# Research Papers — 2026-10 · bundle page 86 of 156

> Full-text markdown of papers #4251–4300 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/86
[← Previous bundle](https://aipod.dev/papers/archive/2026-10/page/85.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-10/page/87.md)

### Causal-fate dynamics of unrealized influence

Authors: Yiwei Liu, Luwei Yang, Shunbo Lei
Published: 2026-10-08
Categories: eess.SY, cs.LG
arXiv: https://arxiv.org/abs/2610.11422v1

Many dynamical systems generate influences whose consequences are not fully exhausted in the realized trajectory at the moment they arise. Such consequences are often treated as absent, delayed or statically stored, leaving unclear how unrealized influence retains future relevance as the system evolves. Here we formulate causal-fate dynamics, in which generated influence may be realized, remain latent, or be transformed by subsequent dynamics, and give an exact finite-transport representation when the relevant maps are specified. A connectome-constrained Caenorhabditis elegans model first motivates the biological hypothesis that unresolved inter-neuronal influence may persist and contribute to later propagation; it does not establish such a mechanism in living animals. We next examine operational Internet routing, where a dynamically updated cross-observer history retains predictive information beyond the current local route state. We then use the representation to construct a Transformer architecture that explicitly transports and selectively realizes latent contextual influence while retaining language-modeling function. The three studies distinguish a model-motivated scientific hypothesis, an observational phenomenon compatible with future-relevant history and an executable construction for carrying unrealized influence through subsequent computation.

---

### Missing Modality-Aware Calibration for Trustworthy Brain Tumor Segmentation

Authors: Sol Lee, Hyunji Kim, Sungrae Hong, Donghee Han, Mun Yi
Published: 2026-10-08
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2610.11419v1

Multimodal brain tumor segmentation typically leverages multiple MRI modalities, yet incomplete modality acquisition is common in clinical practice due to protocol heterogeneity and scan failures. Although recent methods maintain segmentation accuracy under missing modality conditions, they frequently overlook prediction reliability, leading to miscalibrated confidence estimates that hinder clinical adoption. Existing calibration techniques are largely modality-agnostic or assume that prediction difficulty decreases monotonically as additional modalities become available. However, in brain tumor segmentation, prediction difficulty depends primarily on which modalities are absent rather than how many, leading to combination-specific and spatially heterogeneous calibration errors. To address this, we propose Missing Modality-Aware Local Temperature Scaling (MMA-LTS), a post-hoc voxel-wise confidence calibration method. It estimates a spatially adaptive temperature field conditioned on a modality-availability learnable token and a voxel-wise difficulty score. Experiments on BraTS 2020 and FeTS 2024 show that MMA-LTS improves calibration while preserving the segmentation accuracy of state-of-the-art models across diverse missing-modality scenarios, thereby enhancing trustworthiness toward clinical deployment.

---

### Rewiring Semantics, Dynamics, and Control: A Simple yet Effective Action-Centric Tri-Stream Transformer

Authors: Shuang Luo, Yilun Kong, Yunpeng Qing, Yihang Jiao, Zhi Hou, Shunyu Liu, Xiaogang Wang, Dacheng Tao
Published: 2026-10-08
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2610.11416v1

Vision-Language-Action (VLA) models have emerged as a prominent framework for complex robotic manipulation, building on the strong semantic understanding of pretrained Vision-Language Models (VLMs). However, such VLM backbones offer insufficient physical dynamics priors, which limits the generalization capabilities of robot policies. Recent efforts therefore integrate video-generation World Models (WMs) into robot policies through various strategies, using predictive dynamics to facilitate action generation. Despite these advances, harnessing semantic understanding and dynamics prediction as complementary guidance for action generation remains challenging. In this paper, we introduce $\mathrm{ACT}^3$, a simple yet effective Action-Centric Tri-Stream Transformer that fuses semantic and dynamics information into control actions while preserving the distinct roles of context streams. Specifically, $\mathrm{ACT}^3$ enables the dedicated action expert to access VLM and WM representations through layerwise attention, with each backbone attending only within its own stream. This straightforward interaction design maintains independent forward propagation in the context streams while allowing both backbones to be updated through control supervision. Experiments on both simulated and real-world robotic manipulation benchmarks show that the proposed $\mathrm{ACT}^3$ yields results superior to its counterparts.

---

### Refinement as a Service: Algorithmic Predictor Refinement

Authors: Wei Tang, Hanrui Zhang
Published: 2026-10-08
Categories: cs.GT, cs.LG
arXiv: https://arxiv.org/abs/2610.11415v1

Prediction aggregation aims to combine information from multiple predictors into a more informative one. We study this question in the setting of calibrated predictors, where each prediction must equal the conditional expectation of the quantity being predicted given the predictor's signal. Given several calibrated input predictors and the feature distribution, but not the underlying Bayes probabilities, we ask when one can construct refined calibrated predictors that preserve the information in the original predictors and cannot be further refined using the available information. We formulate calibrated predictors as signaling schemes and define refinement through feature-independent garblings: a predictor refines another if its signal can simulate the other's signal. Constructibility is characterized through observable linear information: each signal corresponds to a vector over the feature space, and a new signal is constructible exactly when its vector lies in the linear span of the input signal vectors. Under this formulation, we establish a sharp algorithmic picture. For deterministic output predictors, bilateral refinement admits a polynomial-time algorithm based on a bipartite graph between the two input signal partitions, while refinement with an arbitrary number of input predictors is $\mathsf{NP}$-hard. In contrast, when randomized output predictors are allowed, we give a polynomial-time algorithm for any number of input predictors by decomposing constructible signal vectors into extreme rays of the associated polyhedral cone.

---

### Fresco++: Frequency-Guided and Canonical-Consistent Optimization for Fine-Grained Head Avatar Modeling

Authors: Shikun Zhang, Yong Li, Yiqun Wang, Qiuhong Ke, Cunjian Chen
Published: 2026-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.11412v1

We propose Fresco++, a unified optimization framework for fine-grained and view-consistent head avatar reconstruction. Head avatar optimization is typically driven by per-view image supervision, which can lead to premature fitting of unstable high-frequency details and inconsistent local appearance across viewpoints. Fresco++ addresses these challenges by regulating both the progression of visual detail and the formation of cross-view supervision during optimization. For frequency-aware optimization, a progressive curriculum first stabilizes low-frequency structures and then introduces high-frequency constraints to recover fine facial and hair details without amplifying spurious responses at early stages. For cross-view optimization, we introduce Canonical Group Consensus, which associates local observations through shared canonical surface regions and establishes correspondence across different viewpoints. Geometric and visibility-aware screening removes unreliable observations, while the remaining multi-view evidence is aggregated in feature space to form a consensus target for supervising the current rendering. This design enforces local consistency without relying on a specific image-space parameterization and avoids additional rendering of the auxiliary view. Together, the frequency curriculum and canonical consensus provide stable optimization from coarse structures to fine details while maintaining coherent appearance across viewpoints. Extensive experiments on NeRSemble demonstrate improved reconstruction quality and cross-view consistency, while evaluations across diverse avatar representations further confirm the generality and transferability of Fresco++.

---

### Cognition-Oriented Emotion Tracing from Causes to Consequences in Real-World Social Scenes

Authors: Hao Li, Jinye Zhang, Bobo Li, Mong-Li Lee, Wynne Hsu, Zheng Wang, Hao Fei, Min Zhang
Published: 2026-10-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.11410v2

Affective computing has progressed from categorical emotion recognition to open-ended affective analysis with large multimodal models. Yet affective science describes emotion as an unfolding process shaped by appraisal, regulation, and social interpretation, which remains underexplored computationally. We propose TRACE, a cognition-oriented framework that formalizes an affective episode through three interrelated stages: Condition, Affect, and Effect, integrating observable cues with cognitive factors such as internal stance and regulation of emotional display. Based on this formulation, TRACE-Bench evaluates multimodal models in real-world social scenes through five tasks spanning grounded affect recognition, regulation decoding, cause reasoning, effect reasoning, and full-chain reconstruction, with 3,746 structured question-answer pairs over 646 videos. A matched human-model comparison reveals a substantial performance gap, while affect-specialized models also generally lag behind general-purpose MLLMs. Model outputs show recurring failures, including treating displayed behavior as genuine feeling and fabricating unsupported events during long-chain generation. We further propose TRACER, a cognition-grounded structured reasoning method that couples each inference with explicit premises from factual observations, cognitive appraisals, and established upstream conclusions, forming a traceable graph of intermediate and target conclusions. TRACER outperforms all evaluated model baselines on each of the five tasks. Project page: https://cogaffc.github.io/TRACE

---

### MC-TRCM: Observation-Aware Recursive Fusion for Incomplete Mobile and Wearable Mental-Health Feature Views

Authors: Wentao Wang, Lifeng Han, Zining Ren, Hengyu Zhong, Guangyu Zou
Published: 2026-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.11408v1

