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

+1111新增论文
+874其中 AI 相关
+133已有论文修订
+97新增 AI 导读

arXiv 最近完成扫描:2026-11-20 08:48 · 全站最近入库:2026-11-19 19:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-19 10:08 — 2026-11-20 10:08(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:2026-11-20 08:48最近发现新增版本:2026-11-19 19:09库内论文最新更新时间:2026-11-19 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。

27,982 已收录论文23,249 AI 相关8,559 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 19 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-20 08:46(北京时间)
新论文 · v1arXiv:2611.24672

Predicting Species Splits: A Challenging Fine-Grained Benchmark for Category Discovery

Christian Lange, Joakim Bruslund Haurum, Bingchen Zhao, Oisin Mac Aodha

原文摘要

Widely used category discovery benchmarks have become increasingly saturated and often fail to reflect real-world discovery settings, making long-term evaluation of new methods difficult. We introduce PS-SPLIT, a large-scale fine-grained benchmark for category discovery, motivated by taxonomic splitting: the real-world process by which what was once considered a single species is found to comprise multiple distinct ones. PS-SPLIT contains 79K globally distributed, high-quality, community-collected bird images spanning 771 species, derived from 257 recent real expert-verified taxonomic splits, with associated geographic metadata and full taxonomic hierarchy. The visual differences between categories arising from real taxonomic splits can be very subtle, often requiring significant human expertise to tell apart, making PS-SPLIT a challenging benchmark which we hope will assist in advancing fine-grained category discovery research. Based on taxonomic splitting, we introduce the task of discovery by category splitting, where the goal is to determine which known categories should be subdivided into new finer-grained subcategories. We adapt four generalized category discovery methods to this setting, evaluate existing methods, and show that there is substantial room for future progress.

cs.CV

新论文 · v1arXiv:2611.24622

Evaluating the Effectiveness of Location Encoding Methods for Species Distribution Modelling

Christian Lange, Oisin Mac Aodha

原文摘要

Understanding the spatial distribution of species is a key question in ecology. A variety of solutions, from statistical, traditional machine learning, through to deep learning-based methods have been proposed. These methods take sparse observations for a species of interest as input and aim to generate dense spatial outputs indicating the spatial range of the species. Orthogonal to the choice of statistical model used is the question of what input features are most informative. Thanks to recent developments, the number of options has greatly expanded, with choices spanning different climate variables, learning-based encodings, earth embedding models, or raw transformed geographic coordinates. In this work, we introduce a standardized evaluation framework and quantify the effectiveness of different location encodings in the context of species range estimation, both at the local and global scale.

cs.LG

新论文 · v1arXiv:2611.22777

CrossEnv: Synthesizing Verifiable Cross-Environment Tasks for Long-Horizon Agent Training

Zhengfeng Yu, Tian Lan, Zhijing Wu, Enbo Zhao, Xuannan Liu, Feihu Jiang, Qianghuai Jia, Longyue Wang 等 11 位作者

原文摘要

Executable synthetic environments provide scalable training tasks and verifiable feedback for long-horizon agents. Existing environment synthesis methods primarily generate tasks within individual environments. However, these tasks do not adequately capture real-world interactions across services, where actions in one service depend on information obtained from another. Synthesizing such tasks is challenging because data generated across environments must remain consistent to support executable and verifiable interactions. To address this challenge, we introduce CrossEnv, a framework that uses an entity-tool graph to identify connections between environments and aligns task-specific data to synthesize executable, verifiable cross-environment tasks. We further propose CrossEnv-Curriculum, which progresses from single-environment tool use to coordination across more environments and business domains, before introducing user interaction. Across four external benchmarks, combining cross-environment training data with this curriculum achieves competitive performance with fewer training examples. Further analyses support the benefits of cross-environment data and curriculum training, and provide evidence of transfer to new environment combinations, external tasks less similar to the training data, and longer workflows.

cs.AI · cs.CL

新论文 · v1arXiv:2611.20430

TrainExplorer: Autonomous LLM Post-Training via Plan-and-Decouple Exploration

Xuannan Liu, Tian Lan, Zekun Li, Xing Cui, Zhengfeng Yu, Feihu Jiang, Qianghuai Jia, Longyue Wang 等 12 位作者

