vision-language models, helping them execute user instructions by locating the corresponding elements in screenshots. Single-step grounding struggles with small elements and dense layouts, motivating multi-step visual search. However, existing approaches commonly rely on textual reasoning misaligned with visual space or costly multi-round interactions with external visual tools. To make multi-step visual search an explicit spatial process within the model, we propose ReLaViS, which performs Recurrent Latent Visual Search in a single interaction round. At each step, a spatial search head uses the hidden state to query the screenshot's visual tokens, producing a spatial search distribution that explicitly represents the search focus. This distribution then aggregates the visual tokens into latent visual evidence, which is recurrently fed back as the next input embedding to condition subsequent search. We further introduce a GUI-aware coarse-to-fine inductive bias through trajectories constructed from flat element annotations, supervising search from the global interface through intermediate element groups to the target. Built on Qwen2.5-VL-7B, ReLaViS improves ScreenSpot-Pro accuracy by 3.1 percentage points to 56.3% with only a 3.5% increase in inference FLOPs and outperforms the matched single-step baseline on all five benchmarks.

---

### TIRMamba: A Thermal-Prior-Modulated State-Space Network for Sub-Million-Parameter Infrared Image Super-Resolution

Authors: Chun-An Lin, Tsung-Jung Liu, Yen-Chieh Ouyang
Published: 2026-10-04
Categories: eess.IV, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2610.05182v1

Infrared image super-resolution is currently led by Mamba-based networks with 26 to 37 million parameters, which are difficult to deploy on the airborne and handheld platforms where thermal imaging is most needed. This paper presents TIRMamba, a network with 896K to 910K parameters for single-channel thermal imagery. A Thermal Prior Highway computes gradient, local-contrast and spectral cues once at the input and, through one adapter per residual group, modulates a weight-tied bidirectional state-space trunk and gates its dual-scale detail branch; a tri-path reconstruction adds the learned residual to a bicubic radiometric baseline. Because the standard benchmark provides only 265 infrared training images and evaluates fusion products on full images, we train with a replay strategy: grayscale DIV2K pre-training followed by fine-tuning on 64-pixel patches drawn with equal probability from the infrared and natural corpora. At scale factor 4, TIRMamba matches the strongest protocol-trained methods on both official test sets with 29 to 40 times fewer parameters and 2.8 to 9.4 times lower latency; at scale factor 2 it gives the highest SSIM on both. A variant with prior-conditioned selectivity, TIRMamba-Rad, corrects a 3 dB raw-thermal failure of an intermediate size-invariant design and gives the best results at scale factor 4 on raw-thermal, unmanned-aerial-vehicle and independent-sensor test sets. Code and trained models will be released at https://github.com/julian135707/TIRMamba upon acceptance.

---

### AECG: Asymmetric Experience Consolidation and Governance In Multi-Agent Systems

Authors: Ao Tian, Jialong Liu, Daqi Zheng, Xin Sun, Mengting Li, Zhizhao Xiao, Zijian Huang, Honglei Wang, Zijian Hei, Yukun Yan
Published: 2026-10-04
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.05176v1

Large language model (LLM)-based multi-agent systems increasingly rely on memory to transform execution trajectories into reusable procedural knowledge. Yet repeated retrieval also makes memory errors persistent: memory pollution arises when outdated, weakly supported, or spuriously successful procedures become recurring components of future reasoning. Multi-agent execution introduces an additional structural risk. Scope collapse occurs when procedural knowledge escapes the coordination scope in which it was shown effective and is repeatedly reused at incompatible decision levels, allowing local errors to influence cascades of downstream decisions. Meanwhile, task-level failures provide ambiguous supervision because they rarely reveal which recalled knowledge was responsible. We introduce AECG, a framework for asymmetric experience consolidation and governance for multi-agent systems. AECG turns memory from static experience storage into a dynamic reliability-governance loop, preserving coordination scope and using multi-scale, confidence-aware reliability to detect degradation. It then combines degradation with downstream impact to prioritize high-risk knowledge under a bounded review budget, applies targeted interventions, and reactivates revised skills only after paired replay. Across three multi-agent frameworks and four benchmarks, AECG achieves the best score in 11 of 12 framework--benchmark settings and improves over the strongest competing memory method by as much as 10.23 percentage points; removing scope preservation reduces accuracy by up to 16.89 points. AECG thereby reframes multi-agent memory from passive accumulation into auditable reliability governance. Code is available at https://github.com/fenhg297/AECG

---

### Locality Sensitive Hashing for p-Exponential Kernels with Applications to Density Estimation

Authors: Barak Gorodissky, Tal Wagner
Published: 2026-10-04
Categories: cs.DS, cs.CG, cs.LG
arXiv: https://arxiv.org/abs/2610.05174v1

A kernel $k(x,y)$ is LSHable if there exists a locality sensitive hashing scheme $H$ such that $k(x,y)=\Pr_{h\sim H}(h(x)=h(y))$ for all $x,y$. This notion plays a key role in efficient kernel methods in high dimensions. In this work, we show that the $p$-exponential kernel $k(x,y)=\exp(-\lVert x-y \rVert_p)$ is LSHable in bounded regions for all $1<p\leq2$. Previously, this was known only for $p=1$. Our new "mosaic LSH" scheme is based on a Poisson hyperplane process with hyperplanes sampled as $\ell_1$-biased $p$-stable vectors, for which we develop efficient sampling procedures. As applications, our results yield new and efficient density estimation methods based on LSHability for those $p$-exponential kernels.

---

### Verification Trap: Understanding Test-Time Selection Failures under False Premises in Code Generation

Authors: Feng He, Hejia Wang, Linghao Meng, Ming Gao, Qiankun Li
Published: 2026-10-04
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.05170v1

Test-time compute has become a central way to improve code generation: systems sample multiple candidate programs and use verifier-visible evidence to select the final output. This paradigm implicitly assumes that the verifier provides a corrective signal independent from the generator. We challenge this assumption under misleading task premises. When the generator and verifier share a false premise, they become coupled through a mistaken belief: the generator produces premise-consistent shortcuts, while the verifier supplies evidence that fails to expose them. Consequently, the selector may choose a hidden-test-wrong candidate even when a hidden-test-correct program exists in the pool. We call this failure mode Verification Trap. Across three code-generation benchmarks and five code models, false premises consistently degrade first-sample correctness, reduce selector-chosen correctness after 64-sample test-time selection, and amplify recoverable mis-selection. Mechanistically, verifier-written tests inherit the premise-level blind spot, reshaping verifier-visible candidate space away from hidden-test correctness. These traces make Verification Trap predictable before hidden execution: a lightweight gold-free predictor using verifier-visible features reaches 0.846 AUROC. Our results identify decoupled evidence as a key mitigation axis: coupled scaling provides limited recovery, whereas premise-agnostic robustness auditors recover substantial oracle headroom.