Public mobile and wearable mental-health datasets often provide summarized feature tables rather than synchronized raw sensor streams. In these releases, each anchor corresponds to a survey or label time and may combine phone or wearable summaries, prior symptom scores, demographics, clinical variables, and source-availability indicators. We propose the Modality-Conditioned Temporal Recursive Context Model (MC-TRCM), which preserves each feature source as a separate token and incorporates missingness as part of the input context. Observed sources are encoded with values and missingness summaries, absent sources use learned absence tokens, dataset and task embeddings condition fusion, and a recursive prediction head refines each output over validation-selected steps. We evaluated MC-TRCM on six predefined endpoints from DepreST-CAT and Prediction of Severity Change-Depression (PSYCHE-D) using participant-level splits and validation-only model selection. MC-TRCM achieved the lowest mean absolute error on DepreST-CAT Patient Health Questionnaire-9 (PHQ-9) and Generalized Anxiety Disorder-7 (GAD-7) severity, improving over the best tabular reference by 0.181 and 0.217 scale points. Classification endpoints showed task-dependent behavior: MC-TRCM matched the best rounded GAD-7 category balanced accuracy, was numerically highest by 0.002 balanced-accuracy points on PSYCHE-D multiclass prediction, and remained close to the strongest references on PHQ-9 category and PSYCHE-D binary prediction. Ablations support Feature-wise Linear Modulation, absence tokens, missingness projections, and recursive refinement, while calibration and feature-source controls characterize endpoint behavior. Our code is available at https://github.com/Botwwt/MC-TRCM.

---

### Beyond Distributional Fidelity: Causal-Penalized Diffusion for Synthetic Tabular Data

Authors: Lan Tao, Yongxian He, Shirong Xu, Yidong Ouyang, Guang Cheng
Published: 2026-10-08
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2610.11407v1

Synthetic tabular generators are commonly optimized for distributional fidelity, but statistical similarity alone does not guarantee preservation of causal effects. In this paper, we study whether causal fidelity can be improved directly within a fully generative tabular model. Causal Fidelity is defined with respect to a target estimand as the discrepancy between inferential distributions obtained from real and synthetic data, and theoretical results show that high statistical fidelity does not generally imply high causal fidelity. We then propose a causal-fidelity-aware training framework which adds a causal discrepancy penalty to the generative objective. The framework is instantiated with a causal-penalized TabDDPM and optimized using an on-policy score-function estimator. We further establish conditions under which causal regularization improves expected causal fidelity. Experiments across diverse treatment-effect simulations and two benchmark datasets evaluate the ability of our method to improve causal fidelity while preserving competitive statistical fidelity.

---

### Learning from Hetero Density for Cryo-EM Protein Reconstruction

Authors: Xu Han, Chaozhuo Li, Xiaowei Yuan, Yuancheng Sun, Kang Liu, Qiwei Ye
Published: 2026-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.11403v1

Reconstructing protein structures from cryo-electron microscopy (cryo-EM) maps is essential for understanding macromolecular assemblies. Although learning-based methods have improved protein reconstruction, information from hetero components remains underused. Our analysis finds both false predictions and reference protein sites near hetero components; filtering nearby candidates can improve or impair chain construction. We introduce CryoCue, a framework that uses hetero information to guide protein reconstruction. An anchor-supervised detector learns hetero representations across five component classes. Multiscale hetero features guide backbone localization, while predicted hetero candidates condition structure refinement through their class, confidence, and frame-relative geometry. Experiments show that CryoCue improves backbone localization near hetero components and achieves more accurate protein structure reconstruction.

---

### GroundSight at GroundLM 2026 Shared Tasks: GoldenViewVQA

Authors: Kun Wang, Yupeng Hu, Ruping Cao, Hao Liu, Zhiran Li, Qianlong Xiang, Harry Cheng
Published: 2026-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.11402v1

GoldenViewVQA requires models to jointly answer driving-scene questions and identify the camera view containing the supporting visual evidence, making precise evidence localization as important as answer correctness. We present \textbf{CoVeR-VQA}, a training-free multi-stage verification and correction framework for grounded multi-view VQA. Starting from GPT-5.6 zero-shot predictions, CoVeR-VQA progressively applies view-specific verification with Gemini-3.6-Flash, prior-guided joint verification with Claude-Opus-5, and cross-split group-level verification that exploits semantically filtered question groups from shared multi-view scenes and validation-derived prior knowledge. On the official GoldenViewVQA test set, the four-stage CoVeR-VQA pipeline achieves 84.75\% Joint Accuracy, improving the GPT-5.6 zero-shot baseline by 13.56 percentage points, while reaching 94.92\% Answer Accuracy and 86.44\% View Accuracy. The final submitted run achieves 88.14\% Joint Accuracy after two additional evaluator-informed post-hoc corrections. Our analysis shows that supporting-view localization remains the primary source of residual errors, highlighting the importance of explicit evidence verification for reliable multi-view multimodal reasoning.

---

### WAM-Cache: Staleness-Bounded KV Reuse for Efficient World Action Models

Authors: Kai Ding, Yang He, Ruijie Quan, Yi Yang
Published: 2026-10-08
Categories: cs.RO, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2610.11401v1

World Action Models (WAMs) enable generalist robot manipulation by conditioning an action expert on representations from a pretrained video Diffusion Transformer (DiT). In closed-loop control, the video DiT runs at every chunk to encode the current observation into layerwise key-value (KV) pairs that the action expert queries. This prefill dominates the per-chunk computational cost, yet existing training-free accelerations leave it fully dense. We present WAM-Cache, a training-free framework that retains layerwise key-value representations across chunks and recomputes only a sparse refresh set of tokens. Crucially, we find that the intuitive heuristic of refreshing visually drifted tokens plateaus far below the dense baseline, even with an oracle predicting ground-truth KV drift. Downstream action accuracy is instead governed by where the action expert attends, not by what moved. WAM-Cache therefore selects the refresh set by uniting the action expert's cross-attention with visual latent surprise, complemented by a strict age bound that suppresses compounding error. On Fast-WAM, WAM-Cache cuts video DiT prefill FLOPs by 32-42% across RoboTwin 2.0, LIBERO, and real-world experiments, while staying within 0.7-1.8 percentage points of the dense policy in simulation and 2.5 points on a real robot.

---

### Estimating Great Expectations Under Autoregressive Language Models with Potentials

Authors: Francesco I. Re, Shubhangi Ghosh, Tim Vieira, Ryan Cotterell
Published: 2026-10-08
Categories: cs.AI, cs.LG, stat.ME
arXiv: https://arxiv.org/abs/2610.11399v2

Many applications of language models hinge not on individual samples but on the expectation of a test functional under the model. Estimating such expectations reliably can be computationally expensive. In this paper, we show how to make estimation more efficient by exploiting the next-token conditional probabilities which are available as a by-product of sampling. We do so through potentials: real-valued functions on prefixes that decompose the test functional additively. We construct an estimator whose variance depends on the chosen potential, and derive conditions under which a potential reduces this variance. We then develop practical potentials for several estimands and applications, and demonstrate substantial variance reductions across several estimands at comparable computational cost.

---

### CoPoE: Multimodal Fusion via Decomposable Disease-Coordinate Product-of-Experts for Missing-Modality Alzheimer's Diagnosis

Authors: Chihun An, Ikbeom Jang
Published: 2026-10-08
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2610.11394v1

Multimodal Alzheimer's disease (AD) diagnosis benefits from integrating heterogeneous clinical, imaging, genomic, and biomarker evidence, but clinical cohorts frequently suffer from irregular modality missingness. Existing fusion methods often synthesize absent inputs, risking the introduction of artificial surrogates, or pool available signals into uninterpretable latent spaces. We present CoPoE (Disease-Coordinate Product-of-Experts), a disease-coordinate framework that maps multimodal evidence into a structured latent space partitioned into four distinct biological and clinical axes: genetic Risk, molecular Pathology, Neurodegeneration, and clinical Stage (R/P/N/S). Each observed modality parameterizes a diagonal Gaussian expert over the full RPNS vector, and a masked Product-of-Experts architecture fuses only the available modalities. Consequently, absent modalities add no factor to the fusion path, allowing the network to preserve a robust, decomposable posterior for any non-empty modality subset without synthetic imputation in the RPNS path. Through extensive missing-modality experiments on the ADNI dataset, CoPoE achieves the best all-modality performance and the highest mean AUROC across all 15 observed-subset evaluations among standardized missing-modality fusion baselines under a shared non-PET ADNI embedding benchmark, while substantially improving raw-probability ECE, Brier score, and NLL. Furthermore, PET-supervised probing shows evidence enrichment within the pathology (P) block under full modalities, with tau-related signal retained even when direct fluid biospecimen inputs are withheld. Our code is available at https://github.com/labhai/CoPoE.