原文摘要

LLM-based agents can automate model post-training, accelerating progress toward recursive self-improvement. Despite their promise, existing approaches remain under-explored and face two main challenges: (1) strategy lock-in that limits exploration beyond the initial strategy; and (2) coupled execution that obscures the effects of individual modifications. To address these challanges, we propose TrainExplorer, a multi-agent framework for autonomous post-training, that incorporates strategy planning and execution decoupling, to achieve broaden strategy exploration. First, strategy planning draws on scientific literature to construct a candidate search space of training strategies. Then, decoupled execution enables single-component interventions and attribution to guide strategy exploration. Extensive experiments on PostTrainBench demonstrate that TrainExplorer achieves a weighted aggregate score of 39.02, outperforming Claude Code using the same LLM by 7.32 and surpassing GPT-5.6 Sol-powered Codex, which scores 36.23. Code will be available.

cs.LG · cs.CL

新论文 · v1arXiv:2611.20306

Ontology-Compiled Control Barrier Functions for Heterogeneous Robot Teams

Peng Wu, Seyede Fatemeh Ghoreishi, Nathan Bastian, Mohsen Imani, Tian Lan, Mahdi Imani

原文摘要

Safety filters for heterogeneous robot teams fail because of missing constraints, overestimated braking capabilities and conflicts between individually satisfiable constraints. We present OntoCBF, which compiles a domain ontology with a class taxonomy, typed relations, safety axioms and a dynamics profile per robot class into a control barrier function filter with one quadratic program per agent. Description-logic entailment supplies the constraints of any team online, including those that follow from chains of relations and from classes defined by what a robot carries, so the existing safety axioms cover new robot classes, payload classes and combinations. We prove that a subclass may reuse the braking capability of its parent whenever it can produce every velocity of the parent, a property separate from subsumption. For box-bounded double integrators this property is also necessary, and every loss of safety then begins with a conflict. Once three robots interact, the safe set of pairwise barriers contains states from which a collision is unavoidable, and such states persist in larger teams under any fixed capability reduction. In a simulated warehouse where humans ignore the robots, a filter written for the design classes violates safety in 89-100 % of the episodes with unseen classes. In all scenarios, including one with 32 robots, OntoCBF violates safety in 20-70 % of the episodes, each time after a conflict, with a median deepest intrusion of 10-17 % of the keep-out distance. A multi-agent PPO policy trained with the filter in the loop lowers the rate of infeasible quadratic programs, nearly all of them conflicts, by 18-41 %.

cs.RO · cs.LG

新论文 · v1arXiv:2611.18517

OpenLayout:面向整体VLSI物理设计与基准测试的开放智能体驱动平台

OpenLayout: An Open and Agentic-Driven Platform for Holistic VLSI Physical Design and Benchmarking

Qiufeng Li, Sizhe Tang, Quan Cheng, Zirui Wang, Wantong Li, Tian Lan, Weidong Cao

AI 速读 基于摘要

作者提出一个基于多智能体协作与内置设计知识的开放平台OpenLayout,并配套面向先进工艺节点、使用商业EDA工具的基准OpenLayout-Bench,用于自动化VLSI物理设计中的设计空间优化。

cs.AR

查看原文摘要

Physical design automation of very large-scale integrated circuits (VLSI) has made significant strides, progressing from single-stage placement and routing toward increasingly integrated full-flow implementation. Yet, existing approaches struggle with the vast design space optimization (DSO) arising from diverse technology nodes, circuit designs, and varied constraints. The substantial runtime of physical-design tools further exacerbates this challenge, leaving industrial workflows heavily dependent on experienced engineers to navigate the design space and achieve power, performance, and area (PPA) targets, incurring significant engineering effort. We argue that large language models (LLMs) with strong reasoning capabilities, enriched with distilled human design expertise, offer a promising path toward efficient and automated DSO. Unlike traditional algorithms, LLMs can interpret complex design contexts and naturally incorporate human expertise expressed in natural language for reasoning, acting, observing, and adapting throughout the design process, a capability that conventional optimization methods cannot exploit. To this end, we present OpenLayout, an agentic platform that leverages multi-agent collaboration with embedded design knowledge to enable self-iterative DSO. We further introduce OpenLayout-Bench, a benchmark targeting advanced technology nodes with commercial EDA tools to systematically evaluate physical design automation capabilities of LLMs. Experimental results demonstrate that OpenLayout achieves state-of-the-art performance, with approximately 20% accuracy improvement over baseline methods. Our work is open-sourced at https://github.com/fenggev56/OpenLayout

