Large reasoning models achieve strong performance on challenging tasks, but their long chain-of-thought often incurs substantial inference costs by continuing to deliberate after sufficient information has been obtained. Existing reasoning compression methods primarily operate on reasoning trajectories, paying less attention to the local decision of whether further reasoning is necessary given the current state. We propose LoCo, a local preference learning method for reasoning compression. LoCo detects candidate overthinking states from the model's own traces, freezes the corresponding reasoning prefixes, regenerates shorter verified continuations from the same states, and trains on the resulting state-conditioned preference pairs with DPO. This formulation teaches the model when to continue reasoning and when to conclude, rather than simply encouraging shorter trajectories overall. We construct training data entirely from self-generated mathematical traces and evaluate LoCo on five mathematical and three code generation benchmarks. LoCo reduces completion length by 41.7\%--45.4\% on mathematics and 23.4\%--36.3\% on code, while maintaining or improving accuracy and achieving the best AUC across all code benchmarks. LoCo consistently improves the accuracy-efficiency trade-off on mathematics and transfers effectively to code generation despite math-only training, demonstrating the cross-domain generality of local preference learning for reasoning compression. The code and model will be publicly released at https://github.com/MuyaoYuan/LoCo.
Zhaoyang Wang, Qianhui Wu, Boyu Gou, Demi Wang, Jiacheng Zhang, Peichun Hua, Qize Li, Shi Qiu 等 57 位作者
GUI web agents require realistic and interactive environments that remain stable during both evaluation and training. Live website evaluation suffers from changing content, access restrictions, and limited coverage of authenticated workflows, while existing synthetic environments for training often lack functional depth and visual fidelity. We propose WebHarbor, a suite of 153 executable and dockerized website environments that faithfully reconstruct the visual interfaces, content, and functional workflows of real-world web services under deterministic control. We build WebHarbor through task-driven human-agent collaboration, where environments evolve as new tasks expand their functional scope, coding agents implement the required changes, and human contributors audit visual fidelity, functional correctness, and task validity. The resulting suite comprises 3,518 tasks spanning multi-step and post-authentication workflows, where existing works often fail to cover. Beyond reliable evaluation, WebHarbor provides high-fidelity synthetic web environments for cost-efficient reinforcement learning (RL). We demonstrate that a Qwen 4B-level GUI agent trained with RL in WebHarbor generalizes to unseen tasks and performs competitively with leading open-source GUI web agents across four benchmarks. The code and data are publicly available at https://github.com/aiming-lab/WebHarbor.
Xingzhi Qian, Sungho Park, Rongyuan Tan, Jianbo Yu, Jue Zhang, Lorenzo Cavallaro, Menglin Xia, Yanzhi Chen 等 16 位作者
Harness optimization can substantially improve LLM agents without modifying model weights, but existing methods primarily optimize response quality. Extending them to joint quality--cost optimization introduces a challenge: applying the deployment preference during intermediate updates can prematurely reject candidates that are valuable for later improvements. We introduce ParetoSaddler, which addresses this mismatch by separating intermediate candidate promotion from final deployment selection. At each iteration, an optimizer updates a parent harness to produce a candidate, and then compares the two over repeated executions and uses Bayesian bootstrap Pareto support to promote candidates showing credible progress in either quality or cost. Promoted candidates receive broader development evaluation and remain available as parents for later optimization steps. We evaluate ParetoSaddler on ClawMark and GAIA2 using domain-disjoint splits. On ClawMark, ParetoSaddler improves quality from 70.86\% to 81.35\% while reducing cost from \$1.17 to \$1.01 per task; on GAIA2, it improves quality from 56.22\% to 62.89\% while reducing cost from \$0.78 to \$0.45 per task. The Pareto-selected harnesses also achieve higher quality at lower cost than quality-only harness optimization. Analysis shows that Pareto-aware optimization retains intermediate candidates that would be discarded by deployment preference but can support later improvements, while Bayesian bootstrap screening filters out candidates whose gains are weakly supported across runs.
Self-evolving agents accumulate experience from task streams, but existing frameworks typically rely on fixed pipelines to retrieve and utilize this experience, neglecting when and how to deploy it. We introduce Online Meta-Control of Experience (OMCE), a framework that updates experience memory and learns a meta-control policy from task feedback during test-time adaptation. OMCE employs a lightweight contextual-bandit meta-controller that uses compact retrieval signals to select among four cognitive actions: DIRECT, EPISODE, GUIDE, and DISTILL. This routing mechanism operationalizes three coupled decisions: whether to invoke experience, which memory format to utilize, and when to consolidate new guidance. OMCE evolves online, leveraging task feedback to update the memory bank and refine the routing policy via contextual bandit updates. Experiments on four online adaptation benchmarks across four backbones show that OMCE improves first-attempt success by up to 20.5 percentage points over the strongest compared baseline, while reducing per-task token use by a factor of 5.7 to 62.5 relative to ACE with GPT-5.2. Controlled ablations further support the benefits of learned routing and continued routing policy adaptation.
