跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+197新增论文
+151其中 AI 相关
+16已有论文修订
+91新增 AI 导读

arXiv 最近完成扫描:2026-11-22 08:44 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-21 09:57 — 2026-11-22 09:57(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-22 08:44最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

29,158 已收录论文24,181 AI 相关8,992 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 21,490 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-22 08:42(北京时间)
新论文 · v1arXiv:2611.10566

Online Geometric Consistency Assessment of LiDAR Measurements via Recursive Bayesian Comparison

Mingqiao Han, Qigeng Duan, Xuchen Liu, Jinqiang Cui, Xi Chen, Ben M. Chen

原文摘要

LiDAR-based localization and mapping systems produce registered point clouds that serve as geometric measurements for downstream estimation and navigation. Registration errors introduce duplicated surfaces and structural deformation into these measurements. In the absence of an independent reference, online assessment relies on geometry accumulated from earlier measurements. Such assessment requires tolerance to sampling variation and an accumulation process in which observations enter the history only after evaluation. We therefore formulate a recursive Bayesian comparison that couples geometric assessment with history maintenance. A Normal-Inverse-Wishart model represents historical voxel geometry and its uncertainty, while a weak isotropic reference adapts to current sampling. Comparing the marginal predictive support of the same current points under both models yields Normalized Drift Evidence (NDE). Assessment precedes assimilation: positive NDE triggers an alarm and preserves the preceding historical state; otherwise, the current observations update the history. Across 14 real-world sequences totaling approximately 73 min from four platform types, alarms identified all nine corrupted sequences and were absent from all five consistent sequences. In four representative scenarios with event references, first alarms occurred within 0.9 s of the reference times, with no preceding alarms. Cross-backend evaluation demonstrates consistent responses to reconstructed geometry. Ablation and controlled perturbation results establish the roles of uncertainty modeling, recursive history, displacement, and geometric support. Mean processing time is 4.2--6.1 ms per update at 1 Hz. In ten UAV trials, alarms initiated odometry isolation, landing, relocalization, and mission continuation.

cs.RO · eess.SY

版本更新 · v2arXiv:2605.13414

TRIAGE: Evaluating Prospective Metacognitive Control in LLMs under Resource Constraints

Zabir Al Nazi, Shubhashis Roy Dipta

原文摘要

Deploying language models as autonomous agents requires more than per-task accuracy: when an agent faces a queue of problems under a finite token budget, it must decide which to attempt, in what order, and how much compute to commit to each, all before any execution feedback is available. This is the prospective form of metacognitive control studied for decades in human cognition, yet whether language models possess it remains largely untested. We introduce TRIAGE, an evaluation framework in which a model receives a task pool and a token budget calibrated to its own baseline cost, and commits to a single ordered plan that jointly encodes selection, sequencing, and per-problem allocation. Plans are scored against an oracle built from the measured solvability and token costs of the model, using triage efficiency normalized between random and oracle performance, together with normalized regret relative to the oracle. We evaluate frontier and open-source models, with and without reasoning enabled, across competition mathematics, graduate-level science, code generation, and expert multidisciplinary knowledge, and find that current language models exhibit substantial gaps in prospective metacognitive control, revealing a previously unmeasured capability dimension with direct implications for resource-efficient agent deployment.

cs.AI

版本更新 · v2arXiv:2611.06228

Separation Is a Riesz Energy: How Many Environments Does ICA Need?

Yuda Bi, Yubo Guo, Jiaxiao Cai, Xiaonai Li, Zhuolin Li, Vince D. Calhoun

原文摘要

How many environments and samples does it take to separate $d$ Gaussian sources whose variances change across environments? Each source has a signature, its vector of variances. The Riesz $2$-energy $E_j$ of source $j$ sums the inverse Fisher informations for rotating it towards other sources. With known whitening, we prove a worst-case squared-angle risk lower bound of order $E_j/(n+E_j)$ for orthogonal estimators at every $n$ and $d$. A quadratic pencil given the signatures attains $E_j/n$ up to a constant above a separation-dependent sample threshold, even with estimated whitening. For well-spread signatures at fixed $K$, the energy grows as $d^2$, $d\log d$ and $d$ for $K=2$, $3$ and $K\ge4$, respectively. A design with $K\asymp\log d$ and pairwise Fisher information bounded below by a constant makes $d\log d$ samples sufficient. The eigenvectors of a single fixed linear combination have an average first-order error coefficient of at least order $d^2$. Simulations up to $d=1000$ support the first-order predictions, and on task fMRI the energy helps rank split-half instability.

cs.LG · cs.IT · stat.ML

版本更新 · v2arXiv:2610.37413

Displacement Moments and Path-Terminal Separation in Brownian Interpolant Sampling

Zhong Han

原文摘要

We prove early-stopped, target-to-output KL guarantees for Brownian interpolant Euler sampling from the true source under arbitrary Borel couplings, even with nonintegrable endpoints. At fixed stopping time and noise level, a fourth displacement moment yields an $O(N^{-1})$ discretization term. A second moment suffices for fixed-law convergence with grid refinement and vanishing drift error. For one fixed coupling with no displacement moment above two, the original and comparison paths have KL of orders one and $1/\log N$ relative to the exact-drift Euler path. On the same geometric grid, terminal KL is at most $C/N^2$. The path decomposition identifies the information about the source discarded by Markov projection. When the original bridge is Markov, current-state Euler sampling has an $O((M_2+d)/N)$ discretization term. We prove expected stopped-output KL consistency for a learner trained on iid endpoint pairs with fresh true-source initialization. In a spatial image control, iterative sampling has worse fair energy scores than direct prediction with resampled residuals. Uniform terminal rates for general second-moment couplings remain open.