版本更新 · v2arXiv:2608.23034

ST$^2$U: Stateful Test-Time Unlearning via Restricted Knowledge Boundary Control

Xunlei Chen, Qinghui Gong, Ruini Xue, Yaodong Hu, Tian Lan, Wenhong Tian

原文摘要

Controlling restricted knowledge in large language models is essential for model alignment and safe deployment. Test-time unlearning avoids costly retraining and parameter updates by intervening only during inference. However, existing activation-editing methods apply isolated pointwise corrections, overlooking how autoregressive generation continually reconstructs hidden states from the prompt, cache, and generated prefix. Consequently, later states may return to restricted knowledge regions after a locally successful correction, causing restricted knowledge re-entry. In this work, we propose Stateful Test-Time Unlearning via restricted knowledge boundary control (ST$^2$U), which formulates test-time unlearning as trajectory-wide boundary control. ST$^2$U first models restricted knowledge boundaries in low-dimensional invertible coordinates while leaving orthogonal non-target components unchanged. During inference, ST$^2$U monitors risk along the trajectory, applies minimal boundary corrections with contextual anchoring, and propagates historical correction states across tokens to mitigate knowledge re-entry. This trajectory-wide control enables more persistent forgetting while preserving non-target capabilities and limiting inference overhead. Across three benchmarks and three model families, ST$^2$U delivers the strongest overall balance, combining best or second-best retention with competitive forgetting and substantially less restricted knowledge re-entry than test-time baselines (13.76--19.84% versus 30.44--59.10%).

cs.LG · cs.CL

版本更新 · v4arXiv:2602.16681

VETime: Vision Enhanced Zero-Shot Time Series Anomaly Detection

Yingyuan Yang, Tian Lan, Yifei Gao, Yimeng Lu, Xuming An, Wenjun He, Meng Wang, Chenghao Liu 等 9 位作者

原文摘要

Time-series anomaly detection (TSAD) requires identifying both immediate Point Anomalies and long-range Context Anomalies. However, existing foundation models face a fundamental trade-off: 1D temporal models provide fine-grained pointwise localization but lack a global contextual perspective, while 2D vision-based models capture global patterns but suffer from information bottlenecks due to a lack of temporal alignment and coarse-grained pointwise detection. To resolve this dilemma, we propose VETime, the first TSAD framework that unifies temporal and visual modalities through fine-grained visual-temporal alignment and dynamic fusion. VETime introduces a Reversible Image Conversion and a Patch-Level Temporal Alignment module to establish a shared visual-temporal timeline, preserving discriminative details while maintaining temporal sensitivity. Furthermore, we design an Anomaly Window Contrastive Learning mechanism and a Task-Adaptive Multi-Modal Fusion to adaptively integrate the complementary perceptual strengths of both modalities. Extensive experiments demonstrate that VETime significantly outperforms state-of-the-art models in zero-shot scenarios, achieving superior localization precision with lower computational overhead than current vision-based approaches. Code available at: https://github.com/yyyangcoder/VETime .