---

### TypedBench: A Benchmark for Calibration, Framing Sensitivity, and Cost in System One Decision Models

Authors: Rahul Sharma, Andrew B. Duncan, Gaétan Marceau Caron, Sebastian J. Vollmer
Published: 2026-10-08
Categories: cs.AI, stat.AP
arXiv: https://arxiv.org/abs/2610.11392v2

System One models output calibrated probabilities over typed answers such as categorical choices, ordinal levels, or binary outcomes, via a non-generative interface. Software can act on these probabilities through thresholds, cost-weighted choices, and escalation rules. Consequently, if these probabilities are miscalibrated or wording-sensitive, the software ma take unintended actions leaving human operators with no textual rationale to inspect. Current evaluations largely report accuracy and calibration on public classification datasets without a clear reference. We present TypedBench, a benchmark for typed decision models like Jev built from seven policy-labelled generators and nine evaluation suites. We report accuracy as median and range across paraphrases, and calibration error relative to the finite-sample noise floor of a matched, perfectly calibrated predictor. We assess probability quality through selective prediction, ordinal proper scoring rules, and realised cost under asymmetric cost matrices. We evaluate a hosted model, an open encoder, and a family of open decoders spanning 0.8B-9B parameters on identical items. The hosted model follows the stated policy but is wording-sensitive and systematically underconfident; under asymmetric costs, using its probabilities can be worse than taking its top answer. Decoders route exactly and are slow as options or questions are added. The decoder is least accurate on policy questions and degrades with more options. Overall, typed decision models must be evaluated jointly on policy adherence, wording robustness, probability quality, and induced decision outcomes.

---

### Fact over Fiction: Detection of Pathological Hallucinations in Sinhala-to-English Neural Machine Translation

Authors: Navam Obeysekara, Nevidu Jayatilleke
Published: 2026-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.11389v1

Neural Machine Translation (NMT) models, while capable of producing highly fluent outputs, remain vulnerable to hallucinations, which are translations that are natural yet semantically unrelated to the source. This vulnerability is acute in low-resource settings like Sinhala-to-English, where weak cross-lingual alignment leads to hallucinations. This paper introduces a framework for reference-free hallucination detection in this language pair. We present a 45,000-sample synthetic dataset generated through a probabilistic chain of five linguistically motivated corruption strategies, with a semantic rescue mechanism that uses character-level similarity to distinguish hallucinations from morphological variants. We fine-tune mDeBERTa-v3 for token-level sequence labelling, reaching a token-level F1 of 0.841 +/- 0.001 over three seeds on a source-disjoint test set, and study a three-signal ensemble integrating neural risk scores, sequence log-probabilities, and cross-lingual semantic embeddings (LaBSE). A source-ablation control shows that the detector relies on the Sinhala source rather than on surface artefacts of the corruption process: shuffling or removing the source reduces sentence-level AUROC from 0.970 to chance. We benchmark eight NMT systems spanning five model families and find that detector firings vary by an order of magnitude across architectures.

---

### Sequential Conditional Independence Testing with Machine Learning Models

Authors: Angel Reyero-Lobo, Michele Meziu, Sebastian Uriel Arias, Peter Grünwald
Published: 2026-10-08
Categories: math.ST, stat.ML
arXiv: https://arxiv.org/abs/2610.11388v1

Conditional independence testing is a ubiquitous problem in scientific discovery. The widely employed model-X assumption shifts the modelling burden from the dependence of the output on the inputs to the dependencies within the inputs. Log-optimal e-variables have been studied in this setting, but it remains unclear how to incorporate machine learning models into their design. Other approaches test exchangeability directly, yielding an e-variable with lower power in theory but, surprisingly, higher power in practice. We explain this phenomenon by decomposing the error into null enlargement, approximation, and estimation error. The decomposition shows that GRO e-variable estimates can be beaten because of their worse approximation and estimation errors, and we explore intermediate null hypotheses between model-X conditional independence and exchangeability to reduce these errors. Moreover, the model-X assumption often only holds up to an estimation error, invalidating exact type-I error guarantees. We provide estimation error bounds that accommodate triple robustness results, achieving fast convergence rates.

---

### RISR: Residual-Informed Scientific Equation Discovery with Large Language Models

Authors: Haobo Li, Wenshuo Zhang, Wenxiao Zhao, Eunseo Jung, Rui Sheng, Yushi Sun, Peiqin Zhuang, Hao Chen, Fenghua Ling
Published: 2026-10-08
Categories: cs.SC, cs.AI
arXiv: https://arxiv.org/abs/2610.11387v1

Symbolic regression combines structural search with numerical fitting, but aggregate fit scores do not describe how the remaining error varies across inputs. We introduce RISR, a residual-informed method that uses these error patterns to guide formula discovery and learn which corrections are worth fitting. A residual encoder compresses aligned inputs, targets, current predictions, and residuals into continuous tokens that condition a language model to propose formulas. For subsequent refinement, a dual-view relational encoder uses additive and regularized multiplicative residuals to predict the post-fit utility of candidate corrections. We evaluate RISR on scientific tasks from the LLM-SRBench. RISR achieves 63.57% and 38.50% ID accuracy at the 1% and 0.1% pointwise relative-error tolerances, respectively. The corresponding OOD accuracies are 56.07% and 38.24%. RISR outperforms the reported baselines using the same backbone. The results show that our residual-informed approach can improve numerical equation recovery.

---

### Environmental Feedback Modeling Matters: Rethinking Feedback Treatment in Agentic Hindsight Self-Distillation

Authors: Hangxi Guo, Fengyuan Liu, Yue Wang, Yuhua Qi, Haoyi Xiong, Fei Sun, Mengnan Du
Published: 2026-10-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.11384v1

Reinforcement learning is commonly used to train language agents in interactive environments, but cannot be directly applied when rewards are unavailable. Recent methods use environmental feedback as privileged context for hindsight self-distillation, but our analysis suggests that simply conditioning the teacher on feedback is insufficient, motivating us to rethink how environmental feedback is used in agentic self-distillation. Given that environmental feedback contains rich supervision for modeling how the environment responds to agent actions, we introduce \textit{agentic SElf-distilLation with environmental Feedback modeling} (SELF), a framework that jointly optimizes environmental feedback modeling and hindsight self-distillation. SELF learns to predict environmental responses while distilling guidance from a feedback-conditioned self-teacher into the policy. Our analysis reveals a mutually reinforcing mechanism: environmental feedback modeling strengthens hindsight supervision and policy learning, while self-distillation enhances the model's ability to model environmental feedback. With Qwen3-8B, SELF outperforms SDPO and GRPO by 6.4 and 4.1 percentage points in $τ$-bench success rate, and by 10.71 and 3.57 percentage points in AppWorld task goal completion, respectively. These results show that SELF uses environmental feedback more effectively within agentic self-distillation, improving agent capabilities.

---

### PlanWAM: Planning-Shaped Future Representations for End-to-End Autonomous Driving

Authors: Jinchang Xu, Hongda Yu, Fengwei Dong, Wenhui Huang, Xi Wei, Yongzhi Liu, Sunan Zhang, Jirao Wang, Chen Lv, Bingbing Li, Guodong Yin, Weichao Zhuang
Published: 2026-10-08
Categories: cs.RO, cs.LG
arXiv: https://arxiv.org/abs/2610.11382v1

World models in end-to-end autonomous driving predict future scene evolution to provide foresight for trajectory planning. Existing methods mainly study how to predict the future and how to use it, but less often ask which future representation is actually most useful for planning. To this end, we propose PlanWAM, a Planning-Shaped World Action Model. The key idea is to let the planning task shape the future-state representation, so that it retains the information most useful for planning. A latent world model then predicts this planning-shaped future latent representation from historical observations and uses it for planning, enabling foresighted planning. Specifically, we first use a Temporal Register Pyramid to compress multi-frame historical information in a recency-aware manner, learning a compact history representation oriented toward future reasoning and planning. We then introduce a privileged future posterior branch that observes ground-truth future frames, and shape its future latent representation with trajectory-planning objectives to obtain a planning-shaped future latent representation. Hindsight-to-Foresight Distillation trains a prior branch that depends only on history to predict this future latent representation. The predicted future latent representation serves as planning context and guides trajectory generation and selection. PlanWAM achieves 93.8 PDMS / 90.9 EPDMS on NAVSIM-v1/v2 navtest and reaches 38.7 HD-Score on closed-loop HUGSIM in a zero-shot setting, demonstrating leading planning performance across both open-loop and closed-loop evaluations. Extensive experiments further demonstrate that planning-shaped future representations provide an effective and deployable form of foresight for world-action models.