cs.LG · math.PR

版本更新 · v2arXiv:2605.16632

Learning How to Cube

Ferhat Erata, Sam Kouteili, Thanos Typaldos, Timos Antonopoulos, Robert B. Jones, Byron Cook, Ruzica Piskac

原文摘要

Despite the effectiveness of Cube-and-Conquer (C&C) for solving challenging Boolean Satisfiability (SAT) problems, no prior work has shown that transformer-based models can learn effective cubing heuristics. We introduce a neuro-symbolic post-training framework for this task. We design an MCTS-based data curation pipeline that uses symbolic heuristics to explore splitting decisions over SAT competition formulas, producing preference data grounded in solver statistics and augmented with reasoning traces from a teacher model. Our two-stage post-training, supervised fine-tuning (SFT) followed by direct preference optimization (DPO), enables a 4B-parameter model to achieve a pass@5 score of 53 on 100 SAT competition benchmarks, surpassing frontier LLMs such as Claude-Sonnet-4 (50) and matching, with five attempts per benchmark, the best symbolic heuristic (53), which nonetheless remains preferable for a single attempt. Ablations show that SFT alone improves pass@5 from 46 to 51, with DPO adding 2 additional benchmarks; an entropy/agreement ablation on realized first-cube decisions further shows that SFT, not DPO, accounts for the root-level decision diversity that produces complementary per-run coverage over deterministic symbolic methods. This demonstrates that transformers can be trained to make effective cubing decisions in a domain traditionally dominated by symbolic methods.

cs.LG · cs.AI · cs.LO

新论文 · v1arXiv:2611.10563

Confronting Uncertainty in Mechanism-AI Coupled Dynamical Systems via Optimal Transport and Information Geometry: Part I. Distribution Learning

Pengfei Song, Yanni Xiao, Shuangshuang Yin

原文摘要

Mechanism-AI coupled dynamical systems are increasingly used to study complex biological systems. However, uncertainty associated with noisy, sparse, and partially observed data limits their reliability. This paper presents a systematic mathematical formulation for treating these uncertainties from the perspective of optimal transport and information geometry. We formulate the uncertainty quantification problem as the minimization of an energy functional on a probability density space equipped with a Riemannian metric, with the loss evaluated through a differential equation, and give a unified description of the gradient flows of the energy functional under specific metrics, such as the Wasserstein and Fisher-Rao metrics. Furthermore, we present corresponding numerical methods for solving these gradient flows using abstract adjoint sensitivity analysis. The formulation connects a range of Bayesian inference methods for dynamical systems; numerical experiments compare posterior approximation and predictive uncertainty under a common computational budget. Moreover, it also provides a geometric perspective on dynamical modeling and the study of heterogeneity evolution.

cs.LG · math.DS · math.MG · math.PR · stat.ML

版本更新 · v2arXiv:2603.05432

Ensembling Language Models with Sequential Monte Carlo

Robin Shing Moon Chan, Tianyu Liu, Samuel Kiegeland, Clemente Pasti, Jacob Hoover Vigly, Timothy J. O'Donnell, Ryan Cotterell, Tim Vieira

原文摘要

Combining the predictions of multiple models is one of the most effective strategies in machine learning. Thus, it is only natural to investigate the ensembling of language models (LMs). However, because LMs define distributions over strings, a proper ensemble requires aggregating predictions at the string level, which requires a computation that is generally intractable. In this work, we cast LM ensembling as an inference problem and propose the deployment of sequential Monte Carlo (SMC), an appropriate approximate inference scheme. Concretely, we introduce a unified framework for composing multiple LMs into ensemble distributions parameterized by a broad family of aggregation functions. To sample from these distributions, we introduce an SMC algorithm that operates in a shared byte space, enabling ensembles of models with mismatching vocabularies and consistent sampling in the limit. We evaluate a range of ensembles across prompt and model combinations for various text generation tasks, finding that consensus-seeking strategies such as the product consistently outperform probability averaging, and that better posterior approximations can yield better ensemble performance.

cs.CL · cs.AI · cs.LG

新论文 · v1arXiv:2611.10562

ZARA: Zero-shot Animatable and Relightable 3D Avatar reconstruction from a single image

Yixiao Chen, Dongdong Weng, Chengfeng Zhao, Tao Gong, Zhihe Zhao, Zhe Zhu, Yue Liu, Yuan Liu

原文摘要

Recent large human reconstruction models create remarkable animatable 3D avatars from a single image, but their appearance remains entangled with the illumination and cannot be relighted. In contrast, existing 3D relightable-avatar reconstruction methods typically require person-specific optimization. We present ZARA, a zero-shot feed-forward framework that reconstructs an animatable 3D Gaussian avatar together with its intrinsic attributes from a single image. ZARA couples a pretrained large-scale human reconstruction model with a Material Transformer to inherit geometry priors while learning material-aware Gaussian representations. To preserve localized details, we introduce Gaussian-aligned material feature fusion strategy, which injects multi-scale material features onto individual Gaussians and combines them with geometry tokens. As most human-avatar datasets lack ground-truth material maps, we use pseudo-material labels as conditioning inputs and supervision targets during training. We further introduce MatFace regularization to preserve facial structure and color in albedo prediction under unreliable facial pseudo-material supervision. Extensive experiments demonstrate that ZARA reconstructs animatable and relightable humans within tens of seconds without person-specific optimization or post-processing, outperforming existing baselines in both relighting quality and materials generalization ability. As the ability of recovering the physically-based-rendering attributes of the human, ZARA also enables direct material editing of the avatar's appearance.