cs.CV

版本更新 · v6arXiv:2509.21190

Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy

Tian Lan, Hao Duong Le, Jinbo Li, Wenjun He, Meng Wang, Chenghao Liu, Chen Zhang

原文摘要

Time series anomaly detection (TSAD) is a critical task, but developing models that generalize to unseen data in a zero-shot manner remains challenging. Existing foundation models for TSAD often rely on reconstruction-error scoring at inference time, which can miss subtle anomalies that are well reconstructed and can falsely flag complex but normal patterns in unseen domains. We introduce TimeRCD, a foundation model for TSAD built on Relative Context Discrepancy (RCD), a pre-training paradigm that trains the model to detect anomalies by comparing a query pattern with its surrounding context. This relational formulation, implemented with a standard Transformer architecture, enables the model to infer normality from the input context rather than relying on fixed global normal patterns. We further construct a large-scale synthetic corpus with context-dependent anomaly labels to provide supervised pre-training signals for RCD. Experiments across diverse benchmarks show that TimeRCD outperforms existing general-purpose and anomaly-specific foundation models in most zero-shot TSAD settings, while remaining competitive with dataset-specific full-shot baselines. These results provide empirical evidence that RCD is an effective direction for building robust and generalizable TSAD models.

cs.LG · cs.AI

新论文 · v1arXiv:2611.01706

Agent-Based Disruption Simulation on an Edge-Level Product-Annotated Supply Network of the Automotive Industry

Benjamin Rolf, Hiroyasu Inoue, Sebastian Lang

原文摘要

Disruptions spread through supply networks when customers cannot replace the products they lose. We ask how portfolio-overlap and product-specific rules for selecting candidate suppliers change cascades when customers search for new suppliers and form new supply edges. From the MarkLines database, we construct a product-annotated network of about 77,000 firms and 197,000 supplier-customer edges in the global automotive industry. We extend an agent-based disruption model with edge-level products, a product-specific substitution rule based on the semantic similarity of product names, and calibrated capacities and inventories. Only 6% of the edges carry observed products. We impute the others and test the imputation against the annotated edges. We run 119,000 simulations. With all other mechanics fixed, the product-specific rule makes the cascades after a hub failure four to five times larger than the portfolio-overlap rule of the original model. Under alternative imputations and similarity thresholds, the factor ranges from 1.2 to 18. Within the simulations, substitutability also shapes which suppliers are critical. Network topology largely determines which firms a shock reaches, and substitutability determines how many of them fail. Of the 50 most damaging suppliers under random disruptions, topology alone identifies 20 and an index that adds product substitutability identifies 32. The index carries over without refitting to a regional scenario modelled on the 2011 Tohoku Earthquake. Supply network risk assessment should account for product-level substitutability and therefore needs product data on supply relationships.

cs.SI · econ.GN

新论文 · v1arXiv:2610.38117

Too Hard, Too Easy, Just Right: Performance-Driven Challenge Adaptation in Virtual Reality Firefighter Training

Xuan Wang, Jianan Jiang, Rongqian Chen, Tian Lan, Bin Li

原文摘要

Effective firefighter training requires practice under dynamic and stressful emergency conditions, yet real-world live-fire exercises are costly, risky, and difficult to scale. Virtual Reality (VR) offers a safe and controllable alternative, but many existing VR firefighter training systems rely on fixed scenarios or provide limited difficulty adaptation, making it difficult to maintain an appropriate level of challenge for skill development as trainees' performance changes over time. To address this limitation, we present ProACT, a performance-driven adaptive training system that regulates scenario difficulty through closed-loop interactions between trainee performance and simulated fire dynamics. Specifically, ProACT combines a global module that continuously adjusts scene-level fire spread dynamics in real time based on trainee performance with a local module that periodically updates object-level flammability across the environment. Our evaluation shows that ProACT improves both objective training performance and subjective user experience compared with existing adaptive and non-adaptive baselines. We further discuss how adaptive immersive environments can extend beyond firefighting to broader training domains.

cs.AI

新论文 · v1arXiv:2610.37803

3Dtrees.earth: community research infrastructure for tree and forest analysis using close-range LiDAR data

Janusch Vajna-Jehle, Kilian Gerberding, Daniel Lusk, Teja Kattenborn, Julia Sophie Gäßler, Anna Göritz, Luis Kremer, Charlotte Lange 等 278 位作者