---

### CreativeFlow: A One-to-Many Analogical Relation Transfer Method for 3D Asset Generation

Authors: Xuechen Li, Shuai Zhang, Nanxuan Zhao, Qing Chen
Published: 2026-10-04
Categories: cs.AI, cs.GR
arXiv: https://arxiv.org/abs/2610.05167v1

Inspired by cognitive science, we present CREATIVEFLOW, an analogical generation framework that explicitly models analogical divergent thinking to mitigate creative homogenization in text-to-3D pipelines. Our method derives a series of meaningful yet relationally similar source-target asset pairs, each featuring distinct geometric configurations. Expert evaluations demonstrate that our framework substantially enhances creative novelty and visual fascination. This workflow and its resulting assets establish a foundational dataset and benchmark for future relation-aware 3D model training.

---

### A Safe Action Is Not Enough: Feasible-Future Decoding for Vision-Language-Action Policies

Authors: Tu Nguyen, Matthieu Zimmer, Vu Anh Vu, Ziyi Wang, Jannik Hammel Nielsen, Xuebing Zhou, Haitham Bou Ammar
Published: 2026-10-04
Categories: cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2610.05166v2

A safe action is not necessarily a viable one. A frozen vision-language-action (VLA) policy can favor a locally admissible move that leaves no policy-supported route to safe task completion. We call this the feasibility-likelihood gap: likelihood ranks the next move, while feasibility depends on the futures it leaves open. To bring those futures into the decision, we derive the exact next-block marginal of the history-conditioned policy-environment trajectory law restricted to safe task completion. The derivation reveals a candidate-dependent feasible-future mass: its support records whether safe completion remains possible under the frozen continuation process, while its magnitude measures how much weighted safe-completion mass remains. Since exact evaluation is impractical online, we develop a selective finite-candidate approximation and establish conditions for recovering the best retained viable candidate. Our alarm-triggered, training-free reranker VICS-G lowers mean cumulative safety cost by 1.9%-57.5% across six Safety-CHORES settings while remaining within 2.5 percentage points of policy sampling in success and 0.82 steps in mean episode length. Our approach offers a promising and practical path toward safer task completion, grounded in an exact policy-relative target yet requiring neither policy retraining nor online rollouts.

---

### Blocking at the Boundary: Auditing Long-Horizon Agents against Staged Prompt Injection

Authors: Jingkai Liu, Yufei Han, Xiaoting Lyu, Wei Wang, Ting Yu
Published: 2026-10-04
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2610.05163v1

Long-horizon agents consume external content, invoke tools, and modify persistent state. Indirect prompt injection can exploit task-specific context, propagate across causally connected stages, and alter a consequential action while the workflow continues; we term this staged prompt injection. We build an automated, feedback-guided attack generation pipeline and apply it to Claude Code and Codex in their native runtimes. The confirmed attacks span eight workflow scenarios, seven attack goals, and six injection surfaces, showing that production agents are vulnerable to context-aware, multi-step injection over long horizons. Stopping such attacks requires a decision before each consequential action: input screening and completed-run evaluation cannot locate the intervention point, and existing pre-action methods use incompatible units and labels. We therefore formulate boundary action auditing: given initial context, a trajectory prefix, and a fully specified pending message or tool call, an auditor predicts Pass or Block before its effect occurs. Pairing attacked and benign executions yields a 479-pair, 3,112-unit benchmark. We further propose Path-Aligned Attribution (PAA), a training-free auditor that decomposes pending actions into operative elements and traces what supplied each value and guided each decision. PAA blocks only when the model attributes an unwarranted, material effect on an element to an attacker-reachable source that either provides unqualified steering or conflicts with visible evidence. Under full-benchmark fail-open scoring with Claude Sonnet 5, PAA reaches 86% Block recall at a 6-8% false-block rate (FBR), whereas ARGUS reaches 44-47% recall at 16-33% FBR. Under the same backend, on the tool calls that all three auditors natively support, PAA has higher recall and lower FBR than VIGIL and ARGUS; all paired 95% confidence intervals exclude zero.

---

### Memadapter: Counterfactual Adaptation Against Memory-induced Sycophancy

Authors: Ruqing Ning, Haibo Meng, Zhishang Xiang, Zerui Chen, Jinsong Su, Xin Wang, Qinggang Zhang
Published: 2026-10-04
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.05162v1

Long-term memory enables LLM-based agents to retain and reuse information across tasks and sessions, supporting personalization and long-horizon interactions. However, persistent memories can also induce sycophancy, causing agents to over-align with users' historical beliefs even when they are inaccurate, outdated, or inconsistent with objective evidence. Existing mitigation methods assume that memory-induced sycophancy originates from biased or incorrect memories and attempt to reduce this risk by filtering such memories at different stages of the memory pipeline. However, in the real world, objective and correct memories can still induce sycophancy, and the same memory can warrant different influence across different contexts. To this end, we propose MemAdapter, a novel framework that adaptively integrates retrieved memories to support objective and reliable reasoning. Specifically, MemAdapter consists of three components: (i) Counterfactual Induction, which leverages counterfactual reasoning to uncover the potential risk of retrieved memories; (ii) Context-Aware Reflection, which calibrates the inferential influence of each retrieved memory in light of the current task via self-reflection; and (iii) Evidence-Based Reasoning, which grounds the final response in appropriate evidence while preserving the legitimate influence of memory. Extensive experiments on three benchmarks demonstrate that MemAdapter consistently improves memory reliability across diverse scenarios. Our code is available at https://github.com/DEEP-JLU/MemAdapter.

---

### Beyond Instruction Following: Learning Grounded Skill-Following with Skill Contracts

Authors: Jianghan Shen, Zhenjie Liu, Yue Li, Jie Huang, Siqi Luo, Yiming Cheng, Yizhi Yao, Kaijie Zhang, Cheng Tang, Minghui Zhang, Ming Hu, Yirong Chen et al.
Published: 2026-10-04
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.05161v1

Instruction following typically enforces discrete, response-level requirements, whereas an expert-authored skill prescribes procedural requirements spanning multiple phases and environment interactions. Given such a skill, we train the executor to execute all required phases instead of focusing solely on the final answer. We therefore introduce Grounded Skill-Following, which requires an agent to execute a fixed, expert-authored skill across its required phases by grounding decisions in environment observations. To achieve verifiable procedural execution, we formulate each skill as a skill contract combining visible skill instructions with an explicit contract runtime. The runtime specifies required phases, admissible actions, permitted transitions, and accepted termination. This structure provides a dense, verifiable training signal throughout execution. We leverage this by introducing Verified Progress Credit, which assigns rewards upon the initial completion of contract milestones and aggregates them into the trajectory return to guide policy optimization. During rollout, the contract runtime continuously tracks state transitions to provide Contract-State Feedback, which indicates whether the latest action is accepted and guides the agent toward valid next actions. To measure procedural compliance, we introduce the Protocol Completion Rate (PCR), defined as reaching accepted termination through all required phases, and decouple it from the final Task Outcome. Jointly trained with our framework, Qwen3.5-4B achieves Protocol Completion Rates of 99.27% on Math and 99.96% on Search, while slightly outperforming original baselines in Task Outcome (82.95% and 46.61%, respectively). Controlled studies examine how skill instructions, training signals, and contract-state feedback affect both metrics, while withholding interventions evaluate behavioral dependence on observation content.