cs.CV

新论文 · v1arXiv:2611.10559

CompositionEvidence: Controlling Geometric Evidence for Cinematic Composition Reasoning with Frozen Vision-Language Models

Yichen He, Xin Huang, Yuxi Liu

原文摘要

Cinematic composition questions depend on in-frame geometry that vision-language models (VLMs) use inconsistently. External perception tools can expose this geometry, but naive prompt injection can overwrite useful visual predictions. On ShotBench composition, pre-question geometry reduces Qwen2.5-VL-7B from 49.5% to 46.3%; corrupted measurements lower it to 33.6%. CompositionEvidence derives nine reproducible features from frozen detection, depth, and line experts and supplies their shared 24-dimensional representation through two interfaces. A training-free channel appends gated neutral evidence after the question, reaching 56.2% (+6.7, exact McNemar p=0.0018) and 48.4% under corrupted evidence. A minimal-training channel maps the same representation to four soft tokens with a 7.37M-parameter projector while leaving the VLM frozen; it reaches 61.0% (+11.5). Across nine VLMs, including five commercial models queried through official provider APIs, zero-shot accuracy ranges from 43.8% to 63.0%, and the text channel changes it by +6.7 to -6.9 points; the highest baseline is among the regressions. The effect of explicit geometry depends on measurement reliability and on how the receiving model integrates it.

cs.CV

新论文 · v1arXiv:2611.10558

A Cooperative Game Theoretic Model for Sustainable, Smallholder Carbon Farming

Geetha Charan, Thandava Sunkara, Rohit P Suresh, V. Priyanka, Manojkumar Patil, Kodur Sai Vinay Sathvik, Y. Narahari

原文摘要

Carbon farming offers a promising path to improve farmer livelihoods, mitigate climate change, and make farming sustainable. However, smallholder farmers, who dominate agriculture in developing economies, face structural barriers to participating in carbon farming due to high certification costs, limited landholdings, and limited budgets available to them. In this paper, we develop a cooperative game-theoretic framework to study how coalition formation can enable viable and profitable participation of smallholder farmers in carbon farming. Our approach explores three components: (i) Solo Portfolio Optimization (SPO), which determines an optimal portfolio of carbon farming practices that individual farmers can adopt under budget constraints; (ii) Joint Portfolio Optimization (JPO), which computes the maximum total economic surplus achievable through the formation of farmer coalitions; and (iii) surplus allocation among participating farmers in a principled way using cooperative game-theoretic solution concepts, such as Shapley value, core, least core, and nucleolus. We show that the underlying cooperative game is superadditive under an affordability condition and non-convex in general. As part of this study, we release CarbonFARM-Bench, a carbon farming dataset constructed by experts, and conduct controlled computational experiments on this dataset. We observe that solo participation in carbon farming is largely infeasible for smallholder farmers under baseline parameters, whereas coalition formation creates substantial value driven by economies of scale. In addition, we demonstrate that stability-aware allocation mechanisms are required for sustaining cooperation. Together, our results highlight that enabling smallholder carbon farming is fundamentally a challenge of institutional design, and we offer several policy recommendations to make it attractive to smallholder farmers.

cs.GT

版本更新 · v6arXiv:2604.08242

Scheduling Coflows in Multi-Core OCS Networks with Performance Guarantee

Xin Wang, Hong Shen, Hui Tian, Dong Wang

原文摘要

The coflow abstraction captures application-level communication patterns and enables coordinated scheduling of parallel flows to reduce job completion times in distributed systems. Modern data center networks (DCNs) are employing multiple independent optical circuit switching (OCS) cores operating concurrently to meet the massive bandwidth demands of application jobs. However, existing coflow scheduling research primarily focuses on the single-core setting, while studies of multi-core fabrics have largely considered electrical packet switching (EPS) networks. To address this gap, this paper studies the coflow scheduling problem in multi-core OCS networks under the not-all-stop reconfiguration model, in which the reconfiguration of one circuit does not interrupt other circuits. The challenges stem from two aspects: (i) cross-core coupling induced by traffic assignment across heterogeneous cores; and (ii) per-core OCS scheduling constraints, namely port exclusivity and reconfiguration delay. We propose an approximation algorithm that jointly integrates cross-core flow assignment and per-core circuit scheduling to minimize the total weighted coflow completion time (CCT) and establish a provable worst-case performance guarantee. Furthermore, our algorithm framework can be applied to the multi-core EPS scenario with a corresponding approximation guarantee for packet-switched fabrics. Trace-driven simulations using real Facebook workloads demonstrate that our algorithm can reduce the total weighted CCT and tail CCT.

cs.DC

版本更新 · v2arXiv:2605.07654

Reliable Chain-of-Thought via Prefix Consistency

Naoto Iwase, Yuki Ichihara, Mohammad Atif Quamar, Junpei Komiyama

原文摘要

Large language models often improve accuracy on reasoning tasks by sampling multiple chain-of-thought (CoT) traces and aggregating them with majority voting, a test-time technique called self-consistency. When we truncate a CoT partway through and regenerate the remainder, we observe that traces with correct answers reproduce their original answer more often than traces with wrong answers. We use this difference as a reliability signal, prefix consistency, that weights each candidate answer by how often it reappears under regeneration. It requires no access to token log-probabilities or self-rating prompts. Across five reasoning models and four math and science benchmarks, prefix consistency is the best correctness predictor in most settings, and reweighting votes by this signal reaches the plateau accuracy of majority voting with up to $21\times$ fewer tokens (median $4.6\times$). Our code is available at https://github.com/naoto-iwase/prefix-consistency.

