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

+1680新增论文
+1333其中 AI 相关
+187已有论文修订
+59新增 AI 导读

arXiv 最近完成扫描:2026-11-18 04:28 · 全站最近入库:2026-11-17 23:35各信源进度 →

统计口径与数据新鲜度

统计 2026-11-17 07:43 — 2026-11-18 07:43(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:2026-11-18 04:28最近发现新增版本:2026-11-17 23:35库内论文最新更新时间:2026-11-17 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。

25,786 已收录论文21,491 AI 相关7,725 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 17 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-18 04:27(北京时间)
版本更新 · v2arXiv:2610.11381

EvoKnow: Continual Knowledge Evolution for AI-Generated Image Detection

Zhiheng Peng, Wenwei Jin, Yangshi Ge, Siyu Xia, Jiawei Li, Xu Tang

原文摘要

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.

cs.CV · cs.AI

版本更新 · v3arXiv:2510.08697

BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution

Terry Yue Zhuo, Xiaolong Jin, Hange Liu, Juyong Jiang, Tianyang Liu, Chen Gong, Bhupesh Bishnoi, Vaisakhi Mishra 等 40 位作者

原文摘要

Crowdsourced model evaluation platforms, such as Chatbot Arena, enable real-time evaluation from human perspectives to assess the quality of model responses. In the coding domain, manually examining the quality of LLM-generated content is extremely challenging, as it requires understanding long chunks of raw code and deliberately simulating code execution. To this end, we introduce BigCodeArena, an open human evaluation platform for code generation backed by a comprehensive and on-the-fly execution environment. Built on top of Chatbot Arena, BigCodeArena enables the execution of LLM-generated code and allows humans to interact with the execution process and outcomes. We collected over 14,000 raw code-centric conversation sessions across 10 widely used LLMs, spanning 10 languages and 8 types of execution environments. Among these conversations, we identified more than 4,700 multi-turn samples with pairwise human preferences. Further analysis uncovers underexplored preferences of LLMs in fine-grained domains characterized by tasks, languages, and frameworks. To systematically examine code understanding and generation capabilities of frontier LLMs, we curated two benchmarks based on the collected data, namely BigCodeReward and AutoCodeArena. For BigCodeReward, we post-processed the 4,700 conversations and evaluated the consistency between reward models and human preferences. The evaluation shows that most LLMs have superior performance in judging coding preferences when the execution results are available. Inspired by these findings, we propose AutoCodeArena, an automatic Elo rating benchmark designed to assess the coding quality of LLMs without human involvement. We find that proprietary LLMs like GPT-5, Claude-Sonnet-4, and Claude-Opus-4 still lead in code generation performance among recent emerging models.

cs.SE · cs.AI · cs.CL

版本更新 · v5arXiv:2406.15877

BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions

Terry Yue Zhuo, Minh Chien Vu, Jenny Chim, Han Hu, Wenhao Yu, Ratnadira Widyasari, Imam Nur Bani Yusuf, Haolan Zhan 等 33 位作者

原文摘要

Task automation has been greatly empowered by the recent advances in Large Language Models (LLMs) via Python code, where the tasks ranging from software engineering development to general-purpose reasoning. While current benchmarks have shown that LLMs can solve tasks using programs like human developers, the majority of their evaluations are limited to short and self-contained algorithmic tasks or standalone function calls. Solving challenging and practical tasks requires the capability of utilizing diverse function calls as tools to efficiently implement functionalities like data analysis and web development. In addition, using multiple tools to solve a task needs compositional reasoning by accurately understanding complex instructions. Fulfilling both of these characteristics can pose a great challenge for LLMs.To assess how well LLMs can solve challenging and practical tasks via programs, we introduce BigCodeBench, a benchmark that challenges LLMs to invoke multiple function calls as tools from 139 libraries and 7 domains for 1,140 fine-grained tasks. To evaluate LLMs rigorously, each task encompasses 5.6 test cases with an average branch coverage of 99%. In addition, we propose a natural-language-oriented variant of BigCodeBench, BigCodeBench-Instruct, that automatically transforms the original docstrings into short instructions only with essential information. Our extensive evaluation of 60 LLMs shows that LLMs are not yet capable of following complex instructions to use function calls precisely, with scores up to 60%, significantly lower than the human performance of 97%. The results underscore the need for further advancements in this area.