---

### Cross-Modal Contrastive Learning for the Retrieval of Immunotherapy-Associated Molecular Signatures from Histopathology

Authors: Sigrid Vila-Bagaria, Mar Teixidó, Miquel Piñol, Felip Vilardell, Robert Montal, Veronica Vilaplana
Published: 2026-10-04
Categories: cs.LG, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2610.05157v1

Gastric Adenocarcinoma is a leading cause of cancer mortality. Although "Inflamed/Non-Inflamed" subtypes have been proposed to predict immunotherapy response, their identification relies on a costly 10-gene RNA signature. We propose a Cross-modal Contrastive Multiple Instance Learning (CCMIL) framework for cross-modal retrieval, imputing these molecular signatures directly from standard Hematoxylin & Eosin (H&E) slides. By leveraging a supervised contrastive objective, CCMIL aligns visual morphological patterns with molecular phenotypes into a shared latent space. This establishes an interpretable search-by-case retrieval engine, enabling pathologists to query a whole slide image to surface transcriptomically coherent neighbors and approximate RNA signatures without genomic sequencing at inference. Our results demonstrate that this retrieval-first approach captures the continuous phenotypic spectrum of tumor inflammation and yields clinically interpretable attention heatmaps. Furthermore, the learned representation also supports competitive downstream classification, providing a practical molecular pre-screening strategy.

---

### Construction and Evaluation of Machine Learning Models for Near-Real-Time Fire Detection from MTG FCI Imagery

Authors: Asaf Vanunu, Boaz Nadler, Arnon Karnieli
Published: 2026-10-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.05154v1

Geostationary satellite observations are important for wildfire detection and monitoring. The current study evaluates machine learning models for MTG FCI near-real-time fire detection in 1- and 2-km spatial configurations and compares them with threshold-based algorithms. The models were trained and evaluated using VIIRS fire reference data across diverse ecological regions in Europe, Africa, and the Middle East. The key results are that 1-km models significantly outperform both their 2-km variants and operational threshold products. The constructed 1-km models achieved F1 scores higher by up to 0.36 compared to baseline products. Importantly, the 1-km models detected small fires with higher probability compared to competing models. Finally, the models robustly detected fires up to 260 min earlier than baseline products. To support opensource applications, our trained models are publicly available.

---

### R1A-PC: Physics-Guided Electromagnetic Inversion of Three-Dimensional Human Point Clouds in Complex Static Environments

Authors: Xudong Yuan, Ruyun Xu, Jingtai Yang, Xianzheng Sun
Published: 2026-10-04
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.05144v1

Recovering three-dimensional human geometry from electromagnetic measure?ments in a complex static environment is difficult because strong multipath responses from walls, floors, and other objects obscure the weak target per?turbation. We propose R1A-PC, a physics-guided method that reconstructs a 2048-point human cloud from paired complex fields measured with and without the target. Complex background subtraction emphasizes target-induced ampli?tude and phase changes, while the background field remains available as an environmental condition. A frequency-balanced discrete Born adjoint produces a three-dimensional spatial knowledge map. At each of two bounded deformation stages, the decoder combines complex measurement features, background fea?tures, and multiscale physical features queried at the current point coordinates; the second stage queries again after the first coordinate update. We analyze the residual of paired subtraction, the weighted normal-operator structure of the raw adjoint, and the feasible set of the predicted cloud. In a held-out background generated by full-wave simulation under a fixed acquisition geometry, R1A-PC obtains a squared Chamfer distance of 0.001434 m2 and an F-score of 0.963080 at 0.05 m. Compared with TopNet, the Chamfer distance decreases by 70.28%. Removing physical guidance or background subtraction increases the Chamfer distance by 242.06% or 241.18%, respectively. Experiments across background layouts and poses support the complementary roles of paired subtraction and position-dependent adjoint features.

---

### Arithmetic Actor Heads and Training Stabilization for Out-of-Distribution Reinforcement Learning

Authors: Yifan Zhang, Liang Zheng
Published: 2026-10-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.05143v1

Reinforcement learning (RL) policies can deteriorate under out-of-distribution (OOD) magnitude shifts. Starting from soft actor-critic (SAC) and its Bayesian Amnesic Piecewise-Robust (BAPR) predecessor, we study the causal-symbolic BAPR (CS-BAPR) family. The practical method combines six training-stabilization settings with alternative actor heads: a Neural Addition Unit (NAU) with a Neural Multiplication Unit (NMU)-inspired quadratic correction, a Kolmogorov-Arnold Network (KAN), or a multilayer perceptron (MLP) with rectified linear unit (ReLU) or hyperbolic-tangent activations.

---

### SemCam: Semantic Camera Motion Control for Video Generation

Authors: Janna Bruner, Omer Talmi, Ianir Ideses, Lior Fritz, Lior Wolf, Sagie Benaim
Published: 2026-10-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.05141v1

Controlling the camera relative to a moving subject in an existing video is challenging: behaviors such as maintaining a frontal view require the camera to adapt to the subject's changing position and orientation, making the desired trajectory difficult to specify in advance. Existing camera-controlled video-to-video methods typically rely on explicit trajectories or reference motions, which do not directly express these dynamic camera--subject relationships. We introduce semantic camera motion control, a novel video-to-video task in which a reference video and a target motion label specify the desired subject-relative camera behavior without an explicit target trajectory. Our method, SemCam, learns to realize this behavior while preserving source content. It combines shared-basis low-rank adaptation with motion-conditioned modulation, while a background-consistency loss encourages fidelity in regions visible in both reference and target videos. We construct 661 paired videos covering eight semantic camera behaviors and evaluate on a separate 109-scene benchmark using subject-relative motion metrics, appearance measures, and a user study. SemCam achieves a semantic-motion success rate of 68.6%, compared with 45.3% for Vista4D, the strongest evaluated baseline, while maintaining comparable subject identity preservation.

---

### AutoSciBench: Autonomous Benchmark Generation for Evaluating Scientific Agents

Authors: Dongki Kim, Namkyeong Lee, Surag Nair, Carl Edwards, Xiner Li, Edward De Brouwer, Jenna Lynn Collier, Sung Ju Hwang, Gabriele Scalia, Ehsan Hajiramezanali
Published: 2026-10-04
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.05140v1

As agents rapidly evolve, existing benchmarks can become saturated, limiting their ability to distinguish capabilities and reveal remaining failure modes. Particularly in scientific domains, constructing and updating benchmarks requires substantial time, labor, and domain expertise, making it difficult to keep evaluation aligned with advances in agent capabilities. We address this challenge by investigating whether scientific-agent benchmarks can be automatically generated and iteratively adapted as agent capabilities evolve. We introduce AutoSciBench, a framework that represents each task as a high-level concept specifying the scientific domain, data modality, and required reasoning approach, together with a low-level recipe specifying how the question, environment, and ground-truth answer are constructed and verified. Agents attempt to solve each task, producing solver trajectories and corresponding judge feedback which AutoSciBench uses to revise the recipe or concept, closing observed shortcuts and shifting tasks toward raw-data re-examination, interpretation of intermediate results, and evidence integration. Experience distilled from completed refinement trajectories further guides new concept generation, allowing lessons from earlier task refinement to inform subsequent benchmark construction. Starting from existing benchmarks, we evaluate AutoSciBench across computational biology, materials science, and clinical imaging. Generated benchmarks reduce average solver accuracy by 22.4 and 25.5 percentage points relative to the human-curated benchmarks in computational biology and materials science, respectively, while generated tasks receive higher average quality ratings across all three domains, suggesting that scientific-agent evaluation can adapt as agent capabilities advance.