Yishuo Cai, Minzheng Wang, Liang Zhao, Linghao Zhang, Lei Li, Shicheng Li, Xu Sun, Fuli Luo
To succeed in real-world long-horizon software development, coding agents must satisfy multi-dimensional task specifications, such as interface compatibility and error handling, and do so without breaking existing dependencies. However, current works lack specification in both quantity and diversity, often emphasizing primary goals while ignoring complex constraints. Synthesizing tasks to bridge this gap presents two challenges: naively adding specifications risks reducing tasks to trivial checklists rather than compelling joint reasoning, and verifying these subtle interactions risks overlooking hidden flaws or rejecting valid alternatives. To address these challenges, we introduce CodeSpecWeave, a framework for synthesizing tasks with rich, interdependent specifications. Grounded in real developer seeds, a synthesis agent iteratively develops both coupled task requirements and executable tests, while a review agent audits solution trajectories from multiple models to guarantee test reliability. Using this pipeline, we construct 4,670 training tasks across 2,865 repositories. Applying Reinforcement learning on these tasks significantly improves performance over the base model on DeepSWE-v1.1, largely outperforming existing baselines. Furthermore, we curate CodeSpecWeave-Bench, a rigorous benchmark comprising 100 tasks and 1,044 specifications, which clearly separates frontier models and reveals significant headroom in handling interdependent engineering constraints.
Yanbin Yin, Chuyu Xu, Liqin Ye, Jing Peng, Chao Zhang
Quarterly earnings forecasting requires an agent to connect financial evidence to the income-statement line items that produce a company's reported earnings. We introduce EPSBench, a benchmark for studying this ability across 149 firm-quarters from 86 US companies. Agents read a fixed collection of filings, earnings-call transcripts, and news, then estimate company-specific income-statement drivers with cited evidence. A shared accounting calculator converts these estimates into GAAP diluted earnings per share (EPS), providing a common basis for comparing forecast assumptions. We evaluate six models under a common harness, assessing point forecast error relative to date-matched analyst consensus and checking whether their prediction intervals achieve the stated coverage. Three models show no detectable paired difference in point forecast error from consensus, and three have higher error. Across all six models, nominal 80% intervals contain reported EPS in only 37--70% of runs that return an interval, and most misses fall above the upper bound because the forecasts run low. The driver records trace most of the error gap between models to operating-income estimates.
We introduce Nemotron 3.5 Super and Nemotron 3.5 Lightning, open and efficient Mixture-of-Experts Hybrid Mamba-Transformer models designed for reasoning, long-context understanding, and agentic workloads. Super is a 120B-parameter, 12B-active multimodal model, while Lightning is a smaller 30B-parameter, 3B-active text model; both designed for efficient deployment. Both models combine large-scale distillation, long-context training, and native speculative decoding, while Super further incorporates Indic continued pretraining and agentic software-engineering mid-training. We develop a comprehensive post-training pipeline spanning supervised fine-tuning and reinforcement learning (RLVR and RLHF), complemented in Super by specialized teacher training and multi- teacher on-policy distillation (MOPD). This transforms Super from a text-only base model into a multimodal agent capable of reasoning over text, images, video, and interactive tool environments. We further explore test-time scaling through parallel agent execution and self-verification. Across training and deployment, we jointly optimize capability and efficiency. Indic continued pretraining improves Indian-language benchmarks by up to 9.82 percentage points, while agentic mid-training strengthens software-engineering capabilities and robustness across agent harnesses. The post-trained Super model achieves 51.78% on SWE-bench Pro, surpassing Nemotron 3 Ultra despite using approximately 4.6x fewer active parameters. Post-training MTP boosting improves speculative- decoding acceptance length by up to 21.8% under probabilistic draft sampling, while NVFP4 quantization achieves 99.62% median accuracy recovery relative to BF16. Inference optimizations enable up to 4,856 output tokens/s/GPU on GB200 while sustaining at least 50 tokens/s/user.