cs.SE · cs.AI · cs.CL

新论文 · v1arXiv:2611.14953

RSLiveBench-UAV: A Continually Evolving Vision-Language Benchmark for Aerial Spatial Intelligence

Yue Zhou, Jiawei Liu, Jue Chen, Ziyang Gong, Haojia Wei, Jingxiang Li, Xue Jiang, Zhihang Zhong 等 12 位作者

原文摘要

Aerial spatial intelligence (ASI) requires models to understand objects and spatial relationships across changing viewpoints and scales. Evaluating these abilities as models evolve calls for fresh physical observations, yet producing new aerial spatial questions requires repeatedly establishing entity identities, geometric references, and cross-view correspondences. We introduce \textbf{RSLiveBench-UAV}, a continually evolving vision-language benchmark driven by recurring acquisition of real UAV imagery. Its update protocol admits images captured after the preceding release and delays answer disclosure. An entity-centered production workflow uses geometry-assisted association to link repeated observations of physical vehicles, reuse human-verified attributes, and combine them with view-specific annotations and spatial references for traceable question generation. All tasks use deterministic scoring without model judges. We evaluate 30 general-purpose, remote-sensing, and embodied models on 35,491 question records from ten scenes, covering 17 tasks across 2D perception, 3D perception, cross-view perception, and reasoning. All 18 tested embodied models outperform the three selected remote-sensing comparators in Overall, although the strongest embodied model scores 43.29 versus 59.88 for GPT-6-Astra. Fine-grained vehicle recognition remains challenging, and performance varies across heights and camera pitches. Retrospective scene-group comparisons and rolling-window replay characterize score-pattern consistency under scene renewal. RSLiveBench-UAV connects fresh physical observations, entity-centered answer production, and systematic model evaluation to support continual assessment of ASI. Benchmark will release at https://rslivebench.space

cs.CV

版本更新 · v3arXiv:2603.07388

Sparsity and Out-of-Distribution Generalization

Scott Aaronson, Lin Lin Lee, Jiawei Li

原文摘要

Explaining out-of-distribution generalization has been a central problem in epistemology since Goodman's "grue" puzzle in 1946. Today it's a central problem in machine learning, including AI alignment. Here we propose a principled account of OOD generalization with three main ingredients. First, the world is always presented to experience not as an amorphous mass, but via distinguished features (for example, visual and auditory channels). Second, Occam's Razor favors hypotheses that are "sparse," meaning that they depend on as few features as possible. Third, sparse hypotheses will generalize from a training to a test distribution, provided the two distributions sufficiently overlap on their restrictions to the features that are either actually relevant or hypothesized to be. The two distributions could diverge arbitrarily on other features. We prove a simple theorem that formalizes the above intuitions, generalizing the classic sample complexity bound of Blumer et al. to an OOD context. We then generalize sparse classifiers to subspace juntas, where the ground truth classifier depends solely on a low-dimensional linear subspace of the features.

cs.LG · cs.AI

新论文 · v1arXiv:2611.09129

TouchAnnotator: Multi-Source Tactile Supervision with Privileged-View Distillation

Ao Li, Zhihao Yuan, Chubin Zhang, Kunrui Huang, Sheng Xu, Zengjue Chen, Junjie Wang, Jiawei Li 等 9 位作者

原文摘要

Egocentric video captures human-object interaction at scale but rarely includes tactile labels for hidden contact and pressure. We introduce TouchAnnotator, an ego-only bimanual tactile annotator trained with multi-source tactile supervision and privileged-view distillation. A canonical hand field unifies glove pressure, geometry-derived human contact, and robot fingertip deformation from six datasets and three embodiments, while source-aware masks preserve valid targets. During training, an EMA teacher observes synchronized ego and wrist views and distills hand-local representations and tactile predictions into a student that uses only ego video and estimated pose at inference. Compact past-clip memory supplies temporal context. We evaluate on EgoTouch, zero-shot FPHA transfer, and 860 synchronized glove recordings. The model transfers to bare-hand contact and produces qualitatively coherent tactile responses across bare-hand, gloved-hand, and robot embodiments. On measured recordings, it improves temporal accuracy by 5.38 points and Volumetric IoU by 5.02 points under a shared protocol. These results show that heterogeneous human--robot supervision and privileged training views can turn egocentric video into dense tactile annotations.