stat.ML · cs.CL · cs.LG

新论文 · v1arXiv:2611.10553

Meta-Reinforcement Learning with Zero-Shot Reinforcement Learning

Jake Grigsby, Siddhant Agarwal, Yu Lei, Leonidas Varveropoulos, Yuke Zhu

原文摘要

Meta-reinforcement learning (meta-RL) trains agents to adapt to novel tasks from test-time experience, but requires diverse training environments and reward functions. While environments are becoming cheaper to generate, it remains difficult to anticipate every objective an agent may be asked to pursue at test time. Behavior Foundation Models (BFMs) learn policies from reward-free data and support zero-shot RL (ZSRL): adaptation to new objectives at test time using a large reward-labeled dataset. Recent work has shown that BFM task inference can instead be performed online without prior task-specific data. We note that this capability positions BFMs and meta-RL as alternative approaches for online adaptation to new reward functions in a fixed environment. We then ask whether we can extend BFMs to compete with meta-RL more broadly, including in novel environments, and identify four challenges: environment identification, online data collection, test-time exploration, and learning from mixed reward supervision. We study each individually, then propose MetaBFM, a hybrid method that addresses all four. During training, it combines supervised reward-following with unsupervised learning; at test time, it can interpolate between exploration, exploitation, and ZSRL-style reward inference. We demonstrate that MetaBFM can recover the in-distribution performance of supervised meta-RL while generalizing to reward functions outside the training set. Our work suggests that BFMs and meta-RL are complementary research directions whose combined strengths allow adaptive agents to learn more diverse behaviors from a fixed set of supervised objectives.

cs.LG

版本更新 · v2arXiv:2604.02986

Mitigating Reward Hacking in Reinforcement Learning from Human Feedback via Advantage Sign Robustness

Shinnosuke Ono, Johannes Ackermann, Soichiro Nishimori, Takashi Ishida, Masashi Sugiyama

原文摘要

Reward models (RMs) used in reinforcement learning from human feedback (RLHF) are vulnerable to reward hacking: as the policy maximizes a learned proxy reward, true quality plateaus or degrades. We make the assumption that reward hacking is often caused by flipped advantage signs: instead of reducing the likelihood of a bad response, a flipped sign causes the update to increase it. By considering an adversarial perturbation in the RM parameter space, we can derive a certified sign-preservation radius, which is the smallest perturbation that can flip the advantage sign during policy optimization. Based on this formulation, we propose Sign-Certified Policy Optimization (SignCert-PO), down-weighting non-robust completions in the policy gradient update. Unlike prior approaches that require multiple RMs or access to the RM training data, SignCert-PO is lightweight and operates purely at the policy optimization stage using only the RM parameters and on-policy completions. On TL;DR summarization and AlpacaFarm benchmarks, SignCert-PO consistently achieves a better win rate than baselines and reduces reward hacking.

cs.LG · cs.AI · cs.CL

版本更新 · v3arXiv:2605.11473

TOPPO: Rethinking PPO for Multi-Task Reinforcement Learning with Critic Balancing

Yuanpeng Li, Gefei Lin, Annie Qu, Rui Miao

原文摘要

Soft Actor-Critic (SAC) and its variants dominate Multi-Task Reinforcement Learning (MTRL) due to their off-policy sample efficiency, while on-policy methods such as Proximal Policy Optimization (PPO) remain underexplored. We diagnose that PPO in MTRL suffers from a previously overlooked issue: critic-side gradient ill-conditioning, which may cause tail tasks to stall while easy tasks dominate the value function's updates. To address this, we propose TOPPO (Tail-Optimized PPO), a reformulation of PPO via Critic Balancing -- a set of modules that improve gradient conditioning and balance learning dynamics across tasks. Unlike prior approaches that rely on modular architectures or large models, TOPPO targets the optimization bottleneck within PPO itself. Empirically, on the Meta-World+ MT50 benchmark, TOPPO achieves stronger mean and tail-task performance than prior SAC-family and ARS-family methods while using substantially fewer parameters and reaching their final performance in fewer environment steps. Notably, TOPPO matches or surpasses strong SAC baselines early in training and maintains superior performance at full budget. Ablations confirm the effectiveness of each module in TOPPO and provide insights into their interactions. Our results demonstrate that, with proper optimization, on-policy methods can rival or exceed off-policy approaches in MTRL, challenging the prevailing reliance on SAC and highlighting critic-side gradient conditioning as the central bottleneck.

cs.AI · cs.LG · cs.RO · stat.ML

版本更新 · v4arXiv:2602.00158

RAPTOR: Ridge-Adaptive Logistic Probes

Ziqi Gao, Yaotian Zhu, Qingcheng Zeng, Xu Zhao, Ziqing Wang, Feng Ruan, Kaize Ding