Guoqiang Hu, Lichao Zhang, Yizhou Peng, Yuhao Luo, Haifeng Hu, Sallen Sun, Will Yang, Eng Siong Chng
A full-duplex spoken dialogue model must yield when the user cuts in and hold when the user merely backchannels. Sequence-level RL with a timing reward (GRPO) is the usual recipe; we test its whole-rollout form on four open models and find two failures. A binary window reward gives zero advantage on exactly the windows that most need learning (a zero-gradient trap), and the one score per rollout is spread over listening-state decisions the reward is not written in terms of (credit leakage), so the model talks into silence or stops answering. Both come from sampling a reward that is a known function of a few binary control decisions. We propose \emph{window likelihood} (\WL): sample a continuation per window, but integrate in closed form over the stop decisions it visits and maximise the log-probability of acting correctly---a noisy-OR for yielding, a survival product for holding. On HumDial-FDBench, \WL\ gives the best yield/hold F1 on all six structurally different open models we post-train, exceeds Kyutai's released GRPO checkpoints (trained on different data), and adds no re-opening of the floor on any model.
Work agents operate over digital artifacts to execute professional knowledge-intensive work, requiring training environments that support long-horizon interaction and trustworthy verification. However, hand-crafted environments incur prohibitive engineering overhead that prevents environment scaling, whereas synthesis methods sacrifice workspace complexity, realism, or grounded verifiability. To bridge this gap, we introduce WorkForge, a scalable synthesis framework for constructing verifiable work-agent environments from real-world resources. Starting from expert workflows, WorkForge first identifies the resources, decisions, and deliverables required by each workflow. It then retrieves relevant real-world files and organizes them into a workspace. WorkForge inspects the workspace to extract concrete, checkable facts about its content. These factual anchors fix which task types the workspace can support and how their outcomes can be verified. Therefore, WorkForge derives each task's instructions, solution plan, and complementary programmatic and semantic verifiers directly from these factual anchors, keeping verification traceable to observable workspace evidence. Furthermore, we construct 16.7K verifiable environments across 40 professional domains, with workspaces collectively covering 60 file types. Post-training Qwen3.5-35B-A3B-Base improves GDPVal from 45.5 to 73.6 and APEX Score from 5.0 to 21.3, while enabling Qwen3.5-27B to achieve highly competitive performance and outperform strong competitors. Our analyses confirm the efficacy of the proposed method and reveal consistent scaling behaviors across both data volume and interaction horizons.
Deep research agents extend the role of search engines from retrieving keyword-matched pages to synthesizing knowledge, fundamentally changing how humans interact with information. However, frontier systems remain proprietary, while existing open agents often generalize poorly across different task types, leaving unclear how to train a broadly capable deep research agent. We release QUEST, a family of open models (ranging from 2B to 35B) that serve as general-purpose deep research agents designed to handle a wide range of long-horizon search tasks, with strong capabilities in fact seeking, citation grounding, and report synthesis. To build QUEST, we propose an effective training recipe combining mid-training, supervised fine-tuning, and reinforcement learning. Central to this recipe is a curated data synthesis pipeline based on unified rubric trees, which applies to different task types and enables synthesizing training data with verifiable rewards without human annotation. In addition, QUEST incorporates a built-in context management mechanism that enables effective long-horizon reasoning and knowledge synthesis. Using only 8K synthesized tasks, QUEST approaches or even surpasses frontier closed-source agents across eight deep research benchmarks spanning diverse task types, and achieves the best overall performance among recent open-weight agents. We released everything: models, data, and training scripts.
Tong Zhao, Chenghao Zhang Renmin University of China, Yutao Zhu, Zhicheng Dou Renmin University of China
Audio carries richer information than text, including emotion, speaker traits, and environmental context, while also enabling lower-latency processing compared to speech-to-text pipelines. However, recent multimodal information retrieval research has predominantly focused on images, largely overlooking audio, especially in the setting of interleaved audio-text contextual retrieval. In this work, we introduce the Audio-Text Interleaved contextual Retrieval (ATIR) task, where queries can alternate between audio and text modalities. We construct an ATIR benchmark by integrating several Automatic Speech Recognition (ASR), QA, and retrieval datasets, ultimately unifying four types of contextual retrieval tasks. This benchmark substantially addresses the limitations of existing audio retrieval datasets in semantic retrieval. To study this task, we evaluate several off-the-shelf retrievers and train our ATIR model based on a Multimodal Large Language Model (MLLM). We further propose a novel token compression mechanism, which is orthogonal to existing compression methods, to mitigate the challenge of excessive audio tokens in MLLM-based ATIR models. Experimental results show that our ATIR model achieves significant improvements over strong baselines.