原文摘要

From individual trees to forest stands, three-dimensional structure shapes carbon, water, and energy flows, habitat conditions, and resource availability. Yet tree and forest structural attributes remain difficult to assess consistently across space and time. Close-range LiDAR (light detection and ranging) records detailed 3D structure from branches and trees to forest plots, including trees outside forests. However, broader reuse is constrained when data, acquisition context, processing, computation, and access conditions are maintained separately. We present 3Dtrees.earth, an operational community research infrastructure that brings close-range LiDAR datasets, analysis tools, and computing resources together while linking original observations to their metadata and processing outputs. As of 23 October 2026, the platform comprised 2,760 datasets, including 2,481 publicly visible datasets. These point cloud datasets span 46 countries on all six inhabited continents and include terrestrial, mobile, and uncrewed aerial laser scanning. Users can contribute and discover datasets, run standardized processing workflows on shared computing infrastructure, inspect point clouds and model predictions in the browser, and access data and processing outputs together with citation information. Workflows combine rule-based and machine-learning methods, with tools updated as methods advance. Outputs include raster products, individual-tree and semantic segmentation, and tree- and stand-level metrics. Original point clouds and processing records are retained, enabling reprocessing with improved tools while preserving provenance. With broader coverage, curation, and validation, this shared resource could extend individual surveys into a basis for model evaluation and benchmarking, cross-site synthesis, calibration and validation of larger-scale Earth observation products, and macroecological analysis.

cs.DL

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.1148ACL Anthology · ACL 2026

Know Your Place: Diagnosing Implicit Social Adaptation Failures in Chinese Large Language Models

Yu Tian, Jie Xing, Ziming Li, Jiang Li, Zehua Duo, Tian Lan, Xu Liu, Guanglai Gao Inner Mongolia University 等 9 位作者

原文摘要

As large language models (LLMs) are increasingly deployed in dialogue systems and interactive agents, their social adaptation during natural interaction has drawn growing attention. While prior work shows strong social regulation under explicit role or style instructions, it remains unclear whether LLMs can spontaneously perceive and respond to implicit social differences without explicit prompts. Focusing on high-context Chinese interactions, we identify a robust phenomenon termed Social Agnosia, where LLMs fail to adequately perceive and accommodate implicit social power, affective arousal, and epistemic status during natural interaction. To diagnose this behavior, we propose C-ISA, a framework grounded in Communication Accommodation Theory that decomposes social adaptation into three approximately orthogonal dimensions, and conduct controlled comparisons across multiple Chinese LLMs under implicit and explicit conditions. Results show that while models substantially adjust linguistic strategies under explicit conditioning, they exhibit socially insensitive and homogenized responses in natural interaction, revealing a structural gap between spontaneous behavior and conditioned capability. The C-ISA dataset is publicly available at https://github.com/ty373/C-ISA.

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.121ACL Anthology · ACL 2026

PUPPET: Neural-Symbolic Standardized Patients for Mental Health

Chen Xu, Yu Ji Beijing Institute of Technology, Zhenyu Lyu, Yang Yi, Yizhe Yang, Luyao Ji, Chaoyi Chen, Xianyang Wang 等 15 位作者

原文摘要

The critical therapist shortage demands scalable training solutions. Standardized Patients, the gold standard, are scarce and costly. Current LLM-based approaches focus on patient simulation for conversational realism but lack pedagogical rigor as Virtual Standardized Patients, lacking faithful reactions to clinical errors and explainable feedback. To bridge this gap, we propose PUPPET, the first neural-symbolic Virtual Standardized Patient governed by an OBSERVE-THINK-BEHAVE architecture. PUPPET externalizes LLM reasoning into a symbolic system where experts implant causal associations between intervention logic (propositional logic) and patient mental states (state machine). This allows PUPPET to behave coherently with controllable and explainable psychological dynamics: intervention logic (OBSERVE) → state transition (THINK) → response (BEHAVE). Our PUPPET-TRAINER further leverages this chain to educate trainees about intervention consequences, standardizing and scaling mental health training. Experiments across three clinical scenarios confirm that PUPPET outperforms baselines in clinical faithfulness and pedagogical value.