原文摘要

Probing studies what information is encoded in a frozen LLM's layer representations by training a lightweight predictor on top of them. Beyond analysis, probes are often used operationally in probe-then-steer pipelines: a learned concept vector is extracted from a probe and injected via additive activation steering by adding it to a layer representation during the forward pass. The effectiveness of this pipeline hinges on estimating concept vectors that are accurate, directionally stable under ablation, and inexpensive to obtain. Motivated by these desiderata, we propose RAPTOR (Ridge-Adaptive Logistic Probe), a simple L2-regularized logistic probe whose validation-tuned ridge strength yields concept vectors from normalized weights. Across extensive experiments on instruction-tuned LLMs and human-written concept datasets, RAPTOR matches or exceeds strong baselines in accuracy while achieving competitive directional stability and substantially lower training cost; these quantitative results are supported by qualitative downstream steering demonstrations. Finally, using the Convex Gaussian Min-max Theorem (CGMT), we provide a mechanistic characterization of ridge logistic regression in an idealized Gaussian teacher-student model in the high-dimensional few-shot regime, explaining how penalty strength mediates probe accuracy and concept-vector stability and yielding structural predictions that qualitatively align with trends observed on real LLM embeddings.

cs.LG · cs.AI

新论文 · v1arXiv:2611.10544

Compact Quantum Channel Attention for Static ASL Recognition: A Controlled Study with Parameter-Matched Baselines

Ronak Bhalgami, Deep Kothadiya, Nikita Bhatt

原文摘要

Hybrid quantum-classical models often report good accuracy on image tasks, but it is rarely clear whether the quantum part is responsible. This paper proposes QCA-DenseNet, a static American Sign Language (ASL) recognition pipeline in which an eight-qubit variational circuit acts as a channel-attention gate on DenseNet121 features. The quantum channel attention (QCA) gate has 17,464 parameters, 7.51 times fewer than a squeeze-and-excitation (SE) block. The pipeline is tested on 1,815 MU HandImages images by holding out one of five signers at a time, and a frozen-backbone ablation uses small parts of the Kaggle ASL Alphabet data. On unseen signers, QCA-DenseNet reaches 94.50% mean accuracy, above SE (93.72%) and within 0.28 points of the best model. A matched classical MLP and a model without attention perform about the same, and no difference is significant. QCA gives a much smaller attention gate without a detectable loss in accuracy, but no quantum advantage.

quant-ph · cs.AI · cs.CV · cs.LG

新论文 · v1arXiv:2611.10543

Intra-Option Fitted Q-Evaluation: Evaluating Hierarchical Policies from Non-Hierarchical Data

Yunfu Deng, Josiah P. Hanna

原文摘要

Off-policy evaluation (OPE) estimates the expected return of a target policy from previously collected data without additional environment interaction. While OPE methods for flat Markovian policies are well studied, little work has addressed evaluating hierarchical policies in which a high-level policy selects temporally extended options that generate primitive actions until a termination condition is met. The primary existing approach applies per-decision importance sampling at the option level, but requires option-annotated trajectories and exhibits variance that still grows with the horizon. For non-hierarchical policies, fitted Q-evaluation (FQE) typically achieves lower error than importance sampling by leveraging the classic Bellman equation for policy evaluation; however, a naive extension of FQE to hierarchical policies results in a biased policy value estimate. In this paper, we introduce Intra-Option Fitted Q-Evaluation (IO-FQE), which estimates a value function in the augmented state-option space; this approach enables OPE of hierarchical policies even when we lack annotations of what option was run in the data. We develop two continuous-action instantiations of IO-FQE and show on long-horizon hierarchical continuous control tasks (AntMaze navigation and OGBench Puzzle manipulation) that IO-FQE eliminates the bias incurred by a naive application of FQE to hierarchical policies and substantially lowers mean squared-error compared to option-level importance sampling.

cs.LG

版本更新 · v3arXiv:2608.17253

Co-RL: Unsupervised Reasoning Emerges from Diverse Cohort in Multi-agent RL

Yunhao Yang, Yuexin Bian, Yunjie Tian, Di Fu, Tianjin Huang, Yuanyuan Shi, Ziang Xiao, Nuno Vasconcelos 等 9 位作者

原文摘要

Reinforcement Learning (RL) has emerged as a powerful approach for improving reasoning in language and vision-language models, yet its strongest successes still depend heavily on ground-truth supervision (e.g., verifiable reward). Such annotations are costly to obtain and become increasingly scarce as reasoning capabilities advance beyond what humans can reliably evaluate. Self-rewarding RL reduces this dependence by enabling models to derive reward signals from their own completions. However, training solely on self-generated feedback can reinforce existing biases, reduce response diversity, and ultimately lead to homogenized responses and training collapse. In this work, we show that unsupervised reasoning can emerge through cooperative multi-agent training. We introduce Co-RL, a framework in which multiple decoupled models, sharing no parameters, are simultaneously optimized through RL using rewards derived from the other agent. We further show that increasing cohort diversity, through heterogeneous model families, sizes, and rephrased training samples, reduces the correlated errors that drive self-reinforcing feedback loops. This diversity consistently improves reasoning performance and mitigates training collapse. Without any ground-truth labels, Co-RL improves the base models by 3.0-7.9% on average across seven benchmarks and by 1.6-4.4% across four multimodal benchmarks. It also outperforms the prior state-of-the-art multi-agent RL method CoMAS by 4.0% and the self-rewarding vision-language RL method MM-UPT by 2.0%. Our code is available at https://github.com/Diverse-CoRL/Co-RL and website at https://williamium3000.github.io/Co-RL.

cs.LG · cs.AI · cs.CV

新论文 · v1arXiv:2611.10542

When Experience Becomes a Backdoor: Poisoning Self-Evolving LLM Agents via Failure-Aware Task Optimization