尚无 AI 解读，展示原文摘要
cs.CL · cs.CV
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Wenhao Gao, Tianlong Wang, Wei Jia Tencent, Linhao Zhang, Aiwei Liu Wechat AI, Miao Fan, Zhou Xiao Pattern recognition center
Prompt-based in-context learning (ICL) and parameter fine-tuning are two dominant paradigms for incorporating external information into large language models (LLMs), but they incur high inference costs or require expensive retraining. To bridge this gap, context-to-parameter mapping converts prompts into temporary adapter weights. However, we identify a critical failure mode in existing methods: hidden-state collapse, where the adapter-augmented model’s internal states diverge sharply from the full-context oracle in deeper layers. We trace this failure to two coupled gaps: suboptimal Input-Selection and inadequate Supervision-Signal. To address these issues, we propose SADA (State-Aligned Distillation Adapters). We establish the attention-block output as a principled feature interface to improve input selection and introduce state-alignment distillation to enforce consistency between the adapter-augmented model and the full-context oracle. Experiments on long-context language modeling (PG19) and downstream NLU and summarization benchmarks show that SADA consistently outperforms strong baselines like StreamAdapter and GenerativeAdapter, achieving performance comparable to ICL while significantly reducing memory footprint and latency. We further analyze when parameterized context compression is effective and when explicit context retention remains preferable. Our code is available at https://github.com/Taylor-Gavel/SADA.git.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Yifan Zhang SalesForce.com, Chen Huang National University of Singapore, Yueke Zhang, Jiahao Zhang Vanderbilt University, Toby Jia-Jun Li University of Notre Dame, Collin McMillan University of Notre Dame, Kevin Leach Vanderbilt University, Yu Huang Vanderbilt University
Code Language Models (CodeLLMs) traditionally learn attention based solely on statistical input-output token correlations (“machine attention”). In contrast, human developers rely on intuition, selectively fixating on semantically salient tokens during program comprehension. We present EyeMulator, a model-agnostic technique to align CodeLLM attention with human visual attention without architectural changes. By extracting scan paths from eye-tracking data, we derive token-level attention weights used to augment the loss function during fine-tuning. This induces the model to mimic human focus. Our evaluation across StarCoder, Llama-3.2, and DeepSeek-Coder shows that EyeMulator significantly outperforms baselines, achieving gains of over 30 CodeBLEU points in translation and up to 22 BERTScore points in summarization. Ablation studies confirm that these gains stem directly from replicating human attention dynamics. Artifacts are available at https://zenodo.org/records/17205682.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Minghan Li Soochow University, Junjie Zou, Xinxuan Lv, Chao Zhang, Guodong Zhou Soochow University, China
Retrieval-Augmented Generation (RAG) grounds language models in external evidence, but multi-hop question answering remains difficult because iterative pipelines must control what to retrieve next and when the available evidence is adequate. In practice, systems may answer from incomplete evidence chains, or they may accumulate redundant or distractor-heavy text that interferes with later retrieval and reasoning. We propose S2G-RAG (Structured Sufficiency and Gap-judging RAG), an iterative framework with an explicit controller, S2G-Judge. At each turn, S2G-Judge predicts whether the current evidence memory supports answering and, if not, outputs structured gap items that describe the missing information. We map these gap items into the next retrieval query, producing stable multi-turn retrieval trajectories. To reduce noise accumulation, we maintain a sentence-level Evidence Context by extracting a compact set of relevant sentences from retrieved documents. Experiments on TriviaQA, HotpotQA, and 2WikiMultiHopQA show that S2G-RAG improves multi-hop QA performance and robustness under multi-turn retrieval. Furthermore, S2G-RAG can be integrated into existing RAG pipelines with a lightweight component, without modifying the search engine or retraining the generator.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
The powerful generative capacity of Large Language Models (LLMs) has instigated a paradigm shift in recommendation. However, existing generative models (e.g., OneRec) operate as implicit predictors, critically lacking the capacity for explicit and controllable reasoning—a key advantage of LLMs. To bridge this gap, we propose OneRec-Think, a unified framework that seamlessly integrates dialogue, reasoning, and personalized recommendation. OneRec-Think incorporates: (1) Itemic Alignment: cross-modal Item-Textual Alignment for semantic grounding; (2) Reasoning Activation: Reasoning Scaffolding to activate LLM reasoning within the recommendation context; and (3) Reasoning Enhancement, where we design a recommendation-specific reward function that accounts for the multi-validity nature of user preferences. Experiments across public benchmarks show state-of-the-art performance. Moreover, our proposed “Think-Ahead” architecture enables effective industrial deployment, achieving a 0.159% gain in APP Stay Time and validating the practical efficacy of the model’s explicit reasoning capability.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Xiang Wang, Zongtao Yang Huazhong University of Science and Technology, Zhuojian Hong Huazhong University of Science and Technology, Shuhao Zhang Huazhong University of Science and Technology, Wei Wei Huazhong University of Science and Technology
Agentic workflows are commonly used to guide large language models in solving complex reasoning tasks. However, existing automated workflow generation methods primarily rely on stepwise local refinement or tree-based search over a single evolving workflow. Under limited optimization budgets, this paradigm constrains structural depth, hindering the discovery of workflows that require deep compositional structure. To address this limitation, we propose FusionFlow, a framework centered on workflow fusion. Unlike incremental refinement, fusion enables structural leaps by synthesizing multiple independently evolved workflows, allowing exploration of deeper regions of the workflow space within a finite budget. To make fusion effective, FusionFlow integrates local optimization, task-specific differentiation, and a dynamic scheduling mechanism. Experiments on six reasoning benchmarks demonstrate that FusionFlow consistently outperforms existing automated workflow generation methods. Further ablation and analysis confirm that fusion is the key driver of deep structural exploration, highlighting fusion-driven exploration as an effective approach for overcoming depth limitations in automated workflow generation.