---

### EvoKnow: Continual Knowledge Evolution for AI-Generated Image Detection

Authors: Zhiheng Peng, Wenwei Jin, Yangshi Ge, Siyu Xia, Jiawei Li, Xu Tang
Published: 2026-10-08
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2610.11381v1

AI-generated image detectors are commonly trained on fixed generator domains and become difficult to maintain as new generative models emerge. Continual adaptation is challenging because replaying historical generated images is costly, whereas updating shared parameters with limited current-domain data can overwrite prior forensic knowledge. We propose EvoKnow, a replay-free framework that formulates continual AI-generated image detection as forensic knowledge evolution. EvoKnow preserves a shared forensic basis learned from base domains, incrementally adds isolated residual experts for complementary generator-relevant evidence, and retrieves expertise through an Analytical Incremental Router (AIR) updated in closed form from current-stage generated images and accumulated sufficient statistics. Experiments demonstrate effective cross-generator generalization, few-shot expansion, and long-horizon continual adaptation. With ten generated images per arriving generator, EvoKnow achieves 96.70% average accuracy on non-base GenImage generators and 94.48% accuracy on Chameleon without target-benchmark adaptation. Under a strict replay-free continual learning protocol, EvoKnow achieves state-of-the-art continual learning performance, attaining 96.32% mean stage-wise accuracy and 4.32% average forgetting.

---

### Equal Path Cost, Unequal Output Effects: Understanding Perturbation Propagation in Diffusion Models

Authors: Wei Guo, Yaowen Zhang, Xingtong Ge, Jun Zhang
Published: 2026-10-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.11380v1

Diffusion models have achieved remarkable success in generative modeling, with their sampling procedures routinely modified to control generation and improve efficiency. These modifications introduce perturbations along the sampling trajectory, raising a central question: how do such perturbations affect generated output? To address this question, we develop a theoretical framework to investigate perturbation propagation, combining dynamical analysis of the sampling process with an information-theoretic characterization of output responses. Within this framework, we quantify perturbation strength using the Kullback--Leibler (KL) divergence between perturbed and reference trajectory distributions, termed as path cost, which is shown to bound, but do not determine, changes in the output distribution. Building on this analysis, we derive a response identity that connects the propagation and accumulation of local perturbations with the information captured by a selected feature mean, explaining why changes in the output distribution can remain undetected by its first-order response. We test our theoretical analysis through controlled interventions at equal path cost in pretrained diffusion models, revealing distinct patterns of output sensitivity across sampling stages and spatial frequencies. To assess whether our framework can diagnose perturbations arising from practical approximations, we apply it to cache-based acceleration and show that our propagation analysis reliably identifies sampling intervals where caching causes larger image errors.

---

### FastJEV: Understanding Redundancy for Compact JEV Inference

Authors: Jie Ma, Jie Gao, Yihang Liu, Zhike Qiu, Junle Li, Chongyi Zhuang, Jiayi Ji, Xiaoshuai Sun
Published: 2026-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.11379v1

JEV models make multimodal decisions by directly scoring candidates. Although the common context is encoded once, candidate evaluation can still repeat matching token histories, duplicate inference states, and execute the full backbone. In this paper, we study these sources of redundancy and present FastJEV for compact candidate evaluation. We jointly organize history reuse and state storage, since sharing computation requires preserving states for later branches. We first introduce shared context anchoring to reuse recurrent initial states and omit unused final recurrent caches. We extend this reuse through candidate prefix sharing, retaining the intermediate states needed by subsequent branches. To further reduce the depth of these paths, we apply decision guided pruning based on relative score changes measured on a small unlabeled set. Our method retains full context encoding and all candidates without additional training. We evaluate FastJEV across three OmniJev model sizes on five public benchmarks and reconstructed LIBERO-10 offline questions. At the selected pruning budgets, the complete method reduces candidate depth by 43.75% to 45.83%, while retaining 93.66% to 97.52% of the original task scores on average across the six evaluation sets. Through controlled experiments, we show how candidate overlap and branching structure affect the execution cost of history reuse. In our implementation, candidate prefix sharing can reduce repeated computation while increasing latency. These findings motivate designing sharing granularity and execution schedules together for efficient JEV inference.

---

### CRISP: Fixing Flying Pixels in Latent LiDAR Generation via Diffusion Decoding

Authors: Andrea Ceron, Michael Schmidt, Alvaro Marcos-Ramiro, Sebastian Schmidt, Benjamin Busam
Published: 2026-10-08
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2610.11376v1

Latent LiDAR pipelines suffer from flying pixels: convolutional VAEs blur sharp radial depth discontinuities, yielding edge depths that back-project to points floating between surfaces. We identify this as a major, directly correctable decoder bottleneck and introduce CRISP: a pixel-space diffusion decoder with a backbone-agnostic latent adapter, DiT-based denoiser, and support mask predictor. CRISP replaces video-VAE and LiDAR-native decoders alike while keeping the encoder and latent generator fixed. Across KITTI-360, SemanticKITTI, and nuScenes, replacing only the decoder reduces FSVD/FPVD by 50.5% on average across frozen backbones; for generic video VAEs, the reductions reach 71%/74%. On the LiDAR-native LiDM backbone, FRID drops by 71%, with the largest gains at depth discontinuities. In a pretrained LiDM world model, the same zero-shot replacement improves FSVD by 15.5%, narrowing the sim-to-real gap.

---

### Rethinking Contrastive Loss in CLIP Post-training: A Complementary Framework with Frozen Text Encoder

Authors: Zidan Wang, Yaqian Li, Xiaokai Zhang, Kaiwen Long, Kun He, Hanpeng Liu
Published: 2026-10-08
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2610.11374v2

CLIP serves as a foundational vision-language model and the de facto vision encoder for downstream VLMs such as LLaVA. Post-training offers a lightweight route to refine CLIP, but recent work argues that the standard contrastive loss is unsuitable for post-training due to catastrophic forgetting under small batches, motivating designs that abandon the contrastive objective in favor of distillation. We revisit this premise and find that, for the InfoNCE objective, the reported forgetting is driven primarily not by insufficient negatives but by an inappropriate magnitude of the contrastive temperature $τ$: with $τ$ set sufficiently small, contrastive post-training improves rather than degrades the pretrained CLIP, which we explain through the temperature dependence of the InfoNCE gradient. Building on this finding, we propose \textbf{ComCLIP}, a lightweight single-epoch post-training recipe that freezes CLIP's text encoder---so the refined vision encoder is a drop-in replacement with unchanged architecture and inference cost---and trains the vision encoder with a properly-tempered contrastive loss, an MSE anchoring loss against the original CLIP, and a relational distillation loss from DINOv2. Over multiple seeds, ComCLIP matches the self-distillation baseline CLIP-Refine on zero-shot classification while significantly improving the transferability of visual features, measured by linear probing ($48.99$ vs.\ $42.28$ on ViT-B/16), and on ViT-L/14 it also improves MMVP over CLIP-Refine ($24.20$ vs.\ $19.01$); CLIP-Refine remains stronger on image-text retrieval. Used as a drop-in vision encoder for LLaVA-1.5-7B without re-aligning the projector or LLM, ComCLIP yields no net change across $8$ VLM benchmarks, i.e., the refinement does not break downstream compatibility. Code and models are available at https://github.com/showstarpro/ComCLIP.git.

---

### From a Prompt to Repertoires: Evolving Functional REpertoires Enable LLM Continual Learning

Authors: Fengyuan Liu, Yue Wang, Hangxi Guo, Fengyuan Liu, Chenxu Wu, Yanguang Liu, Mengnan Du
Published: 2026-10-08
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2610.11373v1

Continual learning remains challenging for large language models, which must enable models to acquire new skills and knowledge without degrading existing capabilities. Existing approaches typically address this challenge by carefully designing how model parameters are updated. In contrast, prompt optimization avoids costly parameter updates while achieving competitive or even superior performance to reinforcement learning methods such as GRPO on individual knowledge-intensive and reasoning tasks. This raises a natural question: \textit{Can prompt optimization, as an efficient adaptation approach, be directly applied to continual learning?} Our analysis shows that, under sequential task adaptation, it suffers from catastrophic forgetting, while optimized prompts accumulate rules that overfit to local task distributions. To address these limitations, we propose \emph{Evolving Functional REpertoires} (EFRE), which replaces a single prompt with a repertoire of functions that evolves as new tasks arrive: compatible updates refine existing functions, while conflicting updates trigger the emergence of new ones. On a three-task continual-learning stream, EFRE achieves a final average performance 7.50 percentage points higher than GRPO. Moreover, after adaptation to the Bio task, its performance on FinQA decreases by only 1.56 percentage points, compared with 25.10 percentage points for the base prompt optimization method. We further instantiate EFRE in a minimal agent system and observe consistent improvements across different backbone models. Overall, these results demonstrate EFRE's strong performance in continual learning for large language models and highlight its substantial potential for continual learning in advanced agent systems.