Minhua Lin, Zongyu Wu, Hanqing Lu, Xianfeng Tang, Xiang Zhang, Qi He, Suhang Wang

原文摘要

Large language model (LLM) agents increasingly improve themselves through self-evolution, distilling execution experience into persistent, reusable skills. However, this persistence creates a new attack surface: malicious rules implanted into skills can compromise subsequent agent behavior. Existing skill backdoor attacks typically assume direct manipulation of the victim's skills, which is impractical when skills are constructed internally by a trusted evolver. In this paper, we study a novel problem of task-level backdoor attacks, where the attacker can only inject poisoned evolution tasks, inducing the agent to implant backdoors into its own skills. Since the attacker controls neither skill induction nor downstream execution, a natural approach is to iteratively optimize poisoned tasks based on attack success. However, our preliminary analysis reveals two key challenges: (i) failures at different stages of skill evolution and downstream execution can produce indistinguishable outcomes, providing little guidance for targeted poisoned-task updates; and (ii) unsuccessful updates may undermine earlier progress, while simply discarding them may lead to repeated ineffective updates. To address these challenges, we propose BadEvolve, a failure-aware task-poisoning framework against self-evolving LLM agents. BadEvolve diagnoses attack failures across four stages, i.e., Induction, Activation, Following, and Effect, and directs updates toward the failing stage. It further employs rollback to preserve earlier progress and failure memory to avoid repeating ineffective updates. Extensive experiments across diverse self-evolution frameworks, benchmarks, and backbone LLMs demonstrate the effectiveness of BadEvolve. Our code is available at https://github.com/ventr1c/BadEvolve.

cs.CR · cs.AI

新论文 · v1arXiv:2611.10541

AFVE-Bench: Measuring Abandoned-Frame Verbalization Errors in Multi-Turn LLM Revision

Jiaming Chu

原文摘要

Multi-turn revision often asks a model to replace an earlier organizing frame while preserving still-valid facts and artifact requirements. Existing instruction-following evaluations mainly assess the latest target and may therefore score an artifact as successful even when it adopts the new frame but exposes the superseded one. We call this failure an abandoned-frame verbalization error (AFVE). AFVE-Bench evaluates silent frame replacement in English and Chinese using 192 matched four-turn dialogues across eight writing domains. Each seed has zero, one, or two pre-target user requests to generate under the source frame. AFVE eligibility depends on the user-request history and applies to the one- and two-request conditions; the zero-request condition serves as a frame-bearing baseline. Eleven model configurations yielded 4,224 expected post-target response units. Two annotators independently scored 4,204 scorable responses for target adoption, source-frame verbalization, and direct usability; model and condition metadata were hidden, and disagreements were adjudicated. AFVE occurs in 25.54% (715/2,799) of history-conditioned responses. Of 2,388 target-passing history-conditioned responses, 472 (19.77%) still expose the abandoned source frame, most often through contrastive framing (423/472). For these standalone revision tasks, target adoption does not ensure source-frame silence.

cs.CL · cs.AI

版本更新 · v3arXiv:2610.41561

Digital sovereignty in professional translation workflows: a case study of migrating from Windows to Linux

Michael Farrell

原文摘要

This study examines digital sovereignty in professional translation through a screening of computer-assisted translation tools and translation management systems, and a case study of migrating a translator's workstation from Windows to Linux. The framework combines three principles - Control, Continuity and Exit - with three practical requirements: native Linux operation, independence from mandatory external services, and independent access to essential data and resources. Drawing on documentary evidence and the limited number of responses received from providers, the ecosystem screening distinguishes Linux accessibility from operational independence: browser-based platforms may remain dependent on provider-controlled infrastructure. The migration case demonstrates the feasibility of reconstructing one professional workflow around a locally operable Linux core, using LoopCAT, LibreOffice and locally run TranslateGemma, alongside tools for optical character recognition, communication, credential management and backup. Selected cloud services remained available where needed. The findings suggest that digital sovereignty depends on how workflow dependencies are organized, rather than on individual applications or operating systems. It does not require technological isolation, but meaningful control over essential components, continuity of work and practical exit options. The framework is tailored to the case examined here and may require adaptation to other professional workflows.

cs.CL

新论文 · v1arXiv:2611.10538

Close and Sort: Exact Maximum-Likelihood Aggregation of Cyclic Rank-Two Preferences

Kehan Liu, Zhaoyun Chen, Xianquan Yan

原文摘要

Pairwise probabilities arise in rank aggregation, recommendation, and human or LLM evaluation, yet converting them into a maximum-likelihood list is a weighted Kemeny problem and is NP-hard in general. Known exact algorithms for rank-two tournaments use only comparison signs and do not optimize this likelihood. We show that the weighted problem is exactly solvable when the skew-symmetric log-odds matrix $W_{ij}=\log(p_{ij}/p_{ji})$ has rank two, including when the induced preferences contain cycles. Writing $W_{ij}=\det(h_i,h_j)$ and adding the closing vector $h_0=-\sum_i h_i$ turns the objective into twice the signed area of a closed polygon. This geometry yields CloseSort, which polar-sorts the $n+1$ edge vectors, cuts after $h_0$, and returns a global maximum-likelihood order in $O(n\log n)$ time from the factors. The same geometry identifies the runner-up and gives a stability certificate beyond exact rank two. When the smallest determinant $δ$ of two consecutive edges in the closed angular cycle is positive, it is exactly the best-to-runner-up log-likelihood gap. For $W=W_0+E$, the CloseSort order of $W_0$ has regret at most $\sum_{i<j}|E_{ij}|$ on $W$ and remains optimal whenever this sum is below $δ$, a worst-case tight threshold. In 5,120 determinant-logit simulations, increasing the observations per pair from 4 to 64 raises the fraction on which rank-two projection outperforms the empirical plug-in optimum from 68.6% to 85.7%. On 3,600 Arena-Hard LLM-judge profiles drawn from 63 systems and ten judges, the leading rank-two component captures 89.2% of the log-odds energy. On profiles containing a directed majority triangle, CloseSort reduces normalized regret by 44% relative to Borda and improves the mean normalized objective over each of eight baselines. With factors supplied, it is 8,407 times faster than exact dynamic programming on 18-item rankings.