---

### Hidden in the Comments: A Context-Injection Attack Surface in Code LLMs

Authors: Noor Munir, Francesco Quinzan, Stephen Roberts
Published: 2026-10-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.05139v1

Code large language model (Code LLM) assistants generate code from heterogeneous development contexts, including open files, imported modules, pasted snippets, and comments, much of which may originate from untrusted sources. We investigate whether insecure instructions embedded in such contexts can steer Code LLMs toward vulnerable code without access to model weights or training data. We evaluate ten open-weight Code LLMs spanning 3B--13B parameters, including four base and six instruction-tuned models, across ten web-application weakness classes. We compare completion tasks containing insecure instructions embedded as code comments with benign tasks without malicious instructions. Attack-condition completions contained a medium-or-higher weakness in {\bf 77.4--92.3}\% of cases, compared with {\bf 1.7--5.1}\% in the benign condition. Base and instruction-tuned models averaged 86.5\% and 84.5\% vulnerable outputs, respectively; equivalence testing and three matched model pairs indicated reductions of at most 8.1\% after instruction tuning. Susceptibility showed no clear association with model scale or specialization. Among vulnerable attack outputs, 86.2--91.0\% were rated high or critical, and the effect persisted without the pattern-based detector. Post-generation screening reduced but did not eliminate the risk, the strongest screen leaving roughly one-third undetected. These findings identify inference-time context injection as a substantial attack surface and motivate provenance-aware training objectives.

---

### How Does Geometry Enter Generated Motion?

Authors: Weihan Li, Junhao Wu, Yuhan Song, Xiaofeng Lin, Xinlei Chen
Published: 2026-10-04
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2610.05135v1

Under a fixed physical law, the visible geometry of a scene determines how motion must change. We ask how video generators realize this relationship. We fix the law and the initial state and change only the geometry drawn in the first frame, within matched families of tracks and deflectors, and compare each generated trajectory with the simulator prediction for that geometry. Paired interventions change one thing at a time: a local bump, the height of a barrier, the words of the prompt, the length of the clip. Across nine image-to-video models, geometry is preserved and shapes the motion: the speed of the ball follows the drawn undulation of a track. A physical state would carry this response forward, and here the generated motion parts from the law. The mean slope barely accelerates the ball, successive contacts fail to compose through a consistent state, an edit ahead of the ball alters its motion before it arrives, and the ball climbs over barriers higher than its release point. Two global conditions organize the global trajectory: text strongly controls the destination, while clip length strongly controls timing in the open-weight models tested. The pattern persists with photographed first frames. Current video generation thus behaves as geometry-conditioned motion synthesis whose evolution of state differs systematically from that of a fixed physical law.

---

### RoMod: Temporal Routing Modulation via Mixture-of-Experts for Video Anomaly Detection

Authors: Chao Huang, Pengfei Wei, Benfeng Wang, Chengliang Liu, Wei Wang, Li Shen, Wenqi Ren, Xiaochun Cao
Published: 2026-10-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.05131v1

Intermediate-layer features from multimodal large language models have shown strong potential for video anomaly detection (VAD), yet the origin of their discriminative power remains unclear. We study this question using sparse mixture-of-experts (MoE) models, whose explicit expert structure and sparse activation make their internal computation easier to inspect. With a fully frozen backbone and no additional training, we find that anomaly-related evidence is concentrated in a small set of experts. These experts recur across layers, spontaneously specialize in different anomaly types, and together form a dynamic routing subnetwork. We further show that the output channels most strongly influenced by these experts are also the hidden dimensions that contain the most anomaly-relevant information. Routing statistics can therefore serve as an internal anomaly cue that complements semantic features.Based on these findings, we propose RoMod, an efficient VAD framework trained with only \(5\%\) of weakly labeled videos. RoMod includes a Routing-Modulated Fusion module, RoMF, and a Routing-aware Temporal Network, RoTN. RoMF uses routing signals to adaptively recalibrate hidden semantic channels. Its design also prevents the routing branch from bypassing semantic features and making predictions on its own. RoTN captures the temporal evolution of anomalies from onset to persistence and termination. Experiments on three benchmarks show that RoMod achieves state-of-the-art performance while running substantially faster than dense backbones of comparable size.

---

### A Contrast-Source Inversion Scheme Based on Stochastic Optimization and Plug-and-Play Regularization

Authors: Lingqi Gao, Hakan Bagci
Published: 2026-10-04
Categories: physics.comp-ph, cs.IT, cs.LG
arXiv: https://arxiv.org/abs/2610.05130v1

An electromagnetic inversion scheme that integrates stochastic optimization (STO) and plug-and-play (PNP) regularization into contrast-source inversion (CSI), termed STO-PNP-CSI, is developed. Standard CSI solves for the contrast source vector of every transmitter at each iteration, which is expensive in a multi-transmitter configuration. STO instead solves for only one randomly selected contrast source vector per iteration, which reduces the per-iteration cost and can help the inversion escape poor local minima and saddle points. The resulting loss of information, however, increases the ill-posedness of the inversion. To counter this, the Swin-Conv-UNet (SCUNet) denoiser is plugged into the CSI scheme as an implicit regularizer, supplying a learned prior that is stronger than conventional hand-crafted ones and stabilizes the reconstruction. The proposed STO-PNP-CSI is applied to both synthetic and experimental data. The results show that it yields accurate reconstructions at substantially lower computational cost than CSI, including under strong nonlinearity and measurement noise.

---

### Representation--Behavior Alignment for Explainable Weakly-Supervised Video Anomaly Detection

Authors: Chao Huang, Pengfei Wei, Kaige Li, Chengliang Liu, Wei Wang, Wenqi Ren, Xiaochun Cao
Published: 2026-10-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.05129v1

Multimodal Large Language Models (MLLMs) provide a natural way to make video anomaly detection more explainable. However, their final decisions do not always fully use the discriminative information contained in their hidden states, an issue we refer to as representation--behavior misalignment. We decompose this gap into a capacity component that measures discriminative information never aggregated into the readout position, and a directional component that measures the angular mismatch between the optimal and the native normal--abnormal axis at that position. Across multiple video anomaly detection benchmarks and MLLM backbones the directional component dominates, and residual-stream tracing shows that native-axis separability rises sharply in several mid-to-late attention layers. Because both components are governed by attention rather than MLP updates, we propose Representation--Behavior Alignment (RBA), a parameter-efficient method that adapts those layers using video-level labels alone while updating about 0.012\% of the backbone parameters. Experiments on three benchmarks show that RBA improves native-readout performance and better aligns the model's decision direction with discriminative representations, and it produces anomaly decisions and explanations through a single generative process.