尚无 AI 解读，展示原文摘要
cs.CL · cs.AI
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Minghan Li Soochow University, Tianrui Lv, Chao Zhang, Guodong Zhou Soochow University, China
The semantic gap between colloquial user queries and professional legal documents presents a fundamental challenge in Legal Case Retrieval (LCR). Existing dense retrieval methods typically treat LCR as a black-box semantic matching process, neglecting the explicit juridical logic that underpins legal relevance. To address this, we propose GLIER (Generative Legal Inference and Evidence Ranking), a framework that reformulates retrieval as an inference process over latent legal variables. GLIER decomposes the task into two interpretability-driven stages: (1) A Joint Generative Inference module that translates raw queries into latent legal indicators (Charges and Legal Elements), employing a unified sequence-to-sequence strategy where charges and elements are generated jointly to enforce logical consistency; and (2) A Multi-View Evidence Fusion mechanism that aggregates generative confidence with structural and lexical signals for precise ranking. Extensive experiments on LeCaRD and LeCaRDv2 demonstrate that GLIER outperforms strong baselines like SAILER and KELLER. Notably, our framework exhibits exceptional data efficiency, maintaining robust performance even when trained with only 10% of the data.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Chenghao Zhang, Qingqing Long, Ludi Wang Computer Network Information Center, Chinese Academy of Sciences, Wenjuan Cui, Jianjun Yu CNIC,CAS, Yi Du computer network information center, cas
Recent advances in large language models (LLMs) and text-aware graph learning have increased interest in reasoning over text-attributed graphs(TAGs). In many real-world settings, such graphs are inherently heterogeneous, with most existing benchmarks remaining largely homogeneous in structure. As a result, the lack of large-scale benchmarks for heterogeneous text-attributed graphs has hindered systematic evaluation and fair comparison of existing methods. In this work, we introduce CITE - Catalytic Information Textual Entities Graph, the first and largest heterogeneous text-attributed citation graph benchmark for catalytic materials. CITE contains over 438K nodes and 1.2M edges spanning four node types and four relation types, with rich node-level textual information. We establish standardized evaluation protocols for node classification and link prediction, and conduct ablation studies to assess the impact of graph heterogeneity and textual attributes. Using CITE, we benchmark four classes of learning paradigms, including homogeneous graph models, heterogeneous graph models, LLM-centric models, and hybrid LLM–graph models. By providing a large-scale heterogeneous text-attributed benchmark together with standardized evaluation protocols and comprehensive baselines, CITE enables systematic assessment across diverse modeling paradigms and offers new insights into text-aware and LLM-enhanced graph learning. The dataset, codebase and evaluation suite are publicly available.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Guangya Wan, Mingyang Ling, Xiaoqi Ren, Rujun Han Google, Sheng Li Oracle and University of Virginia, Charlottesville, Zizhao Zhang Google
Long-horizon tasks that require sustained reasoning and multiple tool interactions remain challenging for LLM agents: small errors compound across steps, and even state-of-the-art models often hallucinate or lose coherence. We identify context management as the central bottleneck—extended histories cause agents to overlook critical evidence or become distracted by irrelevant information, thus failing to replan or reflect from previous mistakes. To address this, we propose COMPASS (Context-Organized Multi-Agent Planning and Strategy System), a lightweight hierarchical framework that separates tactical execution, strategic oversight, and context organization into three specialized components: (1) a Main Agent that performs reasoning and tool use, (2) a Meta-Thinker that monitors progress and issues strategic interventions, and (3) a Context Manager that maintains concise, relevant progress briefs for different reasoning stages. Across three challenging benchmarks—GAIA, BrowseComp, and Humanity’s Last Exam—COMPASS improves accuracy by up to 20% relative to both single- and multi-agent baselines. We further introduce a test-time scaling extension that elevates performance to match established DeepResearch agents, and a post-training pipeline that delegates context management to smaller models for enhanced efficiency.