cs.DS · cs.IR · cs.LG · stat.ML

新论文 · v1arXiv:2611.10536

In Search of Lost Time: Temporal Competence in Large Language Models

Ryan Liu, David Lee, Icey Siyi Ai, Marwa Abdulhai, Rachit Dubey, Thomas L. Griffiths

原文摘要

Today's large language models (LLMs) increasingly interact with time: AI agents schedule tasks, coordinate with people and other AI systems, and even decide how long to think. Yet LLMs only ever encounter time secondhand---in descriptions rather than experience. Does this hinder their reasoning and decisions that involve time? Our paper traces this question from a model's knowledge to its actions through four successive evaluations. We find that models know the rules of time, which can be read, but struggle to predict durations, which must be lived; while they are highly accurate (92.0-97.5\%) on a collection of questions built from the theorems of various time-related literatures, they underestimate their own completion times by up to 99.5\% and fail to identify which tasks will take them longer to run. And while they are better at estimating durations of human tasks, their duration judgments change based on how an event is worded, magnifying similar human biases by up to 1.3$\times$. Moving from estimation to action, we find that some LLMs disregard time costs completely when answering user queries, ignoring a 1,200-fold increase in wait time entirely. Together, our experiments reveal new challenges posed to LLMs as they navigate a dimension they cannot directly perceive, and highlight how their blind spots can even be simple cognitive abilities that humans take for granted.

cs.AI · cs.CL · cs.LG

版本更新 · v3arXiv:2609.30906

ToolSearcher: Optimizing Tool Selection at Scale via Reinforcement Learning

Zhenlong Dai, Xujie Song, Zitong Wang, Tong Niu, Jian liu, Weiqiang Wang, Xiu Tang, Sai Wu 等 10 位作者

原文摘要

Large language models (LLMs) excel at natural language processing but struggle to interact with external environments. Tool learning provides a promising way to extend LLMs into actionable agents, where tool selection is a critical prerequisite for successful tool use. Existing work often assumes a small or predefined set of tools, leaving large-scale tool selection underexplored. Real-world repositories contain a vast and diverse array of tools, making it difficult for LLMs to effectively search, distinguish, and compose tools under context-length constraints. We identify large-scale tool selection as a new challenge for agentic reinforcement learning, highlighting that existing RL methods for knowledge-based question answering are inadequate for selecting tools while considering compatibility. To address this challenge, we propose ToolSearcher, a novel RL framework for effective multi-turn search and fine-grained optimization in large-scale tool selection. Specifically, we introduce category-constrained tool discrimination to improve the model's ability to distinguish functionally similar tools, event-level search modeling to explicitly optimize the discovery of target tools during multi-turn search, and trajectory-aligned credit allocation to provide fine-grained reward signals for different stages of the search-selection process. Extensive experiments on large-scale tool selection benchmarks demonstrate that ToolSearcher consistently outperforms a set of strong baselines in challenging settings involving iterative search and complex tool composition.

cs.CL

版本更新 · v2arXiv:2608.21810

MSM-Mem: A Universal Medical Structured Multimodal Memory Framework for Medical AI Agents

Md Asaduzzaman Jabin, Khoa Le, Lin Zhao, Tianming Liu

原文摘要

Clinical decision-making is inherently experience-driven: physicians progressively refine their reasoning by synthesizing patient history, multimodal observations, and prior diagnostic experiences across interactions. In contrast, current multimodal large language model (MLLM)-based medical AI agents largely operate as stateless inference systems, generating decisions independently for each interaction without retaining or internalizing experiential knowledge. This discrepancy limits their ability to progressively improve reasoning reliability through usage and adapt to longitudinal patient contexts in real-world clinical workflows. In this study, we propose Medical Structured Multimodal Memory (MSM-Mem), an agentic memory framework that enables medical AI agents to evolve through accumulated clinical experiences. MSM-Mem organizes heterogeneous clinical experiences into semantic, episodic, and visual memory and incrementally updates them during inference, allowing the agent to retrieve prior experiences to inform current reasoning and progressively refine decision-making over time. Evaluations on MoE-LLaVA backbones demonstrate consistent performance improve- ments with further gains observed through continued usage. In general, MSM-Mem offers a viable pathway toward medical AI agents capable of evolving their reasoning competence in a manner analogous to the way clinicians learn from practice over time.