---

### Component-Level Evaluation of Adaptive PINN Training for CFD-Oriented Crystal Growth Simulation

Authors: Niruta Chapagain, Rohit Raj, Bertwin Kurisinkal Shine, Aditya A S
Published: 2026-10-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.05127v1

Physics-informed neural network (PINN) training minimizes a weighted combination of partial differential equation (PDE), boundary-condition, and initial-condition losses. Because adaptive methods modify these weights during training, their weighted total losses are not always directly comparable. We compare fixed-weight PINN, gradient-normalized PINN (GNPINN), and a rule-based adaptive controller (AgenticPINN) under matched settings on a heat-equation benchmark and a simplified Czochralski-oriented thermal-fluid problem. In the crystal-growth MLP experiment, adaptive control reduced the PDE residual from the order of $10^{-5}$ to $10^{-6}$, while the boundary-condition loss increased from the order of $10^{-5}$ to $10^{-2}$. On the heat-equation benchmark, GNPINN achieved the lowest relative $L_2$ field error (0.054), whereas AgenticPINN obtained the smallest PDE residual but a relative $L_2$ error of 1.368. Gaussian-process surrogates were additionally evaluated using case-wise holdout tests on corrected Czochralski CFD parameter sweeps. The temperature-field error for the temperature sweep was approximately 6%, whereas the axial-velocity error for the crystal-rotation sweep was approximately 42%. These findings show that adaptive control can improve equation satisfaction while weakening other physical constraints. PINN training should therefore be evaluated using separate PDE, boundary-condition, and solution-error metrics rather than weighted total loss alone.

---

### Selecting Repetition Counts Across Model Scales in Data-Constrained Pretraining

Authors: Ziyue WANG, T. Kanamori
Published: 2026-10-04
Categories: cs.CL, stat.ML
arXiv: https://arxiv.org/abs/2610.05126v1

The repetition count that works best for a small language model may not remain best at a larger scale. We study this effect in pretraining with a finite target corpus mixed with generic data at a fixed target fraction. On Wikipedia-derived data and Proof-Pile-2, the ranking of measured repetition counts changes with model size, and a 520M Proof-Pile-2 experiment confirms that reducing repetition from sixteen to eight improves loss while using fewer training tokens. We use loss curves from several smaller models to retain a short list of promising repetition counts for evaluation at a larger scale. On PubMed and Caselaw, candidate sets fixed before target-model training retain the lowest-loss measured count on the original evaluation grids at both 200M and 520M. This supports candidate retention as a practical alternative to exact point prediction. We also relate the pruning regression to an empirical scaling model with two opposing repetition-dependent loss terms. A first-order expansion in log model size yields the linear form used by the selection rule, providing a scaling-based interpretation of the candidate-selection procedure.

---

### Bayesian Entropy-based Reordering for Calibrated Diffusion Language Models

Authors: Zhejun Jiang, Mijung Park
Published: 2026-10-04
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2610.05125v1

Masked Diffusion Language Models (MDLMs) generate sequences by iteratively replacing masked tokens with model predictions. At each denoising step, the decoder chooses which positions are sufficiently confident to commit. Existing decoding methods typically rely on softmax confidence, which can be miscalibrated. We introduce BayesER (BAYESian Entropy-based Reordering), a post-hoc Bayesian decoding framework that uses predictive uncertainty to guide token commitment. In BayesER, we construct a lightweight approximate posterior centered at the pretrained checkpoint, similar to Laplace-LoRA but without training LoRA adapters. We average predictions over posterior samples and use predictive entropy to prioritize reliable positions. We examine how posterior predictions affect position ordering and token selection across benchmarks spanning code generation, mathematical reasoning, planning, and molecular generation. We show that BayesER reduces sequence-level calibration error while preserving or improving accuracy relative to common decoding schemes, including confidence-threshold decoding. Additionally, a posterior fitted on one code-generation dataset reduces calibration error on another without refitting, suggesting that Bayesian uncertainty may provide a transferable signal for more reliable MDLM decoding.

---

### Memory Canonicalization: A Framework and Benchmark for Cross-Model Drift in Persistent LLM Memory

Authors: Amit Vadnere, Aishwarya Lonarkar
Published: 2026-10-04
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.05124v1

Persistent memory for Large Language Models (LLMs) has matured rapidly: systems such as MemGPT/Letta, Mem0, and Zep now provide agents with tiered, temporally-aware, model-agnostic external storage, while the Model Context Protocol (MCP) standardizes access to memory servers. A less addressed problem is that an identical stored memory object, retrieved by two different LLMs under otherwise identical conditions, may not be interpreted the same way, factually or emotionally. This paper proposes memory canonicalization: a write-time pipeline that detects ambiguity, conditional structure, and emotional loading in a raw memory object and rewrites it into an explicit, structurally disambiguated canonical form, with emotional valence represented as a separate field rather than inferred from tone. We formalize the pipeline, define a companion Cross-Model Semantic Drift / Emotional Consistency Score benchmark (CMSC-E), and report results from a three-arm pilot using 176 synthetic memory objects and three downstream model families. We find an uncorrected improvement in cross-model emotional consistency for fully canonicalized memory relative to raw memory (+0.050, 95% bootstrap CI (0.013, 0.086), paired t-test p = 0.010), but this result does not survive Bonferroni, Holm, or Benjamini-Hochberg correction across the six comparisons tested. None of the factual-drift (CMSD) comparisons reach significance at any correction level. We report these results as exploratory rather than confirmatory and outline needed follow-up work, including larger samples, independent judge models, human-validated rendering, and preregistration.

---

### LexiHorizon: Stabilizing Reinforcement Learning for Long-Horizon Deep Search

Authors: Zhiqing Nong, Liang Wen, Chao-Hsuan Liu
Published: 2026-10-04
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.05119v1

Deep search agents tackle complex knowledge tasks through iterative retrieval, multi-hop reasoning, and evidence synthesis across multiple sources. Existing approaches typically assume relatively stable retrieval systems and operate over short-horizon tool interaction. However, when retrieval is sensitive to query formulation, even a semantically appropriate query may fail to surface critical evidence because of mismatched entity names, aliases, or keyword combinations. Recovering from such failures requires repeated query reformulation and longer interaction trajectories. This setting poses a distinct training challenge, as the policy must sustain long-horizon query exploration while managing an expanding volume of retrieved content. We propose LexiHorizon, a framework for training search agents over long horizons that expands the trajectory context budget, manages accumulated retrieval content using a window over recent tool observations while preserving the reasoning history, and introduces an outcome-gated search-effort reward that provides a bounded bonus for tool invocations to trajectories with nonzero answer reward. Experiments on XBench, WebWalkerQA, and BrowseComp-ZH show that the resulting 9B model consistently outperforms both its base model and MiroThinker-1.7-mini, with maximum absolute gains of 8.7 and 23.8 percentage points, respectively. These results suggest that combining an extended context budget with reasoning-preserving context management benefits long-horizon deep search agents.