cs.CV

版本更新 · v2arXiv:2608.01684

GABench: A Comprehensive Benchmark for Evaluating LLM Agents on Graph Analysis Tasks

Jiarui Tan, Zhongjian Zhang, YaBo Guo, Jiawei Liu, Yujie Xing, Muhan Zhang, Cheng Yang, Chuan Shi

原文摘要

Large language model (LLM) agents are increasingly capable of planning, using tools, and interacting with external environments. They are typically supported by harnesses, which manage state and coordinate multi-step execution. Graph analysis provides a promising setting for evaluating their agentic capabilities, because it requires agents to access data and execute operations in a graph environment. However, existing graph benchmarks for LLMs provide limited coverage of graph tasks and graph types, making it difficult to comprehensively evaluate LLM agents. Moreover, they typically formulate graph analysis as text-based question answering, where graph information is directly provided in the prompt, limiting the evaluation of end-to-end agentic capabilities. To address these limitations, we introduce GABench, a comprehensive benchmark for agentic graph analysis. GABench spans three graph types and covers four graph analysis task categories: graph retrieval, graph theory, graph machine learning, and graph open-ended question answering. GABench also provides 84 executable tools for accessing graph data and performing diverse graph operations. Building on these tools, we develop an agentic graph analysis task generation pipeline and construct 10,400 tasks with verifiable ground truth.Using GABench, we evaluate a range of frontier LLMs and agent harnesses. Our experiments reveal three key findings: (1) Existing LLM agents still struggle with complex graph analysis tasks. (2) Harness choice significantly affects performance, yet existing harnesses remain limited on complex graph tasks. (3) Graph analysis depends more on tool-call quality than quantity. Our findings provide practical insights into the development and evaluation of LLM agents for graph analysis.

cs.AI

新论文 · v1arXiv:2611.04943

Learning Where to Look: Observation Policy Optimization for Thinking with Images

Junfeng Wang, Jiawei Liu, Yongchao Xu, Tao Jiang, Jiangbo Ai, Jin Zhang, Chong Wang, Qixing Zhang

原文摘要

Complex visual question answering often requires vision-language models to think with images, i.e., actively acquire local visual evidence by zooming into informative regions of high-resolution images. Our error analysis shows that many failures in this setting originate from incorrect observation actions, where the model fails to localize key regions or obtain crops that contain sufficient evidence for answering. We further observe that bounding-box tokens exhibit substantially higher generation entropy than ordinary language tokens, indicating high uncertainty when the model decides where to look. However, existing reinforcement learning methods based on final-answer rewards provide only trajectory-level feedback, making it difficult to assign precise credit to the observation actions. We propose Observation Policy Optimization (OPO), an RL algorithm for optimizing observation actions in tool-augmented thinking with images. OPO consists of two core modules. First, Uncertainty-Guided Observation Branching (UOB) treats each image zoom-in tool call as an observation event and selectively branches at high-uncertainty, low-redundancy events during rollout, enabling efficient exploration of alternative cropping decisions and their resulting visual evidence. Second, Evidence-Localized Advantage Attribution (ELAA) compares sibling branches using local evidence-sufficiency rewards and assigns credit only to the corresponding observation-action tokens. By decoupling observation-action optimization from trajectory-level outcome supervision, OPO improves visual evidence acquisition and further enhances visual reasoning performance. Experiments show that OPO consistently improves Qwen3-VL models across scales and achieves competitive performance against larger models and tool-augmented baselines. Code is publicly available.

cs.CV

新论文 · v1arXiv:2611.02784

HLSClaw: Bringing Vibe Coding to High-Level Synthesis through Skill-Based Agentic Harness

Jinming Ge, Shang Liu, Jiawei Liang, Shangkun Li, Afzal Ahmad, Jiang Xu, Linfeng Du, Wei Zhang