cs.LG · cs.CV

新论文 · v1arXiv:2611.10530

Mismeasuring the Life of a Line of Code: Lessons Learned the Hard Way

Pavel Gurov

原文摘要

Studies of how long lines of code live, including lines written by AI agents, rest on choices that look technical: when a line counts as gone, what to do with lines still alive, whether to pool projects, and how to evaluate a model. We studied 32.5 million line births in 120 TypeScript repositories and got several of these choices wrong at first. For ten of them, we compare the result as we first computed it, or as commonly done, with the result after correction. All ten change conclusions, or would have. Six were our own mistakes. Counting moved and rewritten lines as dead shortens a line's median life from 3.0 years to 1.3. Counting any change as a death hides an outcome that can be predicted: within-project concordance falls from 0.71 to 0.56. Regressing observed lifetimes discards three quarters of the lines. Keeping rewritten lines at risk makes protective effects grow with age. Lines are born and removed together, so treating them as independent misleads twice: nine of fifteen effects look significant only under that assumption, and a split by file makes a barely predictable outcome look good (within-project concordance 0.71 instead of 0.61). After the corrections, removal depends on a line's age and project, but our models could barely rank it within a project. Local revision they could rank (0.71). Obvious cases aside, the top 1% of a project's new lines are revised at 2.3 times the base rate. Each pitfall leaves a symptom; we give a checklist.

cs.SE

新论文 · v1arXiv:2611.10528

PrivMark: Pixel-Space Steering against Privacy Leakage in Vision-Language Models

Ruofan Xing, Arman Akbari, Weikai Lin, Yuhao Zhu, Xuan Zhang

原文摘要

Vision-language models (VLMs) routinely disclose soft-biometric attributes such as age, gender, and race in their text outputs, exposing demographic information from uploaded images to any downstream API user. Existing privacy defenses do not fit this setting: face de-identification leaves distributed soft-biometric cues intact, classifier-targeted adversarial perturbations do not transfer to open-ended generation, and stronger VLM-specific methods require retraining or runtime activation access unavailable to downstream APIs. We propose PrivMark, a framework that suppresses biometric leakage at the image level. By analyzing VLM activations, we identify two weakly aligned steering vector directions in hidden-state space, each tied to a distinct leakage behavior --- one corresponding to incidental attribute disclosure under open-ended descriptions, the other to compliance with direct biometric probes instead of refusal --- and encode both directions into a single bounded pixel perturbation, so the protected image alone enforces privacy with no invasive access to model internals at deployment. To support evaluation, we assemble BioleakBench, $1{,}600$ VQA pairs covering biometric privacy attributes under both free-form description and direct-probe protocols. Across three white-box source models, PrivMark achieves up to $85.9\%$ biometric suppression while retaining $75\%$ of clean OK-VQA utility, up to $1.4\times$ the privacy-utility tradeoff of the strongest pixel-only baseline. The same one-shot perturbations transfer consistently to seven unseen VLMs including closed-source APIs.

cs.CV

版本更新 · v3arXiv:2604.08322

Fundus-R1: Training a Fundus-Reading MLLM on Public Data

Yuchuan Deng, Qijie Wei, Kaiheng Qian, Jiazhen Liu, Bangxiang Lan, Qingwei Shen, Jianfeng Dong, Weihong Yu 等 9 位作者

原文摘要

Fundus imaging such as CFP, OCT and SLO is crucial for the early detection of retinal anomalies and diseases. Fundus image understanding, due to its knowledge-intensive nature, poses a challenging vision-language task. An emerging approach to addressing the task is to post-train a generic multimodal large language model (MLLM), either by supervised finetuning (SFT) or by reinforcement learning with verifiable rewards (RLVR), on a considerable amount of in-house samples paired with high-quality clinical reports. However, these valuable samples are not publicly accessible, which not only hinders reproducibility but also practically limits research to few players. In this paper, we make a novel attempt to train a reasoning-enhanced fundus-reading MLLM, termed Fundus-R1, using exclusively public datasets, wherein over 94% of the data are annotated with image-level labels only. Our technical contributions are two-fold. First, we propose a RAG-based method for composing image-specific, knowledge-aware reasoning traces. Such auto-generated traces link visual findings identified by a generic MLLM to the image labels in terms of ophthalmic knowledge. Second, we enhance RLVR with a process reward that encourages self-consistency of the generated reasoning trace in each rollout. Extensive experiments on three fundus-reading benchmarks, i.e., FunBench, Omni-Fundus and GMAI-Fundus, show that Fundus-R1 clearly outperforms multiple baselines, including its generic counterpart (Qwen2.5-VL) and a stronger edition post-trained without using the generated traces. This work paves the way for training powerful fundus-reading MLLMs with publicly available data.

cs.CV

版本更新 · v3arXiv:2604.01342

Massively Parallel Exact Inference for Hawkes Processes

Ahmer Raza, Hudson Smith

原文摘要

Multivariate Hawkes processes are a widely used class of self-exciting point processes, but maximum likelihood estimation naively scales as $O(N^2)$ in the number of events. The canonical linear exponential Hawkes process admits a faster $O(N)$ recurrence, but prior work evaluates this recurrence sequentially, without exploiting parallelization on modern GPUs. We show that the Hawkes process intensity can be expressed as a product of sparse transition matrices admitting a linear-time associative multiply, enabling computation via a parallel prefix scan. This yields a massively parallelizable algorithm for estimation of linear exponential Hawkes processes. Our method reduces the computational complexity to approximately $O(N/P)$ with $P$ parallel processors, and naturally yields a batching scheme to maintain constant memory usage, avoiding GPU memory constraints. Importantly, it computes the exact likelihood without any additional assumptions or approximations, preserving the simplicity and interpretability of the model. We demonstrate orders-of-magnitude speedups on simulated and real datasets, scaling to thousands of nodes and tens of millions of events, substantially beyond scales reported in prior work. We provide an open-source PyTorch library implementing our optimizations.

cs.LG · stat.ML