尚无 AI 解读，展示原文摘要
cs.CL · cs.MA
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Ming Li, Pei Chen Amazon, Zhenhao Zhang Amazon, Tao Yang Amazon, Xinyang Zhang Anthropic, Han Li Shopify, Tianyu Cao, Ming Zeng Amazon 等 13 位作者
Large Language Models demonstrate strong capabilities in single-turn instruction following but suffer from Lost-in-Conversation (LiC), a degradation in performance as information is revealed progressively in multi-turn settings. Motivated by the current progress on Reinforcement Learning with Verifiable Rewards (RLVR), we propose Curriculum Reinforcement Learning with Verifiable Accuracy and Abstention Rewards (RLAAR), a framework that encourages models not only to generate correct answers, but also to judge the solvability of questions in the multi-turn conversation setting. Our approach employs a competence-gated curriculum that incrementally increases dialogue difficulty (in terms of instruction shards), stabilizing training while promoting reliability. Using multi-turn, on-policy rollouts and a mixed-reward system, RLAAR teaches models to balance problem-solving with informed abstention, reducing premature answering behaviors that cause LiC. Evaluated on LiC benchmarks, RLAAR significantly mitigates LiC performance decay (62.6% to 75.1%) and improves calibrated abstention rates (33.5% to 73.4%). Together, these results provide a practical recipe for building multi-turn reliable and trustworthy LLMs.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Wei-Cheng Tseng University of Texas at Austin, Xuanru Zhou Zhejiang University, Mingyue Huo, Yiwen Shao Nuance Labs, Hao Zhang Wuhan University, Dong Yu CapitalOne
Audio-language pretraining (ALP) holds promise for learning general-purpose audio representation, yet remains underexplored. Crucially, there is no consensus on whether audio–language models can build effective general-purpose audio encoders, nor a systematic understanding of how pretraining objectives behave across diverse tasks and scales.We identify three key barriers: limited scale of audio-text corpora, limited coverage of audio attributes in existing caption corpora, and lack of systematic exploration and evaluation.To fill this gap, we present the first principled empirical study of ALP.We first introduce CaptionStew, a 10.7M caption dataset aggregating open-source audio-text corpora across multiple domains and captioning focuses.We then conduct the first comprehensive evaluation comparing contrastive and captioning objectives for learning audio representation across speech, music, and environmental sound tasks.Our results not only demonstrate that ALP yields competitive, transferable representations, but reveal critical trade-offs: contrastive learning offers superior data efficiency, while captioning exhibits better scalability.Furthermore, we find that the benefits of supervised initialization often diminish at larger scales, challenging common practices.By grounding these claims in empirical evidence, we establish a viable pathway toward general-purpose audio representation learning, guiding future research.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Tianyu Zong, Rui Dai, Hongzhu Yi, Yuanxiang Wang University of the Chinese Academy of Sciences, Zhenghao Zhang, Zhenyu Guan, Yujia Yang University of the Chinese Academy of Sciences, Bingkang Shi 等 12 位作者
Multimodal representation learning primarily relies on contrastive objectives such as InfoNCE to align diverse modalities. However, these methods focus almost exclusively on directional alignment and often neglect the intrinsic role of embedding magnitudes (L2-norm) in the contrastive process. To bridge this gap, we propose L2Dir, a plug-and-play framework designed to optimize L2-norm alignment and Directional consistency jointly. As a highly efficient solution, L2Dir doesn’t require extra data, distillation, or external supervision. It can be integrated seamlessly into existing pipelines by employing a lightweight MLP to reconstruct magnitudes from frozen backbone features. Extensive evaluations across 95 tasks using UniIR and VLM2Vec-V2 frameworks demonstrate that L2Dir yields consistent and significant performance gains over established baselines across various backbones and scales, proving that explicit magnitude modeling is a versatile and potent strategy for refining unsupervised multimodal representations. The source code for L2Dir in VLM2Vec-V2 is available in the supplementary materials.