---

### SignRAG: Unified Retrieval-Augmented Gloss-Free Sign Language Translation

Authors: Zhi Rao, Yucheng Zhou, Qianran Sun, Yiqing Huang, Longcan Yuan, Jiayi Hou, Chengwen Yao, Lin Cheng, Donghui Sun, Xiaoxin Chen, Jun Wan
Published: 2026-10-08
Categories: cs.CL, cs.CV, cs.MM
arXiv: https://arxiv.org/abs/2610.11371v1

Contemporary decoder-only large language models (LLMs) have demonstrated strong capabilities across a wide range of domains. However, existing pretraining paradigms for gloss-free sign language translation (SLT) are largely designed around conventional encoder-decoder pretrained language models, which limits their direct applicability to decoder-only LLMs. To address this limitation, we propose SignRAG, a unified framework combining hierarchical pretraining, target-domain retrieval augmentation, and retrieval-aware reinforcement fine-tuning. Hierarchical pretraining first learns linguistically grounded sign representations and then jointly aligns the sign encoder with an LLM, mitigating cross-modal optimization imbalance. For downstream adaptation, SignRAG complements parameter-based fine-tuning with a target-domain retrieval gallery that provides instance-specific translation cues. To ensure that retrieved contexts are used appropriately, we further introduce Retrieval Utility-Guided Reinforcement Fine-Tuning (RUG-RFT), which combines translation-quality and retrieval-utility rewards to encourage beneficial retrieval use while suppressing harmful reliance. Experiments on multiple SLT benchmarks establish new state-of-the-art performance. In particular, to the best of our knowledge, SignRAG is the first gloss-free approach to outperform gloss-supervised methods across all reported metrics on CSL-Daily. Our code has been released at \href{https://github.com/shahelaojieraozhi/SignRAG}{GitHub}, together with models of different sizes to support future academic research.

---

### RIT-RAG: Navigating Document Corpora with Retrieval-Induced Trees

Authors: Meghanadh Pulivarthi, Swaraj Kumar Biswal, Kushagra Bhushan, Yatin Nandwani, Sachindra Joshi, Dinesh Raghu
Published: 2026-10-08
Categories: cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2610.11370v1

Retrieval-augmented generation (RAG) grounds language models in external corpora. Agentic RAG enables iterative search, yet exposes the model to isolated chunks without document structure, making it difficult to distinguish relevant evidence from chunks that merely resemble the query. Structure-aware methods such as PageIndex navigate document structure but cannot scale to the structures of large corpora, which do not fit in the LLM context. Hence, they first commit to a single document using a document retriever and cannot recover from a wrong choice. We propose RIT-RAG (Retrieval-Induced Tree RAG), which combines content retrieval with structural navigation. Offline, RIT-RAG builds a tree for each document from its table of contents or sitemap. At query time, it retrieves a broad set of chunks and uses their positions to induce manageable sub-trees, potentially across multiple documents. An LLM agent navigates these sub-trees, selectively reads promising nodes, and reformulates queries when needed. Thus, retrieval proposes where to look, while the agent decides what to read. Across financial, scientific, and customer-support benchmarks, RIT-RAG achieves the highest answer accuracy among vanilla, graph-based, and agentic baselines. On EntQABench, our new benchmark of 2.84 million technical-documentation webpages, it improves accuracy by 6.8 to 11.4 points over the strongest baseline across three LLMs.

---

### SpatialOPSD: Self-Distilling Spatial Intelligence from Verified Coding Agent Traces

Authors: Rongxue Li, Meng Yang, Yiru Mao, Yongliang Tao, Lulu Hu, Bin Yang, Zhao Xu, Weihua Luo, Bowen Xu
Published: 2026-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.11366v1

Spatial coding agents significantly improve spatial reasoning in Multimodal Large Language Models (MLLMs) by using external tools to generate verified execution traces. However, this paradigm inherently suffers from prohibitive inference-time overhead and external dependencies. In this paper, we explore whether an MLLM can internalize this agentic capability to operate entirely tool-free. We begin with a simple observation: prompting an MLLM with summarized execution traces of a spatial coding agent naturally unlocks the model's internal spatial Chain-of-Thought (CoT). Motivated by this, we introduce SpatialOPSD, an on-policy self-distillation framework that internalizes spatial reasoning into a standalone MLLM by formulating verified agent traces as privileged information. To mitigate privileged-information leakage during distillation, we introduce Repetition-Aware Distillation, which combines repetition masking with unlikelihood regularization. Experiments across multiple benchmarks demonstrate that self-distilling SpatialOPSD achieves higher average accuracy than SFT and GRPO on both spatial and OOD datasets, exhibiting superior performance and generalization.

---

### FlyMark: Training-Free Invisible Watermarking of 3D Gaussian Splatting via a Fruit Fly Connectome

Authors: Ziyuan Luo, Haoliang Li, Renjie Wan
Published: 2026-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.11364v1

A trained 3D Gaussian Splatting (3DGS) scene ships as a portable parameter array that can be copied, pruned, requantized, or repackaged outside its training pipeline, so ownership evidence is most useful when it lives in the released parameters and remains checkable long after the embedding tooling is gone. Existing 3DGS watermarks typically tie embedding or extraction to scene optimization, a learned decoder, or rendered views, so the evidence survives only as long as a second trained artifact does. FlyMark instead writes a keyed message into the parameters a 3DGS file already stores. Its carrier directions are derived from the photoreceptors of a published connectome, a citable versioned artifact that fixes the geometry exhaustively and leaves nothing to tune per scene. A virtual observer reads cone-wise apparent luminance along a scene-normalized orbit from stored centers, colors, and opacities; a keyed dithered quantization-index-modulation code replicates each message bit across these observations; and one sparse bounded least-squares solve realizes the targets through achromatic shifts of existing degree-zero colors under a hard per-channel linear-RGB bound. All geometry and higher-order appearance parameters are preserved bit-identically, and extraction needs only cone queries, rounding, and majority voting. Under a model-domain threat model on synthetic and real scenes, FlyMark attains high clean bit accuracy and visual fidelity while cleanly separating matched from wrong keys.

---

### UniData: Universal Multimodal Instruction Generation Pipeline

Authors: Jiaqi Tang, Yi-Feng Wu, Yuting Zhang, Hao Lu, Bowen Fu, Qing-Guo Chen, Xiaogang Xu, Yuwei Hu, Shiyin Lu, Wei Wei, Lei Zhang, Zhao Xu et al.
Published: 2026-10-08
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2610.11363v1

Multimodal Large Language Models (MLLMs) are increasingly being applied in a wider range of real-world scenarios. However, due to the substantial labor cost, creating high-quality multimodal instruction datasets for MLLMs remains a significant challenge. Although some methods propose to generate instruction data, they often face limitations in modality support and struggle with generating multi-round instructions. To address these problems, we introduce UniData, a universal instruction generation pipeline, to transform simple user requirements into multi-round, multimodal instructions. Specifically, UniData first expands user requirements into multiple diverse events. Using these events, UniData then integrates an any-to-any large model for multimodal instruction generation. Finally, UniData enhances data quality by correcting irrelevant and redundant inference flow, leveraging correlations between instruction rounds. To train this pipeline, we also build UniDataset, a dataset comprising 20,000 entries across nine modalities for improved multimodal generation. Our experiments demonstrate that UniData achieves SOTA performance in data quality and can also enhance the understanding and generation capabilities of other multimodal models.

---

### Bernoulli Flow Models: Self-Consistent Generative Modeling for Binary Data

Authors: Hao Mo, Liying Yang, Shumin Yao, Xinxing Yu, Ajian Liu, Xudong Mao, Yanyan Liang
Published: 2026-10-08
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2610.11362v1

Binary diffusion models typically require a large number of function evaluations (NFEs) to generate high-quality samples, making practical inference computationally expensive. Reducing NFEs while preserving sample quality without distillation or additional training remains a significant challenge. Existing binary diffusion models define a discrete one-step forward path and then derive the reverse posterior. In low-NFE settings requiring cross-step sampling, they approximate the true multi-step likelihood with a single-step likelihood transition, which severely degrades sample quality. To address this fundamental limitation and decouple the generative dynamics from fixed discrete time steps, we propose Bernoulli Flow Models (BFM). Rather than relying on sequential one-step Markov diffusion chains, BFM defines a unified continuous global Bernoulli probability flow path between data distributions and pure noise, from which we derive analytical closed-form posterior transitions over arbitrary time intervals. Consequently, reducing the inference NFE is no longer an approximation based on skipping discrete steps; it only requires re-evaluating the analytical posterior over a new time grid. This eliminates the structural training-inference mismatch inherent to discrete chains and yields self-consistent low-NFE sampling. Experiments show that BFM is highly robust to aggressive NFE reduction. On LSUN Churches 256x256, a BFM trained with 256 steps achieves an FID of 9.22 using only 16 sampling steps, whereas the state-of-the-art discrete baseline degrades to 204.10. BFM also remains competitive with continuous and discrete generative baselines under standard full-step inference. These results establish BFM as a theoretically rigorous, self-consistent, and practically effective framework for fast binary data generation.