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.238ACL Anthology · ACL 2026

CEDAR: A Chinese Evaluation Dataset for Computational Argumentation

Tian Lan, Jiang Li, Rong Yan Inner Mongolia University, Feilong Bao, Weihua Wang Inner Mongolia University, Guanglai Gao Inner Mongolia University, Xiangdong Su Inner Mongolia University

原文摘要

Computational argumentation has received increasing attention in recent years. However, existing debate datasets neglect some important labels for argument mining, generation, and evaluation. Meanwhile, the lack of comprehensively annotated Chinese oral debate datasets hinders progress in this field. To address these gaps, we introduce a comprehensive Chinese Evaluation Dataset for Computational Argumentation, named CEDAR. Compared to previous datasets, CEDAR includes the essential labels of computational argumentation (claim, stance, evidence) and five additional crucial labels: rhetorical figures, debater roles, modal words, utterance time, and debate results. Moreover, it offers complete transcripts of each debate, including speeches from the Pro and Con sides. Thus, the proposed CEDAR not only supports common argument mining and generation tasks, but also provides resources for rhetorical figure detection, argument quality evaluation, and debate result prediction. This dataset covers 600 debates about 318 topics from Chinese debate competitions. Besides providing a dataset for research, we conduct experiments on common computational argument tasks and a novel task (rhetorical figure detection), in which we also evaluate LLMs. The experimental results highlight the challenging nature of the dataset. Our corpus is available at https://github.com/VelikayaScarlet/CEDAR.

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.245ACL Anthology · ACL 2026

Who Wrote This Line? Evaluating the Detection of LLM-Generated Classical Chinese Poetry

Jiang Li, Tian Lan, Shanshan Wang, Dongxing Zhang, Dianqing Lin, Guanglai Gao Inner Mongolia University, Derek F. Wong University of Macau, Xiangdong Su Inner Mongolia University

原文摘要

The rapid development of large language models (LLMs) has extended text generation tasks into the literary domain. However, AI-generated literary creations has raised increasingly prominent issues of creative authenticity and ethics in literary world, making the detection of LLM-generated literary texts essential and urgent. While previous works have made significant progress in detecting AI-generated text, it has yet to address classical Chinese poetry. Due to the unique linguistic features of classical Chinese poetry, such as strict metrical regularity, a shared system of poetic imagery, and flexible syntax, distinguishing whether a poem is authored by AI presents a substantial challenge. To address these issues, we introduce ChangAn, a benchmark for detecting LLM-generated classical Chinese poetry that containing total 30,664 poems, 10,276 are human-written poems and 20,388 poems are generated by four popular LLMs. Based on ChangAn, we conducted a systematic evaluation of 12 AI detectors, investigating their performance variations across different text granularities and generation strategies. Our findings highlight the limitations of current Chinese text detectors, which fail to serve as reliable tools for detecting LLM-generated classical Chinese poetry. These results validate the effectiveness and necessity of our proposed ChangAn benchmark. Our dataset and code are available at https://github.com/VelikayaScarlet/ChangAn.

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.25ACL Anthology · ACL 2026

Your Reasoning Model Knows What Counts: Self-Guided Chain-of-Thought Pruning for Efficient Reasoning

Zi-Ao Ma, Xian-Ling Mao Beijing Institute of Technology, Tian Lan Alibaba Group, Chen Xu, Zhijing Wu Beijing Institute of Technology

原文摘要

Chain-of-Thought (CoT) reasoning is crucial for the performance of Large Reasoning Models (LRMs) but is often hindered by redundant and distracting segments, which incur excessive inference costs and degrade robustness. Existing approaches try to solve this problem by enforcing brevity through external supervision, such as length-based penalties or heuristic truncation. However, these approaches often degrade performance because they disregard the model’s intrinsic reasoning dependency and thus fail to distinguish between essential and redundant CoT segments. To address this problem, we propose SGP-CoT, a novel Self-Guided Pruning framework that leverages the model’s intrinsic likelihood landscape to identify segments that are extraneous to its specific reasoning pattern. Specifically, SGP-CoT treats the reasoning trajectory as a sequence of semantic units and assesses the necessity of each one via internal likelihood signals, measuring its contribution to the answer and local coherence. Based on this, it selectively removes non-essential segments and then forms high-quality pruning-based preference pairs, enabling the model to learn focused reasoning via self-optimization. Extensive experiments across diverse benchmarks demonstrate that the proposed SGP-CoT significantly reduces output length while maintaining or improving accuracy. These results validate that LRMs intrinsically possess the capability to discern reasoning utility, positioning SGP-CoT as a robust pathway toward scalable inference.