尚无 AI 解读，展示原文摘要
cs.CL · cs.CV
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Junchao Wu University of Macau, Yefeng Liu, Chenyu Zhu, Hao Zhang, Zeyu Wu, Tianqi Shi, Yichao Du, Longyue Wang Alibaba Group 等 11 位作者
The effective detection and governance of Large Language Model (LLM) generated content has become increasingly critical due to the growing risk of misuse. Despite the impressive performance of existing detectors, their reliability and potential in multilingual, real-world scenarios remain largely underexplored.In this study, we introduce DetectRL-X, a comprehensive multilingual benchmark designed to evaluate advanced detectors across 8 dimensions. The benchmark encompasses 8 languages commonly used in commercial contexts and collects human-written texts from 6 domains highly susceptible to LLM misuse. To better aligned with real-world applications, We create LLM-generated texts using 4 popular commercial LLMs, and include typical AI-assisted writing operations such as polishing, expanding, and condensing to capture authentic usage patterns. Furthermore, we develop a multilingual framework for paraphrasing and perturbation attacks to simulate diverse human modifications and writing noise, enabling stress testing of detectors across languages.Experimental results on DetectRL-X reveal the strengths and limitations of current state-of-the-art detectors when applied to diverse linguistic resources. We further analyze how domains, generators, attack strategies, text length, and refinement operations influence performance in different languages, underscoring DetectRL-X as an effective benchmark for strengthening multilingual and language-specific detectors.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Hao Zhang, Lyu Mengsi, Zhuo Chen Beijing Academy of Artificial Intelligence, Yulong Ao Beijing Academy of Artificial Intelligence, Yonghua Lin
Large Language Models (LLMs) demonstrate exceptional capabilities across various tasks, but their deployment is constrained by high computational and memory costs. Model pruning provides an effective means to alleviate these demands. However, existing methods often ignore the characteristics of prefill-decode (PD) disaggregation in practice. In this paper, we propose a pruning method that is highly integrated with PD disaggregation, enabling more precise pruning of blocks. Our approach constructs pruning and distillation sets to perform iterative block removal, obtaining better pruning solutions. Moreover, we analyze the pruning sensitivity of the prefill and decode stages and identify removable blocks specific to each stage, making it well suited for PD disaggregation deployment. Extensive experiments demonstrate our approach consistently achieves strong performance in both PD disaggregation and PD unified (non-PD disaggregation) settings, and can also be extended to other non-block pruning methods. Under the same settings, our method achieves improved performance and faster inference.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Bo Lv, Jingbo Sun Institute of automation, Chinese academy of science, Chinese Academy of Sciences, Jianwei Lv Baidu, Chen Tang, Shaojie Zhang, Nayu Liu Tianjin University, Guoxin Yu Pengcheng Laboratory, Zihao Li University of the Chinese Academy of Sciences 等 12 位作者
Optimizing the trade-off among predictive performance and computational cost is a central focus in the deployment of Large Language Models (LLMs). Current routing methods primarily rely on direct mapping from queries to models based on surface-level features, making them susceptible to the memorization trap and leading to poor generalizability on out-of-distribution (OOD) data. In this paper, we propose DecoR, a novel routing framework that recasts the routing task as a matching process of sifting similar queries from historical logs, effectively mitigating the memorization trap. To enhance matching accuracy, we introduce a query capability deconstruction method that decouples linguistic surface forms from task-intrinsic requirements, directing matching toward capability dimensions to ground decisions in essential task attributes. Furthermore, we develop CodaSet, a comprehensive benchmark for assessing routing generalization, where experimental results demonstrate that DecoR maintains superior accuracy while substantially lowering inference costs across both in-distribution and OOD settings.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Jihang Jin, Ronghao Chen QuantaAlpha, Hao Zhang, Ziyan Liu, Huacan Wang QuantaAlpha, Qi Ye East China University of Science and Technology, Jingping Liu SUN YAT-SEN UNIVERSITY
Visual scale recognition is a fundamental aspect for humans to perceive physical quantities in the real world, and it is crucial for enabling human-like intelligence in multimodal large language models (MLLMs). However, existing benchmarks typically focus on a single type of quantity (e.g., time) or a specific format (e.g., dials), lacking a comprehensive evaluation of scale recognition capabilities. To address these problems, we propose ScaleBench, a visual scale recognition benchmark built using images from COCO, Open Images, and Flickr, designed to comprehensively evaluate the scale recognition capabilities of MLLMs. To ensure high data quality, we develop detailed annotation guidelines and procedures, resulting in a total of 6,574 annotated samples. Based on this benchmark, we evaluate multiple closed-source and open-source MLLMs. Experimental results reveal that the best-performing model achieves only 42.60% accuracy, far lower than the 97.40% of humans. Furthermore, we conduct in-depth experimental analyses and provide future research directions. Our benchmark and implementation codes are available at https://github.com/Sonder-hang/ScaleBench.