---

### PCLM: Small-target localization with frozen CLIP via prototype contrast and local magnification

Authors: Zhipeng Ye, Feng Jiang, Qiufeng Wang, Hao Li
Published: 2026-10-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.05115v1

Small targets occupy few patches in a vision-language encoder, so spatial features often mix object appearance with surrounding content. We propose Prototype Contrast and Local Magnification (PCLM), a support-conditioned localization method that uses a frozen CLIP encoder. Five masked support images per class define foreground and background prototypes through equally weighted regional features. Their difference provides a shared scoring direction for query patches, explicitly comparing target evidence with the demonstrated background. Nine overlapping query windows are enlarged and encoded independently to sample small targets more densely. Reprojection and coverage averaging combine their scores into a continuous localization map. The class direction occupies 2 KiB regardless of support count and transfers unchanged across datasets with mapped categories. On 5,047 small-target queries from VOC, COCO, ADE20K and Oxford-IIIT Pets, PCLM achieves higher mean pixel AP than every evaluated text-conditioned localization baseline on each dataset under our evaluation protocol. Gains over the strongest scene-dataset baselines range from 5.63 to 13.23 percentage points. At comparable measured latency, local magnification improves scene small-target AP by 4.51 to 5.68 points over whole-canvas enlargement. Factorial experiments show that prototype contrast increases the benefit of local observation, including under matched image-coordinate filtering. Support-budget experiments show that additional examples refine category estimation without increasing representation size or query-time scoring cost.

---

### Belief-Trajectory Energy: Measuring the Path to a Prediction

Authors: Jiahao Ying, Wei Tang, Boxian Ai, Yaoning Wang, Haotian Chen, Wenhe Sun, Caijun Xu, Haozhan Cai, Changyi Xiao, Yixin Cao
Published: 2026-10-04
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.05114v1

Large language models (LLMs) progressively revise their predictions across Transformer layers, yet we typically observe only the final output, discarding the trajectory through which it is formed. We introduce Belief-Trajectory Energy(BTE), a model-grounded measure that characterizes an input through the layerwise predictive revisions it induces in a model. By mapping intermediate states into a shared predictive space, BTE provides a principled measure of belief change that can be summarized as either a scalar or a structured depth profile. Theoretically, we show that local BTE corresponds to predictive revision under the Fisher-Rao geometry, while the sequence of revisions captures information beyond the initial-to-final belief change. Empirically, scalar BTE provides a model-relative signal of difficulty across diverse reasoning tasks, while richer BTE representations support human-LLM review detection and fine-grained generator attribution, reaching up to $0.998$ macro-AUROC and $95.6\%$ eight-way attribution accuracy. Further analysis shows that BTE develops throughout pretraining and is selectively reshaped by targeted training, demonstrating that the resulting measurement reflects what the scoring model has learned. Together, our results establish belief trajectories as a principled model-grounded signal and suggest a broader perspective in which learned models can themselves serve as instruments for characterizing the data they process. More demonstrations can be found at https://yingjiahao14.github.io/BTE-web/.

---

### InstMoE: Adaptive Multimodal Routing with Specialized Experts

Authors: Guimin Hu, Xiang He, Yingjian Li, Zheng Lian, Boyan Xu, Ruichu Cai
Published: 2026-10-04
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.05111v1

Multimodal inputs are inherently heterogeneous, not only across modalities but also in the information pathways required for effective prediction. To address this limitation, we propose InstMoE, an adaptive expert routing framework for multimodal learning. InstMoE dynamically routes each input to specialized unimodal and cross-modal experts, allowing the model to adapt its information pathways to the characteristics of the input. However, routing can be misled when modality-specific variations obscure task-relevant semantics. Such irrelevant variations may distort routing decisions, causing inputs to be assigned to inappropriate experts. We therefore introduce a Contrastive Semantic Alignment module, which encourages semantically similar inputs to share task-relevant representations while suppressing irrelevant modality-specific variations. Experiments on multimodal sentiment analysis benchmarks demonstrate that InstMoE achieves state-of-the-art performance on CMU-MOSEI and CH-SIMS v2 while using substantially fewer parameters than competitive baselines. Further analysis shows that different inputs exhibit distinct expert preferences, demonstrating that InstMoE moves beyond fixed fusion toward adaptive multimodal computation.

---

### LoopMoEVR: Loop-Based Degradation-Aware Mixture-of-Experts for Unified UHD Video Restoration

Authors: Yucheng Xin, Runci Bai, Yongcong Wang, Guangwei Gao, Jiao Liu, Dianjie Lu, Linwei Fan, Zhuoran Zheng
Published: 2026-10-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.05109v1

Recently, unified high-definition image restoration has attracted considerable attention; however, existing models tend to excessively increase their depth in pursuit of improved generalization, which often yields only limited gains. Meanwhile, loop-based learning paradigms have drawn widespread attention due to their low parameter counts and strong regression capability, as exemplified by GPT-6 and looped Transformers. In this paper, we introduce the loop learning paradigm to address restoration tasks that require cross-domain learning. Specifically, we propose LoopMoEVR, a loop-based mixture-of-experts model capable of handling degraded ultra-high-definition (UHD) inputs. First, a degradation-conditioned low-rank loop embedding is designed to construct input-dependent stage conditions. Second, a spatio-temporal iterative adaptive normalization module, termed IterAda3DN, is developed to fuse local features with global loop context, thereby performing position-wise affine modulation. Finally, the expert branches further integrate the attention-updated local and global video states with the loop conditions to generate dedicated modulation parameters, while an input-conditioned depth predictor adaptively configures the number of loop iterations. With only approximately 0.884M trainable parameters, the proposed model uniformly handles UHD video dehazing, deraining, denoising, and low-light enhancement tasks, achieving state-of-the-art restoration performance on both public benchmarks and real-world scenarios.

---

### Best-of-$N$ Guidance for Test-time Diffusion Alignment

Authors: Richard Lee Kim, Yeongmin Kim, Gyuwon Sim, Taekyu Kim, Minsang Park, Il-chul Moon
Published: 2026-10-04
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2610.05108v2

Diffusion models achieve strong generative performance but often struggle to align generated samples with human preferences measured by a reward model. A simple yet effective algorithm for test-time alignment is Best-of-$N$ (BoN) sampling, which draws $N$ i.i.d. samples from a pre-trained diffusion model and outputs the single highest-reward sample. Despite its empirical success, BoN makes limited use of reward information, as it is incorporated only at the final selection stage without influencing the reverse diffusion trajectory during sampling. Consequently, BoN sampling does not improve the average alignment of generated samples and is primarily suited to single-output settings. We propose Best-of-$N$ Guidance (BoNG), a novel method that integrates the principle of BoN sampling directly into the reverse diffusion process. BoNG performs online BoN selection over denoising particles and adjusts the reverse diffusion process to steer the particle population toward higher-reward regions during generation. Specifically, by introducing an asymmetric guidance interaction among denoising particles, BoNG uses the current BoN particle as a guidance signal to the rest of the particle population. This particle-level interaction reshapes the sampling process toward higher-reward regions, enabling BoNG to improve not only the final best sample beyond Vanilla BoN sampling, but also the average quality of generated samples. Over 36 empirical comparisons, BoNG achieves the best performance in 29 cases, ranking first in 80.56% of the comparisons against SMC and Vanilla BoN sampling. BoNG also supports multi-output capability, achieving 1.3$\times$ ImageReward score of the latest sample-based guidance method with a 1.6$\times$ speedup. We release the code at https://github.com/aailab-kaist/BoNG.