原文摘要

LLM agents are rapidly shifting software development toward intent-driven \emph{vibe coding}, yet their effectiveness drops sharply in high-level synthesis (HLS), where code optimization must jointly consider design structure, directive search, and downstream hardware constraints. Existing HLS optimization approaches, including both heuristic-based methods and recent LLM-assisted pipelines, typically operate at fixed abstraction levels or in weakly coupled stages, limiting their ability to leverage the strong interplay between source code restructuring and directive search outcomes. Our key insight is that HLS optimization can be reframed from a fixed, hardwired transformation pipeline into a skill-based agentic control problem: an LLM agent equipped with modular, executable optimization skills and a feedback-driven orchestrator can autonomously navigate the coupled space of code restructuring and directive search. This motivates the design of HLSClaw, the first HLS-specific, skill-based agentic harness for holistic HLS optimization. On real-world HLS benchmarks, HLSClaw achieves a 39.12x geometric-mean latency speedup, outperforming the compiler baseline ScaleHLS by 1.98x, and surpassing the commercial coding agents Claude Code and Codex by 1.86x and 1.70x, respectively, while maintaining strong timing robustness.

cs.LG · cs.SE

新论文 · v1arXiv:2610.37299

Structured Representation Probing for Risk Anticipation in End-to-End Autonomous Driving

Jiawei Liang, Tianrui Lou, Le Yang, Xianghao Jiao, Wei Wang, Xiaochun Cao

原文摘要

End-to-end driving policies form structured internal representations of traffic, ego behavior, and road constraints. These representations offer a monitoring interface for anticipating failures, complementing risk signals from trajectories, controls, and manually designed features. We introduce the Structured Representation Probe (SRP), a lightweight monitor that reads actor, ego, and map representations from a frozen policy. SRP learns a separate linear risk direction for each source and aggregates element scores through cardinality-normalized log-mean-exp pooling, retaining sensitivity to salient evidence while reducing dependence on token count. Event-window supervision links the readout to upcoming hard failures, and auxiliary event type heads jointly train the source directions across failure modes. Online alerting uses a single generic score without modifying the driving policy. Bench2Drive experiments on DriveTransformer, UniAD, and VAD show higher frame-level PR-AUC and ROC-AUC than the evaluated runtime baselines. On DriveTransformer at a horizon of 2 seconds, ROC-AUC reaches 0.833 versus 0.715 for temporal consistency, with 2.67% readout runtime overhead. The trained probes also retain the ability to distinguish impending failures on new routes.

cs.LG

版本更新 · v2arXiv:2602.22724

AgentSentry: Mitigating Indirect Prompt Injection in LLM Agents via Temporal Causal Diagnostics and Context Purification

Tian Zhang, Yiwei Xu, Juan Wang, Keyan Guo, Xiaoyang Xu, Bowen Xiao, Quanlong Guan, Jinlin Fan 等 11 位作者

原文摘要

Tool-augmented large language model (LLM) agents aggregate dialogue history, tool outputs, and retrieved content into an accumulated runtime state to complete multi-step tasks. This execution model exposes agents to indirect prompt injection (IPI) attacks, in which attacker-controlled instructions embedded in external artifacts enter the agent state and later influence tool use. Multi-turn IPI is especially challenging because injected content can persist across steps and trigger unauthorized state-changing actions only after merging with user intent. This creates a source-attribution problem: existing inference-time defenses can often detect suspicious behavior but do not directly distinguish whether a pending action is supported by the user task or influenced by injected content. They therefore resort to conservative blocking, termination, or broad filtering. We propose AgentSentry, an inference-time defense that operationalizes temporal causal diagnostics through boundary-local counterfactual re-executions at tool-return boundaries. It substitutes the mediator under a restored snapshot, records whether the pending proposal survives, and aggregates user-view and probe scores across adjacent boundaries. When a proposal is mediator-sensitive, AgentSentry purifies the implicated mediator content while preserving task-relevant evidence and resumes execution from the sanitized state. We evaluate AgentSentry on AgentDojo across four task suites, three IPI attack families, and three black-box LLM backbones. It records no observed successful attack in the evaluated cases (ASR = 0%) and achieves an average Utility Under Attack (UA) of 76.10%. Over the strongest evaluated baseline, it improves average UA by 1.84--7.60 percentage points, with benign FPRs of 2.06%--5.15%. We further evaluate long-horizon and adaptive attacks, imperfect purification, runtime overhead, and an OpenClaw case study.

cs.CR · cs.AI

版本更新 · v2arXiv:2512.15773

TS-DP: Reinforcement Speculative Decoding For Temporal Adaptive Diffusion Policy Acceleration