尚无 AI 解读，展示原文摘要
cs.CL · cs.CV
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Zhihao Zhan, Yuhao Chen SUN YAT-SEN UNIVERSITY, Jiaying Zhou SUN YAT-SEN UNIVERSITY, Qinhan Lyu, Hao Liu SUN YAT-SEN UNIVERSITY, Keze Wang SUN YAT-SEN UNIVERSITY, Liang Lin SUN YAT-SEN UNIVERSITY, Guangrun Wang SUN YAT-SEN UNIVERSITY
Vision-Language-Action (VLA) models have demonstrated impressive capabilities in generalized robotic control; however, they remain notoriously brittle to linguistic perturbations. We identify a critical "modality collapse” phenomenon where strong visual priors overwhelm sparse linguistic signals, causing agents to overfit to specific instruction phrasings while ignoring the underlying semantic intent. To address this, we propose Residual Semantic Steering (RSS), a probabilistic framework that disentangles physical affordance from semantic execution. RSS introduces two theoretical innovations: (1) Monte Carlo Syntactic Integration, which approximates the true semantic posterior via dense, LLM-driven distributional expansion, and (2) Residual Affordance Steering, a dual-stream decoding mechanism that explicitly isolates the causal influence of language by subtracting the visual affordance prior. Theoretical analysis suggests that RSS effectively maximizes the mutual information between action and intent while suppressing visual distractors. Empirical results across diverse manipulation benchmarks demonstrate that RSS achieves state-of-the-art robustness, maintaining performance even under adversarial linguistic perturbations.
尚无 AI 解读，展示原文摘要
cs.CL · cs.CV
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Language agents, i.e., LLM agents, progress rapidly and are increasingly deployed in production environments. This trend underscores the urgent need for rigorous and realistic evaluations. However, most existing benchmarks evaluate agents in simplified, idealized settings. They typically rely on pre-packaged tool interfaces, overlook critical steps, and assume inputs are clean and fully specified. Consequently, they understate the difficulty of real deployments, where uncertainty and noise are ubiquitous and agents must proactively explore the environment to uncover new tools. To bridge this gap, we present AgentGym2, a new evaluation framework with task instances grounded in real-world end-to-end working demands. Beyond reasoning and planning, it measures agents’ ability to execute end-to-end procedures, discover tools via exploration, compose tools for unseen tasks, and remain robust to noisy and underspecified information. Experiments on 15 proprietary and open-source models show that even SOTA systems like Gemini and GPT-5 struggle on AgentGym2, revealing a substantial gap between the capability of current agents and the demands of real-world applications.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Yuhao Zhang, Liang Yan Harbin Institute of Technology, Shenzhen, Shaoming Duan, Xinyu Zha, Jinhang Su Harbin Institute of Technology(Shenzhen), Peiyi Han Harbin Institute of Technology（ShenZhen）, Chuanyi Liu Harbin Institute of Technology
Traditional tabular data synthesis methods often overlook the cross-modal heterogeneity of real-world tables, where structured continuous and discrete attributes coexist with unstructured long-text columns. Existing synthesis approaches struggle to simultaneously achieve accurate statistical fidelity for non-textual attributes and consistent semantic constraints between textual and non-textual attributes. In this work, we establish the first benchmark for long-text tabular data synthesis and introduce a novel metric, termed Textual Column Correlation Fidelity (TCCF), to quantify cross-modal semantic alignment. We propose AFT-Tab, an adversarial fine-tuning framework that synergistically trains an LLM-based text generator and a deep-learning-based non-textual generator. Through a dual-feedback mechanism guided by an LLM discriminator, AFT-Tab ensures both precise statistical distributions and rigorous semantic constraints. Experimental results show that AFT-Tab significantly outperforms state-of-the-art baselines in statistical fidelity, TCCF, diversity, and downstream task utility.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Tingyu Song University of the Chinese Academy of Sciences, Yanzhao Zhang Alibaba Group, Mingxin Li Alibaba Group, Zhuoning Guo Hong Kong University of Science and Technology (Guangzhou), Dingkun Long, Pengjun Xie Alibaba Group, Siyue Zhang, Yilun Zhao Yale University 等 9 位作者
Composed Image Retrieval (CIR) is a pivotal and complex task in multimodal understanding. Current CIR benchmarks typically feature limited query categories and fail to capture the diverse requirements of real-world scenarios. To bridge this evaluation gap, we leverage image editing to achieve precise control over modification types and content, enabling a pipeline for synthesizing queries across a broad spectrum of categories. Using this pipeline, we construct EDIR, a novel fine-grained CIR benchmark. EDIR encompasses 5,000 high-quality queries structured across five main categories and fifteen subcategories. Our comprehensive evaluation of 13 multimodal embedding models reveals a significant capability gap; even state-of-the-art models (e.g., RzenEmbed and GME) struggle to perform consistently across all subcategories, highlighting the rigorous nature of our benchmark. Through comparative analysis, we further uncover inherent limitations in existing benchmarks, such as modality biases and insufficient categorical coverage. Furthermore, an in-domain training experiment demonstrates the feasibility of our benchmark. This experiment clarifies the task challenges by distinguishing between categories that are solvable with targeted data and those that expose intrinsic limitations of current model architectures.
尚无 AI 解读，展示原文摘要
cs.CL · cs.CV
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表