---

### SepGen: Multi-Stem Audio-Video Separation and Generation in a Single Model

Authors: Aviad Dahan, Rajaei Khatib, Yonatan Bitton, Idan Szpektor, Lior Wolf, Raja Giryes
Published: 2026-10-08
Categories: cs.SD, cs.CV
arXiv: https://arxiv.org/abs/2610.11361v1

A 4D audio-visual scene comprises a video, the dynamic geometry it depicts, and the sound sources that populate it, each with its own position and trajectory. Rendering such a scene from a novel viewpoint requires that every source be available as an individual waveform, so that it can be localized in the scene and propagated to the observer before the signals are mixed. Joint audio-video generators can synthesize the video and its soundtrack, but the soundtrack is emitted as a single audio-mix in which the sources are not individually accessible. We present SepGen, which extends a pretrained audio-video generator to emit the video, the mixed soundtrack, and one waveform per captioned source in one joint sampling run. SepGen supports two complementary modes: generation and separation. In generation mode, each source caption specifies what its stem contains. A two-speaker dialogue, for example, comes out as one stem per speaker in the original turn order. In separation mode, the input audio-mix remains clean while the captions specify what to extract, so the model can decompose a recording from a free-text description. We evaluate generation on scenes synthesized from text, and separation on scenes rendered by other generators and on real recordings of speech, music, and sound effects. Given an audio-mix and captions that carry the spoken lines, SepGen outperforms language-conditioned separators, most clearly on speech, and it keeps the lead when the lines are removed from the captions. Code, checkpoints, and datasets are available at https://sepgen.github.io/

---

### RaReCache: Bridging the Gap in Cross-Model KV Cache Reuse via Rank disagreement-based Selective Recomputation

Authors: Sreetama Sarkar, Saptarshi Mitra, Sitao Huang, Souvik Kundu, Peter A. Beerel
Published: 2026-10-08
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2610.11358v1

Cross-model KV-cache reuse remains a key challenge in modern LLM serving. Coding agents and multi-model systems increasingly route a shared context across models: a user may switch models mid-session, or a cascade may escalate a difficult query. Because KV caches contain model-specific representations, each switch typically forces the receiving model to prefill the entire context from scratch. Recent work shows that closed-form linear maps can translate KV caches between models in the same family, but transfer accuracy degrades as the model-size gap widens. In this paper, we establish that these transfer failures are concentrated in a small subset of information-dense tokens. To bridge this gap, we introduce RaReCache, a framework that enables a large target model to decode accurately from a cache prefilled by a much smaller source via selective recomputation. RaReCache identifies these critical positions using a novel rank disagreement metric, scoring each token by the energy of its mapped KV in output directions weakly supported by the calibration data. Across two model families and five benchmarks, on a 23x parameter gap (Qwen3-0.6B to 14B) recomputing just 30% of positions retains 95-99% of the target accuracy, whereas on a 8.8x gap (Llama3-8B to 70B), recomputing 40% retains 96.5% of the target accuracy. RaReCache largely removes sensitivity to source-model size, and achieves up to a 3.04x prefill speedup. For online serving, it handles 1.8x the request throughput of target prefill on a single GPU, and at the target's saturation load, reduces median and 99th-percentile time-to-first-token (TTFT) by 5.0x and 6.4x respectively, with a 30% recompute budget. RaReCache establishes an efficient serving paradigm where small models prefill on behalf of massive targets, enabling large models to recompute only critical tokens, drastically reducing prefill latency.

---

### Adaptive Adversarial Augmentation for Controllable Face Synthesis

Authors: Saransh Suri, Shivang Agarwal, Mayank Vatsa, Richa Singh
Published: 2026-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.11356v1

Synthetic data provides a scalable alternative to real-world datasets for training face recognition models, particularly under challenging conditions such as low resolution, occlusion, and masks. Yet, most approaches lack diversity and fail to generalize effectively. We propose Ensemble Feedback Controllable Synthesis (EFCS), a guided framework that generates diverse and challenging samples while preserving visual realism. EFCS expands distributional variability, often reflected in higher FID and KID scores compared to single-feedback and random synthesis, while maintaining high precision. Recognition models trained on EFCS data consistently outperform baselines across multiple benchmarks, showing improved generalization to real-world scenarios. Furthermore, we introduce an analytically motivated formulation linking perturbation-induced difficulty, sample utility, and performance degradation, offering principled insights into balancing synthetic data complexity for optimal training. Together, these contributions establish EFCS as an effective and analytically grounded approach for bridging the gap between synthetic and real datasets.

---

### Defensive Writing in GPT Models

Authors: Junchi Liao, Xiao Huang, Yucheng Liu, Jiawen Deng, Fuji Ren
Published: 2026-10-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.11355v2

Researchers increasingly use ChatGPT to revise their papers, and when asked to make a paper hold up under review, recent GPT versions often narrow or even retract the authors' claims. We call such changes defensive writing when the given material does not support them, and we test two explanations: the model corrects the authors' overclaiming, or it writes for an anticipated reviewer. We ask GPT versions and models from other developers to rewrite paragraphs from papers written before ChatGPT, or to write from an evidence sheet that lists a paper's method and results. From GPT-5.5 on, GPT versions add clearly more ungrounded qualifications than the authors' originals contain, and GPT-6-astra adds the most and often retracts the authors' claims. Each explanation fits one part. Checked against the full papers, GPT-6-astra's retractions mostly correct overstated claims or explanations, but most added qualifications are redundant. The qualifications follow the request: they are absent under polishing, appear with any request to check the claims, and peak when the prompt names a reviewer's concerns. AI reviewers score such rewrites higher and score them lower once only the qualifications are removed, while human readers in a small study find them harder to read. Combining AI writing with AI review may reward qualifications that readers pay for.

---

### AdaptEvo: Learning under Imperfect Supervision through Confidence-Adaptive Training with Knowledge Evolution

Authors: AllSpark Team
Published: 2026-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.11354v3

Rule-governed contextual decision tasks require models to apply specified rules to case-specific context and evidence. Written rules can leave gaps in decision guidance and process evaluation, while reference judgments vary in their support from the rules and evidence. To address these challenges, we introduce AdaptEvo, a framework for learning under imperfect supervision that couples confidence-adaptive policy optimization with evolving decision knowledge and evaluation rubrics. Its Training module uses Confidence-Adaptive GRPO (CA-GRPO) to balance outcome and process rewards according to reference confidence. Its Evolution module synthesizes reusable decision knowledge from recurring failures across training cases and refines process rubrics to detect overlooked errors. To support empirical evaluation, we construct an industrial multimodal content moderation dataset comprising a training set and In-Period and Out-of-Period test sets, with the latter collected under changed rules. Using Qwen3.6-35B-A3B, AdaptEvo achieves 61.9% exact-label accuracy and 72.2% binary decision accuracy on In-Period, exceeding GRPO by 7.5 and 3.7 percentage points, respectively. On Out-of-Period, the policy trained with CA-GRPO retains exact-label accuracy gains over the base model across evaluated checkpoints without injected decision knowledge, while GRPO declines with continued training. CA-GRPO also outperforms the tested fixed reward mixtures on both Out-of-Period metrics.

---

### RL-ARC: Calibrating Large Reasoning Models via Reasoning-guided Uncertainty

Authors: Gukhyeon Lee, SangKeun Lee
Published: 2026-10-08
Categories: cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2610.11352v1

Language models (LMs) are commonly trained with Reinforcement Learning with Verifiable Rewards (RLVR) to enhance their reasoning capabilities. However, since RLVR does not explicitly account for calibration during training, it can lead to severe calibration degradation, including overconfidence. Recent calibration-aware training methods for LMs, which incorporate objectives for uncertainty estimation into training, improve calibration but still exhibit overconfidence under distribution shift, while sacrificing reasoning performance. To this end, we propose RL-ARC, a calibration-aware training framework that jointly leverages reasoning confidence and answer confidence. Specifically, RL-ARC leverages reasoning confidence as an auxiliary signal for calibrating answer confidence, applying it as reasoning-guided regularization for correct cases and as an overconfidence penalty for incorrect cases. Comprehensive results across ID and OOD settings show that, beyond improving calibration, RL-ARC enables reasoning models to adaptively estimate confidence based on the given question without substantially sacrificing reasoning performance, thereby highlighting the importance of reasoning confidence for training reliable reasoning models.

---

### Deception by Omission: Language Models Knowingly Hide Their Mistakes

Authors: Lucas Florin, Amelie Knecht, Ulysse Schaller, Thilo Hagendorff
Published: 2026-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.11351v1

Large language models (LLMs) increasingly act as agents with little human oversight, so potential mistakes they make can go unnoticed. Users then depend on the model to report what went wrong. An honest model discloses its mistakes, while a deceptive one conceals them. However, it is unclear how current LLMs behave in such situations. In this study, we prefill LLM trajectories with synthetic mistakes. The trajectories resemble real deployments in chat and agentic settings. Models fail to disclose their mistake in 36.4% of chat and 67.1% of agentic rollouts. In 2.4% and 5.3% of rollouts, respectively, they are aware of the mistake in their chain of thought but still deceptively conceal it. Rates vary by model: for instance, Gemini 3.5 Flash knowingly conceals mistakes in up to 19.9% of agentic rollouts. In 11.9% of chat and 51.8% of agentic rollouts, models show no awareness of mistakes, even though they reliably spot them when reviewing the same transcript as an outside observer. Our results show that, as agents take on more tasks with less oversight, users cannot rely on them to self-report possible mistakes. Developers should instead use independent monitors that review agent trajectories, or specifically train models to check their past actions and disclose what they find.