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.913ACL Anthology · ACL 2026

MTAVG-Bench: A Diagnostic Benchmark for Multi-Talker Dialogue-Centric Audio-Video Generation

Yanghao Zhou, Haitian Li, Rexar Lin, Heyan Huang Beijing Institute of Technology, Jinxing Zhou Mohamed bin Zayed University of Artificial Intelligence, Changsen Yuan, Tian Lan Alibaba Group, Ziqin Zhou Canva 等 15 位作者

原文摘要

Recent advances in text-to-audio-video (T2AV) generation have enabled models to synthesize audio-visual videos with multi-participant dialogues. However, existing evaluation benchmarks remain largely designed for human-recorded videos or single-speaker settings. As a result, structural failures in generated multi-talker dialogue videos, such as identity drift, unnatural turn transitions, and audio-visual misalignment, cannot be effectively diagnosed. To address this issue, we introduce MTAVG-Bench, a failure-driven diagnostic benchmark for multi-talker dialogue-centric audio-video generation. MTAVG-Bench is built via a semi-automatic pipeline, where 1.8k videos are generated using mainstream T2AV models with carefully designed prompts, yielding 2.4k manually annotated QA pairs for fine-grained failure diagnosis. The benchmark evaluates multi-speaker dialogue generation at four levels: audio-visual signal fidelity, temporal attribute consistency, social interaction, and cinematic expression. Built on a hierarchical failure taxonomy and a targeted QA protocol, MTAVG-Bench is primarily designed to evaluate whether proprietary and open-source omni-models can reliably identify failure modes in multi-speaker T2AV outputs. We benchmark 12 proprietary and open-source omni-models on MTAVG-Bench, with Gemini 3 Pro achieving the strongest overall performance, while leading open-source models remain competitive in signal fidelity and consistency. Overall, MTAVG-Bench enables fine-grained failure analysis for rigorous model comparison and targeted video generation refinement.

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.937ACL Anthology · ACL 2026

HSCodeComp: A Realistic and Expert-level Agent Benchmark for Hierarchical Rule Application

Tian Lan Alibaba Group, Yiqian Yang, Qianghuai Jia, Li Zhu Alibaba Group, Hui Jiang, Hang Zhu, Weihua Luo Alibaba International Digital Commerce Group, Longyue Wang Alibaba Group

原文摘要

Despite recent progress, existing agent benchmarks neglect a fundamental real-world capability: hierarchical rule application, a critical requirement in fields such as law and medicine where agents must reason from broad categories down to specific exceptions to reach rule-compliant decisions.This introduces significant challenges in resolving logical dependencies and disambiguating vague boundaries.To bridge this gap, we introduce HSCodeComp, a novel benchmark derived from e-commerce, requiring agents to assign a unique 10-digit Harmonized System (HS) Code to products by aligning their fuzzy attributes with strict tariff classification rules.HSCodeComp comprises 632 realistic products across 32 categories, featuring detailed yet noisy product information (titles, attributes, and images). The HS Codes are annotated by a panel of 26 tariff experts, strictly adhering to official rules and an empirical knowledge base, both of which we jointly open-source.Through a comprehensive evaluation of 23 LLMs, VLMs, and agents on HSCodeComp, we demonstrate that: 1) a substantial performance gap remains between state-of-the-art agents and human experts (46.8% vs. 95.0%); and 2) test-time scaling fails to close this gap. Further analysis reveals that 1) excessive reasoning steps frequently induce “reasoning drift,” which degrades accuracy; and 2) agents are prone to premature decisions on high-level categories and reasoning hallucinations that lack factual grounding.

cs.CL

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