Ye Li, Jiahe Feng, Yuan Meng, Kangye Ji, Chen Tang, Jiajun Fan, Xinwan Wen, Jiawei Li 等 12 位作者

原文摘要

Diffusion Policy (DP) excels in embodied control but suffers from high inference latency and computational cost due to multiple iterative denoising steps. Existing diffusion model (DMs) acceleration methods improve inference speed by reducing computational overhead, as DMs for image generation are computation-bound. In this work, we reveal that DP are I/O bound, and thus propose using speculative decoding, a parallel computing framework, to accelerate DP for the first time. However, it is non-trivial to address the following challenges: (1) How to preserve the denoising quality of the base model at reduced computational cost under time-varying task difficulty in embodied settings; and (2) How to dynamically allocate computation according to task difficulty in such environments. Therefore, we propose Temporal-aware Reinforcement-based Speculative Diffusion Policy (TS-DP), the first framework that enables speculative decoding for DP with temporal adaptivity. First, to handle dynamic environments where task difficulty varies over time, we distill a Transformer-based drafter to imitate the base model and replace its costly denoising calls. Second, an RL-based scheduler further adapts to the time-varying task difficulty by adjusting speculative parameters to maintain accuracy while improving efficiency. Extensive experiments show that TS-DP achieves up to a 4.17x NFE reduction and a 3.2x wall-clock speedup with a draft acceptance rate of over 85% in simulation. Real-world experiments further demonstrate a 3.8x NFE reduction while improving success rates on real-time tasks (e.g., a 23% gain on the conveyor-belt task), reaching an inference frequency of 26 Hz and enabling real-time control while maintaining comparable task performance. The code is available at https://github.com/ChildTang/TS-DP.

cs.LG · cs.AI

新论文 · v1arXiv:2610.34959

GUIFlow: Temporal Redundancy-Aware Incremental Inference for GUI Agents

Ye Li, Haoran Ding, Huanan Liu, Yuan Meng, Yutian Shen, Yuansong Wang, Kangye Ji, Hanyun Cui 等 13 位作者

原文摘要

GUI agents built on vision-language models interact with continuously evolving interfaces, yet conventional inference repeatedly recomputes representations of largely overlapping observations and histories. This mismatch makes multi-step interaction costly, while changes in context, interface content, and action arguments prevent straightforward cache reuse. We introduce GUIFlow, a framework for full-pipeline incremental inference in multi-image GUI interaction. Our central insight is that advancing a decision need not require rebuilding all supporting representations: each interaction step can instead selectively update computational states maintained across the trajectory. To support new decisions as the context evolves, GUIFlow adapts how past computation is reused: historical KV states are position-aligned and injected into the current context; change signals guide selective updates of current-observation states in the vision encoder and language model; and earlier action responses serve as speculative drafts verified by the target model. Together, these mechanisms enable cross-step reuse throughout visual encoding, prefill, and decoding without additional training, a separate draft model, or changes to the model-visible inputs and action interface. Experiments demonstrate up to 3.39x geometric-mean speedup across offline multi-image benchmarks and up to 3.49x in online, closed-loop interaction on OSWorld, while maintaining task performance broadly comparable to the dense baseline.

cs.CV · cs.AI

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.100ACL Anthology · ACL 2026

EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning

Jiawei Liu, Qisi Chen, Jianshu Zhang, Quan Liu, Defu Lian University of Science and Technology of China

原文摘要

Large Language Models (LLMs) excel at complex reasoning through search algorithms, yet current strategies often suffer from massive token consumption due to redundant exploration of semantically equivalent steps. Existing semantic similarity methods struggle to accurately identify such equivalence in domain-specific contexts like mathematical reasoning. To address this, we propose EquivPruner, a simple yet effective approach that identifies and prunes semantically equivalent actions during LLM reasoning search. We also introduce MathEquiv, the first dataset we created for mathematical statement equivalence, which enables the training of a lightweight equivalence detector. Extensive experiments across various models and tasks demonstrate that EquivPruner significantly reduces token consumption, improving searching efficiency and often bolstering reasoning accuracy. For instance, when applied to Qwen2.5-Math-7B-Instruct on GSM8K, EquivPruner reduced token consumption by 48.1% while also improving accuracy. Our code is available at https://github.com/Lolo1222/EquivPruner.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1381ACL Anthology · ACL 2026