---

### Sample-Efficient Generative Conformal Prediction

Authors: Minxing Zheng, Shixiang Zhu
Published: 2026-10-08
Categories: cs.LG, stat.ME
arXiv: https://arxiv.org/abs/2610.11349v1

Generative conformal prediction builds uncertainty sets from samples of a conditional generator, which are efficient only when the samples represent the response distribution well. This can require many samples, each of which can be costly, as in large diffusion models and scientific simulators, so the sampling budget must be used efficiently. Existing methods draw the same number of samples at every input, wasting samples where the response distribution is simple and undersampling where it is complex, which inflates sets and leaves those inputs under-covered. We propose CASA (Conformal Adaptive Sample Allocation), which characterizes the marginal value of an additional sample and allocates samples across inputs to minimize the expected set size subject to marginal coverage and an average sampling budget. Theoretical analysis shows that adaptive allocation yields smaller sets than a fixed count at the same budget: a missed mode forces a radius that spans the gap between modes, and even oracle radius cannot compensate for it. On synthetic and real tasks, CASA produces substantially smaller sets at the same budget, often improves conditional coverage, and complements existing radius-adaptive methods.

---

### EgoPhys: Estimating Peak Contact Force and Mechanical Work from Egocentric Manipulation Video

Authors: Zhuo Dong, Jianhua Yang, Haohao Li, Yumeng Zhao, Keji He, Yan Huang, Liang Wang
Published: 2026-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.11347v1

Physically grounded manipulation of articulated objects requires understanding both the maximum forces encountered during contact and the work performed as their parts move. Peak contact force and mechanical work quantify these complementary aspects, but estimating them from egocentric video is challenging because physical interaction cues are local and indirect. Moreover, peak force is associated with brief contact events, whereas mechanical work depends on force-motion coupling throughout the contact duration. To address these challenges, we propose EgoPhys, an RGB-only framework comprising Contact-Aware Spatial Aggregation (CASA) and Target-Specific Multi-Expert Temporal Routing (TMTR). CASA integrates appearance and geometry features to emphasize interaction-relevant cues, while TMTR models semantic, event, and motion cues with specialized temporal experts and routes them separately for force and work prediction. On the test split from Hoi! dataset, EgoPhys substantially improves predictions of peak force and mechanical work, achieving MAEs of \(5.205 \pm 0.584\) $N$ and $0.894 \pm 0.081$ $J$, respectively.

---

### SynCo: Data Synthesis Co-Training for Self-Evolving LLMs via Multi-Agent Reinforcement Learning

Authors: Wei Yang, Shawn Li, Yuehan Qin, Yawei Wang, Mingxi Wang, Shixuan Li, Tiankai Yang, Jiate Li, Jesse Thomason, Xuezhe Ma, Yue Zhao
Published: 2026-10-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.11345v1

Self-evolving LLM agents promise to improve autonomously through continual interaction and learning, reducing their dependence on manually curated supervision. Realizing this promise requires not only updating the agent, but also evolving its training experience as its capabilities change. However, most existing pipelines rely on static datasets or separately updated synthesis models, causing previously useful tasks to become trivial while overly difficult tasks remain uninformative. This growing mismatch between agent capability and training experience limits sustained self-improvement. To address this problem, we propose SynCo, an agentic data synthesis co-training framework for self-evolving LLMs based on multi-agent reinforcement learning. SynCo jointly optimizes two independently parameterized agents: a Synthesizer that constructs training tasks from the Reasoner's evolving capability state, and a Reasoner that learns from the resulting experience. Each synthesized task induces multiple Reasoner rollouts whose outcomes provide complementary rewards to both agents. Correctness feedback improves the Reasoner, while task quality, answer reliability, and outcome-grounded teachability guide the Synthesizer. Their updates are fed back into subsequent synthesis rounds, allowing the task-solving policy and its training distribution to evolve together. Extensive experiments across eight mathematical reasoning benchmarks demonstrate that SynCo substantially outperforms a broad range of existing synthetic-data methods and controlled baselines, achieving the strongest overall performance while deriving most of its gains from previously unsolved problems.

---

### EvoSim: Learning to Model, Modeling to Learn

Authors: Yun-Wei Song, Jinkai Tao, Jun-Dong Zhang, Rui Zhang, Yi-Min Wu, Qiang Zhang
Published: 2026-10-08
Categories: cs.AI, cs.CE
arXiv: https://arxiv.org/abs/2610.11344v1

Physics-based models connect scientific explanation with quantitative prediction. Constructing them requires selecting physical processes, defining states and governing equations, specifying couplings, and identifying parameters from experiments. Existing AI systems remain limited in making these model structure decisions autonomously. We introduce EvoSim, a self-evolving AI scientist for physical modeling. It uses experimental discrepancies to drive mechanism and equation revisions and held-out experimental data to test physical plausibility. Exploration traces make updates to knowledge, skills, and multi-agent orchestration. This co-evolution improves physics-based models and EvoSim's ability to select mechanisms, diagnose failures, and coordinate research. We evaluate EvoSim on two industrial battery modeling tasks. It predicts lithium-metal-plating onset from 25 to 45 degrees Celsius and 2 C to 6 C with a mean absolute error of 1.79% in state of charge. Dynamic voltage prediction under vehicle driving conditions achieves a root mean square error of 7.62 mV, surpassing the reported accuracy of models developed by human experts. Self-evolution reduces model and physics errors by approximately 36% relative to baseline, demonstrating improved scientific modeling capability. EvoSim turns experimental observations into validated models and cumulative research expertise.

---

### Point-Focused Attention Meets Context-Scan State Space: Robust Biological Visual Perception for Point Cloud Representation

Authors: Kanglin Qu, Pan Gao, Qun Dai, Yuanhao Sun
Published: 2026-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.11342v1

Synergistically capturing intricate local structures and global contextual dependencies has become a critical challenge in point cloud representation learning. To address this, we introduce PointLearner, a point cloud representation learning network that closely aligns with biological vision which employs an active, foveation-inspired processing strategy, thus enabling local geometric modeling and long-range dependency interactions simultaneously. Specifically, we first design a point-focused attention, which simulates foveal vision at the visual focus through a competitive normalized attention mechanism between local neighbors and spatially downsampled features. The spatially downsampled features are extracted by a pooling method based on learnable inducing points, which can flexibly adapt to the non-uniform distribution of point clouds as the number of inducing points is controlled and they interact directly with point clouds. Second, we propose a context-scan state space that mimics eye's saccade inference, which infers the overall semantic structure and spatial content in the scene through a scan path guided by the Hilbert curve for the bidirectional S6. With this focus-then-context biomimetic design, PointLearner demonstrates remarkable robustness and achieves state-of-the-art performance across multiple point cloud tasks.

---

### Type-Checking for Pattern-Based Tree Transformations

Authors: C. Aiswarya, Sahil Mhaskar, M. Praveen
Published: 2026-10-08
Categories: cs.FL, cs.CL
arXiv: https://arxiv.org/abs/2610.11337v1

We introduce and study pattern-based tree transformations. As an illustrating example, consider a source pattern $(x \cdot y) + (x \cdot z)$ and a target pattern $x \cdot (y + z)$ as a pair. This source pattern matches any expression $e$ of the form $(e_1 \cdot e_2) + (e_1 \cdot e_3)$ (by substituting $x$ with $e_1$, $y$ with $e_2$, and $z$ with $e_3$) and the pair transforms it into the expression $e_1 \cdot (e_2 + e_3)$ as dictated by the target pattern. Note that in this example, the set of expressions that match the source pattern is not a regular tree language. We propose a model of tree transformations given by a finite representation of a (possibly infinite) set of such (source pattern, target pattern) pairs. The expressive power of this model comes at the cost of undecidability of checking equivalence. Nevertheless, we show that the type-checking problem is decidable for our model of pattern-based tree transformations. The type-checking problem asks whether applying a given transformation to trees having a given regular property (type) preserves the property. Our decision procedure is by a reduction to the emptiness problem of alternating tree automata.