---

### SearchJev: A Fast and Calibrated System-1 Model for Search Agents

Authors: Congfeng Cao, Lipeng Zuo, Konstantinos Papakostas, Qiwei Xu, Songwei Xu, Lun Zhou, Zhaochun Ren, Yougang Lyu, Xiaohui Yan
Published: 2026-10-04
Categories: cs.IR, cs.CL
arXiv: https://arxiv.org/abs/2610.05107v1

Search agents repeatedly make short decisions about relevance, evidence sufficiency, and search actions. Using generative language models for these decisions introduces latency and unreliable confidence. We present SearchJev, a fast and calibrated System-1 model that separates search decisions from System-2 reasoning and generation. Given a search state and a decision schema, SearchJev directly scores legal options without autoregressive output generation. We propose Soft-Label Learning for Calibrated Decisions (SLCD) to learn decision probabilities from uncertain supervision and calibrate their confidence. In a dual-system search agent, SearchJev handles short decisions and delegates uncertain judgments to System 2, which retains planning, query generation, and answer composition. We also introduce SearchDecision-Bench, a benchmark unifying six types of search decisions for training and evaluation. On SearchDecision-Bench, SEARCHJEV improves decision quality over same-size Qwen3.5 autoregressive models, achieves 5.2-5.3 times faster decisions, and reduces average expected calibration error by 41-74%. On BrowseComp-Plus, the dual-system agents achieve a 3.7-4.7 times speedup in active search time while improving answer accuracy from 45% to up to 54%.

---

### SharpDraft: Accelerating Long-Context Speculative Decoding with Cardinality-Aware Query Scaling

Authors: Jeonghoon Park, Seongwoon Jo, Jongwon Lee, Taesik Gong
Published: 2026-10-04
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.05106v1

Long-form reasoning makes inference expensive, and speculative decoding mitigates this cost by verifying multiple draft tokens in parallel. Its speedup, however, can fade as context grows and draft acceptance declines. We focus on attention-mass dilution: as softmax normalizes over more visible Keys, the mass concentrated on the highest-scoring Keys can decrease. We introduce SharpDraft, a training-free method that counteracts this effect through cardinality-aware Query scaling, without the computational overhead of online adaptation. Under explicit assumptions, we derive an exact top-$k$ mass correction and deploy a closed-form fixed-slope approximation. Across AIME-26, GPQA-Diamond, and LongGenBench Diary, SharpDraft achieves $2.59$-$3.19\times$ geometric-mean end-to-end speedups over target-only autoregressive decoding when applied to DFlash, PARD, and EAGLE 3.1. With DFlash, it improves decoding speed and outperforms full-parameter and LoRA-based online adaptation in end-to-end speedup, while matching the unmodified drafter's reported peak allocated GPU memory.

---

### VulValidate: Auditing Function-Level Vulnerability Labels with Executable Evidence

Authors: Leizhen Zhang, Sheng Chen
Published: 2026-10-04
Categories: cs.CR, cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2610.05103v1

Reliable learning-based vulnerability detection requires high-quality labels, yet datasets built from vulnerability-fixing commits may label functions as vulnerable simply because they were changed by a security patch. We present VulValidate, a framework that uses LLM agents to coordinate dynamic analysis tools and construct vulnerability-triggering experiments from runtime feedback. Given a labeled function and its fixing patch, VulValidate reconstructs vulnerable and fixed revisions, selects suitable tools and execution paths, refines triggering inputs, and compares runtime behavior to assess function-level attribution. We audit all 35,849 instances originally labeled vulnerable in BigVul, PrimeVul, and DiverseVul. We confirm 20,510 (57.2%), correct 6,819 labels (19.0%), leave 7,981 attacked but undecided (22.3%), and cannot successfully measure 539 (1.5%). After conflict resolution and byte-exact deduplication, the corrected release contains 15,890 distinct confirmed vulnerable function bodies. In a blinded review of 581 sampled decisions, expert consensus supports 90.0%--92.0% of confirmations and 92.6%--99.0% of label corrections. With model parameters fixed, corrected evaluation lowers F1 for all five tested detectors on both BigVul and DiverseVul; retraining with corrected labels improves F1 for four of five detectors on each dataset. We also release a reusable VulValidate skill, corrected datasets, and reproducible evidence for future vulnerability-detection research.

---

### Private Component-by-Component Learning

Authors: Dvir Karni, Eliad Tsfadia
Published: 2026-10-04
Categories: cs.LG, cs.CR
arXiv: https://arxiv.org/abs/2610.05102v1

We study differentially private learning problems in the realizable setting, where a hypothesis is specified by $k$ components. A direct iteration of private component learners is obstructed by a simple difficulty: an approximate choice of the next component may destroy exact realizability of the labeled sample, even when the next component is locally accurate. We restore realizability using the LabelBoost procedure of Beimel, Nissim, and Stemmer (SODA '15, Algorithmica '21) and recycle data through two alternating reservoirs. The resulting learner, for a target privacy $\varepsilon$, pays only $\widetilde O(\sqrt{k}/\varepsilon)$ overhead relative to the active sample requirement of a single component learning step at target accuracy $Θ(α/k)$. For learning $d$-dimensional halfspaces over a finite coordinate grid of size $L$, exact realizability makes the direct component-depth objective quasi-concave. Instantiating the framework with the IPConcave algorithm of Nissim, Tsfadia, and Yan (SODA '26) and with the quasi-concave optimizer of Cohen, Lyu, Nelson, Sarl'os, and Stemmer (STOC '23) yields a realizable sample complexity of $\widetilde{O}\left(\frac{1}{\varepsilon α}\cdot \min\{d^{2.5} \log^*L, \:\: d^{2.5} + d^{1.5} 2^{\log^*L}\}\right),$ which improves on the previously known bound of $\widetilde{O}\left(\frac{1}{\varepsilon α}\cdot\min\{\frac{1}α\cdot d^{5.5}\log^*L,\:\: d^{2.5}2^{\log^*L}\}\right).$ We also apply the framework to Boolean compositions: given proper private learners for classes $H_1,\ldots,H_k$, we obtain a proper private learner for $G(H_1,\ldots,H_k)$ for any fixed Boolean function $G:\{0,1\}^k\to\{0,1\}$. Compared with the closure theorem of Alon, Beimel, Moran, and Stemmer (COLT '20), this reduces the overhead on a common component sample bound from $\widetilde O(k/\varepsilon)$ to $\widetilde O(\sqrt{k}/\varepsilon)$.