From Language to Driving: A Dual-Loop SLM-Enhanced Framework for Multi-Planner Scheduling via a Domain-Specific Language

Jiawei Liu, Xun Gong Jilin University, China, Muli Yang A*STAR, Xingrui Yu Institute of High Performance Computing, Singapore, A*STAR, Fen Fang, Xulei Yang I2R, A*STAR, Ivor Tsang, Yunfeng hu 等 10 位作者

原文摘要

Advancing from usable to collaborative autonomy requires driving systems to execute passenger instructions safely and reliably. This work formulates instruction realization as scheduling across multiple motion planners and presents a dual-loop framework that provides a transparent decision chain from natural language to vehicle control. The outer loop uses a small language model (SLM) for high-level, low-frequency semantic reasoning and schedule generation, while the inner loop performs low-level, high-frequency schedule execution and vehicle control. To compensate for the SLM’s limited capacity, the framework integrates receding-horizon scheduling to segment long-horizon instruction tasks, a domain-specific language (DSL) that restricts SLM outputs to a scheduling-oriented subspace, and reinforcement learning in high-fidelity urban traffic to refine the SLM’s DSL proficiency and scheduling performance. Experiments show that the framework improves instruction-completion rates while maintaining high safety and compliance relative to multiple baselines.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1386ACL Anthology · ACL 2026

Think Better, Not Longer: Token-Level Marginal Utility for Efficient Reasoning in Large Reasoning Models

Jiawei Li, Yang Gao, Huashan Sun, Chong Feng

原文摘要

While Large Reasoning Models (LRMs) have demonstrated remarkable capabilities through explicit Chain-of-Thought (CoT) generation, they frequently suffer from “overthinking”. In this work, we bridge this gap by introducing Token-level Marginal Utility, which quantifies the per-token log-probability gain of the ground-truth answer. Leveraging this dense supervision signal, we propose MUTO (Marginal Utility Guided Thinking Optimization), a unified training framework designed to synthesize concise reasoning chains. Rather than relying only on coarse trajectory-level length control, MUTO identifies tokens that reduce the model’s likelihood of the correct answer and penalizes such negative-utility reasoning, yielding concise yet effective CoT trajectories. Experiments on DeepSeek-R1-Distill-Qwen backbones (1.5B and 7B) across six math reasoning benchmarks show that MUTO yields a markedly better efficiency-accuracy Pareto frontier. It reduces average token usage by 87.1% at 1.5B while improving accuracy by 2.3%, and cuts tokens by 80.2% at 7B with only -0.1% accuracy change, achieving the best length-normalized accuracy among baselines.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.2048ACL Anthology · ACL 2026

ReTRE: Benchmarking LLM Transfer Robustness with Structure-Preserving Variants

ZhongDong Li, Weijie Shi Hong Kong University of Science and Technology, Yue Cui Alibaba Group, Haolun MA The Hong Kong University of Science and Technology, Yuanjun Liu, Jiawei Li Department of Computer Science and Engineering, Hong Kong University of Science and Technology, An Liu Soochow University, Jia Zhu Zhejiang Normal University 等 9 位作者

原文摘要

Large language models (LLMs) have achieved strong performance on standard benchmarks, yet their performance is not robust across different task manifestations. It remains unclear how performance changes under controlled task rewrites that preserve the original solution structure, while varying the rewrite type and level. To address this question, we introduce ReTRE (Rewrite-based Transfer Robustness Evaluation), an evaluation benchmark inspired by learning transfer theory that probes transfer robustness along two rewrite levels: Near Transfer and Far Transfer. ReTRE employs a multi-agent system to construct textual and visual variants while preserving the structure of the original solution. Evaluations on mathematical and science tasks across state-of-the-art multimodal LLMs reveal a consistent transfer gap: performance exhibits a general declining trend as transfer similarity drops and strong text performance can face performance decline under cross-modal transfer. Crucially, we identify a divergence between post-training paradigms: reinforcement learning preserves transfer robustness, whereas supervised fine-tuning tends to overfit the training distribution, leading to severe degradation in far-transfer performance despite strong in-distribution accuracy.

cs.CL · cs.MA · cs.CV

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表