---

### ReCast: Attribution-Oriented Step Representation Learning for LLM-Based Agent Systems

Authors: Weilin Jin, Mingyu Wang, Taiyu Zhu, Ziqi Zhou, Wenbo Li, Haoyang Huang, Nan Duan, Yifan Wu, Ying Li, Zhonghai Wu
Published: 2026-10-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.11334v1

In LLM-based agent systems, failures can originate from early steps whose effects propagate through subsequent interactions, making their origins difficult to identify. To trace such failures back to their origin, failure attribution has been formulated as the task of identifying the earliest step responsible for the failure. Recent methods leverage LLM internal signals for failure attribution, typically using hidden states as step representations. We therefore conduct an empirical study to evaluate how effectively these representations distinguish root-cause steps from other steps and find limited separation. Motivated by this observation, we propose ReCast, a step representation learning method that transforms hidden states from a frozen LLM into attribution-oriented step representations. ReCast first selects attribution-relevant layers, then constructs complementary pattern and deviation features, and finally learns contextualized step representations through an encoder trained with contrastive and ranking objectives. We also introduce ReCast-2K, a training dataset for failure attribution. ReCast achieves the best Hit@1 across four benchmarks, surpassing the strongest baseline by 5.65 and 9.19 pp on Who&When Algorithm and Handcrafted, respectively. Code is available at https://anonymous.4open.science/r/ReCast-5FB6 .

---

### TokenBank: Financial Infrastructure for AI Services

Authors: Cary Chang, Jialin Zhou
Published: 2026-10-08
Categories: cs.AI, cs.CE
arXiv: https://arxiv.org/abs/2610.11333v1

AI services incur inference costs during execution, while revenue may arrive later. Changing API prices, limited upfront capital, and service failures can limit operators' ability to sustain or expand their services. Beyond reducing per-request costs, operators need to plan future spending, fund execution before revenue arrives, and obtain compensation for specified losses. This requires clear agreements across services with different pricing and execution conditions. These agreements must distinguish rights to consume services from rights to receive payments, define obligations under uncertain costs and income, and specify which failures qualify for compensation and how much can be paid. We present TokenBank, a financial infrastructure that represents these commitments through structured contracts. It supports service-consumption rights, agreements that settle API-price differences in cash (forwards), financing through limited rights to future service revenue, and protection claims for specified service failures. Contracts specify participants, covered services, validity, ownership, fulfillment conditions, and settlement rules. Evaluation combines replay of 899,441 API requests, real model-driven agent execution, and contract API tests. In a zero-discount rising-price resampling scenario, forwards reduce mean expenditure by USD 304.88 but increase its standard deviation from USD 1,152.45 to USD 1,190.82. A controlled replication with five portfolios per capital condition finds mean contribution differences between financing and self-funding of +1.0635, -0.1406, and -0.2962 experimental USD under low, baseline, and ample capital, respectively. The evaluation distinguishes contract correctness from economic effectiveness under declared economic and failure assumptions; supplier invoices and commercial revenue are unavailable.

---

### ReCal: Calibrating Structured Pruning for On-Policy Distillation Recovery

Authors: Houcheng Jiang, Mao Zheng, Mingyang Song, Qiyong Zhong, Jie Sun, Tianyu Zhang, Junfeng Fang
Published: 2026-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.11332v1

Structured pruning reduces the deployment cost of reasoning language models, but the resulting capability degradation can hinder subsequent on-policy distillation (OPD) recovery. Because OPD relies on student-generated trajectories, pruning damage that persists after offline distillation can limit its effectiveness. We propose RECAL, Recovery-Aware Calibration, a simple plug-and-play approach that improves OPD recovery by adjusting calibration before pruning. RECAL uses forward KL between an unpruned teacher and a pruned probe to identify teacher-supported predictions disrupted by pruning, then reweights calibration statistics to guide existing pruning criteria toward preserving these predictions. Across multiple models and pruning methods, RECAL consistently improves mathematical reasoning after OPD, achieving gains of up to 16.7 percentage points on AIME, alongside improvements in most code-generation comparisons. Further analysis shows that RECAL reduces residual damage at heavily affected tokens and establishes performance advantages that persist through recovery. These results demonstrate the value of recovery-aware calibration for improving on-policy distillation recovery of pruned reasoning models.

---

### PathLang: A Language-Centered Benchmark for Vision-Language Models in Computational Pathology

Authors: Fanqi Cheng, Kuo Gong, Shangke Liu, Beidi Zhao, Junchao Zhu, Zheyu Zhu, Leiyue Zhao, Fengbei Liu, John Cannon, Gang Wang, Zu-hua Gao, Kenji Ikemura et al.
Published: 2026-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.11329v1

Pathology vision-language models (VLMs) have shown strong visual perception ability, but their robustness in the language domain remains poorly characterized. Existing pathology VLM benchmarks largely rely on canonical closed-set prompts or perturb only generic templates, treating language as a fixed evaluation component rather than a variable axis of model behavior. In clinical practice, however, diagnostic language varies across reports, institutions, and candidate diagnoses. We introduce PathLang, a language-centered and clinically grounded zero-shot benchmark. PathLang holds the underlying slides, ground-truth labels, and image-text evaluation direction fixed while systematically varying only the diagnostic language, so that performance differences reflect how a diagnosis is phrased rather than what is imaged. The language variation follows how pathologists actually rephrase diagnoses (terminology, specificity, and reporting style), and all prompts and candidate pools are validated by six board-certified pathologists. PathLang covers four task families: (1) zero-shot classification with image-text alignment analysis, (2) cross-modal retrieval, (3) paraphrase robustness, including semantic-equivalence paraphrases, length and reporting-style variation, and prompt ensembling, and (4) open-vocabulary diagnosis retrieval over four candidate pools with distinct forms of semantic competition. Across nine VLMs and five public datasets spanning four organs, we find that performance is highly sensitive to clinically equivalent paraphrases, varies substantially across forms of semantic competition, and that image-text alignment quality does not necessarily translate into inter-class separability. We release the prompt corpus, candidate pools, pre-computed text embeddings, and evaluation code at https://anonymous.4open.science/r/PathLang.

---

### Mine Odyssey: Benchmarking Spatial Agentic Intelligence in the Wild

Authors: Yuxuan Cao, Junlong Li, Hao Li, Junxian He
Published: 2026-10-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2610.11328v1

Advances in foundation models are driving efforts to introduce agents to assist people in the physical world. Such agents require agentic spatial intelligence: exploring unfamiliar environments, updating spatial understanding through interaction, and adapting actions based on feedback to sustain progress toward a sequence of goals. Existing benchmarks cover only a limited range of spatial layouts, scales, and traversal requirements. We introduce Mine Odyssey, a benchmark for evaluating agentic spatial intelligence using Minecraft reconstructions of real-world locations. It comprises 180 tasks covering 30 such locations across 20 countries and regions on five continents, including 20 outdoor and 10 indoor settings. These settings span diverse spatial scales, layouts, terrains, and connectivity patterns, from Midtown Manhattan and rural Entrup to Santa Lucía Hill and Buckingham Palace. We select meaningful waypoints, such as landmarks, buildings, and rooms, and manually verify their accessibility. Each task provides a natural-language instruction specifying which waypoints to visit and in what order. Completing these tasks requires agents to find accessible routes and entrances, open doors, and move between levels using stairs and ladders, while monitoring their progress and recovering from navigation errors. Across eight evaluated state-of-the-art models, GPT-6 Astra achieves the highest success rate of 85.6%. However, the second-best model, Claude Opus 5.5, completes 73.9% of tasks, while the strongest evaluated open-weight model, DeepSeek-V4.1-Flash, reaches 23.9%, highlighting substantial room for improvement in the agentic spatial intelligence of current models. Comprehensive analyses and ablation studies on Mine Odyssey reveal current models' limitations and provide insights for advancing agentic spatial intelligence.

---

### It's Always 10:10: Reference Images Break a Bias That Prompts Only Dent

Authors: Luca Cazzaniga
Published: 2026-10-08
Categories: cs.CV, cs.HC
arXiv: https://arxiv.org/abs/2610.11320v1

Text-to-image models appear to reproduce the habits of the photographs they learned from. Analog clocks are an extreme case: in advertising, watches almost always show 10:10, and generated clocks return to 10:10 even when another time is requested. We measure this bias and test three ways of overcoming it on 52 models available on the Magnific platform, with a replication on Higgsfield. Every image shows three identical clocks that must show 2:35, 6:50 and 11:20. The description of the object is fixed and only the request about the time changes: no time (A), the time in digits (B), the hand positions described by construction relative to the dial numerals (C), or the same description plus a drawn reference dial (D). Two AI readers read all 1,799 images blind from coded copies, with a third reader and the author settling disagreements (dial-level agreement 96.0% and 97.3%). With no time requested, 67% of the images have all three clocks at 10:10. On the 20 current models, all three clocks are correct in 34% of the images with digits, 30% with the hands described in words and 75% with the reference dial (D-B: +37 points, 95% CI +28 to +45); we found no evidence that describing the hands in words beats the digits (C-B: -4 points, CI -10 to +1). The replication on the 12 models shared by both platforms gives the same picture (B 54%, C 50%, D 81%). Writing the time reduces the bias but leaves two thirds of the images of the 20 current models with at least one wrong clock; adding a drawn reference raises full accuracy to three quarters and almost eliminates images entirely at 10:10. We release all images, prompts, raw readings and a script that recomputes every result.

---