---

### METRO: Metric-Enhanced Token Routing Operator

Authors: Nodens Koren, Thomas Hofmann, Georgios Kissas
Published: 2026-10-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.05100v1

State-of-the-art neural operators scale to complex meshes via slice-and-process architectures, yet many rely on linear compatibility scores for latent tokenization. Under common feature normalization, such scores are equivalent to isotropic Euclidean clustering, while without normalization they induce unbounded linear decision regions. In both cases, they lack slice-specific anisotropic locality, which can lead to redundant and entangled latent slices. To address this, we propose Metric-Enhanced Token Routing Operator (METRO), a geometry-aware routing mechanism that replaces linear projection with a learnable Mahalanobis metric. By enabling each latent slice to learn a local anisotropic tensor, METRO shapes receptive fields into exponentially localized, oriented ellipsoids that naturally align with flow features like boundary layers and wakes. As a drop-in replacement, METRO yields consistent improvements across both Transformer and Mamba backbones. Empirically, our method achieves substantial performance gains on irregular domains, outperforming baselines on both standard PDE benchmarks and complex industrial design tasks. Finally, METRO exhibits enhanced robustness in out-of-distribution regimes across varying Reynolds numbers and geometric configurations.

---

### Small Agents with Semantic Search: Efficient Multilingual Code Localization

Authors: Maxence Lasbordes, Aarush Sinha, Raphael Sourty, Amélie Chatelain, Djamé Seddah
Published: 2026-10-04
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.05099v1

Locating relevant files from natural-language requests is a core subtask for agents operating over code repositories. We investigate whether this task can be delegated to compact, specialized models to enable on-device search while reducing the token usage, latency, and inference cost of larger agents. We show that semantic search improves file localization, with gains in accuracy, cross-language transfer, and inference efficiency. To study this setting, we introduce a training framework for file-localization agents built around ColGREP, a local semantic search tool based on late-interaction retrieval models. Our recipe combines weighted supervised fine-tuning on teacher trajectories, assigning turn-level credit based on retrieval outcomes, with reinforcement learning on localization quality. We train three model families with fewer than two billion parameters to formulate search queries, inspect retrieved content, and identify relevant files. On localization tasks derived from SWE-bench Lite and Multi-SWE-bench Flash, ColGREP-equipped agents substantially improve over their base models and outperform corresponding GREP-based agents. In addition to improving localization accuracy, ColGREP reduces mean end-to-end trajectory latency by 44.1\% on CPU while using 29.1\% fewer tokens, and enables better generalization to programming languages unseen during fine-tuning. These results suggest that compact, tool-specialized localization agents can provide an efficient interface between natural-language requests and large codebases.

---

### Advectra: Asymmetric Latent Transport for Non-Stationary Physics

Authors: Nodens Koren, Thomas Hofmann, Georgios Kissas
Published: 2026-10-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.05098v1

Many latent neural operators represent input and output fields in a stationary latent chart. In particular, common latent routing mechanisms use fixed or shared assignment weights for feature projection and reconstruction, limiting their ability to model transport-dominated systems where coherent structures move relative to fixed coordinate frames. We propose Advectra, a transport-aware latent operator that introduces a regularized kinematic coordinate map to decouple source and target coordinate systems. This yields an approximately co-moving latent reference frame and enables asymmetric feature aggregation and reconstruction. Combined with a geometry-aware ordering mechanism for state-space models, Advectra captures advective dynamics while maintaining stable global interactions. Advectra achieves the best performance among evaluated geometry-constrained and form-free baselines on advection-dominated benchmarks, including passive scalar transport in Navier--Stokes flows and Rayleigh--Taylor instability, while demonstrating strong generalization on real-world engineering tasks. These results highlight the benefit of explicit moving-frame structure in neural operators for non-stationary physics.

---

### ReMAP: Restoring the Perceptual Cycle with Reasoning-Time Latent Visual Memory

Authors: Hao Jiang, Zhanyu Guo, Chenwei Wu, Yichen Guo, Qizhe Zhang, Junchi Yao, Jixian Wu, Jinhao You, Kai Tang, Jiajun Cao, Tinghao Wang, Mengyu Wang et al.
Published: 2026-10-04
Categories: cs.CV, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2610.05097v1

As multimodal large language models (MLLMs) reason for longer, attention to the initial visual input diminishes, weakening visual grounding. Visual memory reintroduces visual evidence during reasoning. We conduct a controlled analysis of visual memory along three axes: curation, organization, and access. We find that local evidence benefits from global context, compact latent representations balance accuracy and visual-context cost, and the utility of memory access depends on the reasoning state. Guided by these findings, we propose ReMAP (Reasoning-Time Memory-Augmented Perception), which couples two complementary latent memories: a static, question-conditioned Global memory that preserves scene and cross-image context, and a dynamic Local memory that uses this context as an anchor while selecting and re-encoding region-level evidence according to the current reasoning state. Both memories return compact latent tokens inserted into the reasoning sequence, and a reinforcement-learning access policy trained with branched rollouts decides when to continue reasoning or invoke Global or Local memory. On ten benchmark families, ReMAP outperforms prior visual-memory methods on all four multi-image benchmarks, exceeding the strongest prior results on MuirBench and MIMIC by 8.38 and 14.84 percentage points. Across four backbone families, enabling memory access improves over the same trained model with memory disabled, and on shared V*Bench, CV-Bench-2D, and MuirBench questions ReMAP reduces the visual tokens entering the reasoning sequence by 51.0-76.8% relative to the native-resolution backbone. Further analyses show that Global and Local memory form distinct yet complementary latent representations. Together, these components restore the perceptual cycle by letting the reasoning state trigger targeted visual retrieval, with the retrieved evidence guiding subsequent reasoning.

---

### vMF Sentence LDA: A Spherical Topic Model over Sentence Embeddings

Authors: Ryotaro Kobayashi, Yuri Murayama, Kiyoshi Izumi
Published: 2026-10-04
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2610.05095v1

Latent Dirichlet Allocation (LDA) and models derived from it remain widely used topic models. LDA observes each document as a bag-of-words and models each topic by a categorical distribution over the vocabulary, so that it uses neither the internal structure of the document nor the similarity in meaning between words. Earlier work has responded to this limitation in two ways: many models have introduced embeddings, and some have assigned topics to sentences rather than to words. Their combination, a topic model that observes sentence embeddings, remains little explored. We propose vMF Sentence LDA (vSLDA), which keeps the admixture structure of LDA, observes each sentence as its L2-normalized embedding and models each topic by a von Mises-Fisher (vMF) distribution, which matches the cosine geometry of sentence embeddings. Its per-topic parameter count and per-iteration cost are linear in the embedding dimension, versus quadratic for the full-covariance Gaussian distribution in the existing model over sentence embeddings. We evaluate vSLDA where the limitation is expected to matter most, among topics that share much of their vocabulary: the topics that subdivide the one subject of a collection, and the narrow topics that result when a corpus is divided into a large number of topics. On two corpora, vSLDA attains the best mean rank against eight baselines when the fine categories within each coarse category are classified from the document-topic distributions. On the whole corpus, its advantage appears or widens as the number of topics grows. Weighting the word frequencies of each sentence by its topic posterior yields expected topic-word counts of the same form as those of LDA, so that the standard topic coherence and diversity measures apply to models that assign topics to sentences. On their product, topic quality, vSLDA leads in most within-category conditions of both corpora.

---