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 10:52 — 2026-11-18 10:52(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 23 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)
新论文 · v1arXiv:2611.19692

MathaMAGICal: Validating Trajectory Data Attribution During Capability Acquisition

Jason Lee, Dikshanta Pokhrel, Phonn Nay Khant, Victor Lee, Moritz Weckbecker, Sebastian Lapuschkin, Wojciech Samek, Mark Riedl 等 9 位作者

原文摘要

Influence-function-based methods like MAGIC provide exact first-order scores for trajectory data attribution, yet only retraining indicates whether those scores accurately predict data removal. We evaluate MAGIC on $86$M- and $152$M-parameter GPT-2-style models learning multistep arithmetic from scratch on filtered web text and four synthetic math families. Full-run attribution at $86$M suffers from numerical overflow, and even with metagradient clipping, scores correlate near chance with retraining (linear datamodeling score, LDS, $0.17$--$0.22$). In contrast, short checkpoint windows yield stable, accurate predictions at both scales (LDS $0.86$--$0.99$ across four $100$-step windows at $152$M), whereas a single-checkpoint gradient-dot baseline shows near-zero correlation. Rankings of individual training blocks predict retraining only within that single run and do not transfer across seeds or hyperparameters ($ρ\le 0.09$), whereas format-level patterns replicate across runs. Two data families, worked examples and primitive facts, occupy $2.1$--$2.6\times$ their corpus share in both the helpful and harmful $5\%$ score tails, reflecting strong bidirectional local sensitivity distinct from net benefit under multi-epoch family deletion. These results show that trajectory attribution is reliable within short, validated windows and yields family-level insights that generalize across runs.

cs.LG · cs.AI · cs.CL

新论文 · v1arXiv:2611.19299

Staged Semantic Distillation: Preserving Free-Form Semantics in a Low-Compute Non-LLM Surrogate of a Staged LLM Agent

Zhiyang Niu, Huayuan Shen, Chuanjie Li, Mengmeng Zhao, Jiajia Zhang

原文摘要

Staged LLM agents make market and social simulators realistic, but one 102-day run of a 200-agent, ten-index market simulator issues 203,100 language-model calls and returns one realization. Conventional low-compute distillation drops their free-form intermediate state. We present staged semantic distillation, a low-compute method that preserves non-structured semantics in a non-LLM student trained from one recorded trace. A frozen encoder maps each teacher output to a 1024-d vector; the student sees typed stage-tagged vectors with stage-specific visibility, is jointly supervised, and trains with scheduled self-history. One TwinMarket trace yields a 13.2M-parameter deterministic student that trains in 1,658 seconds on one 8-GB GPU and runs with zero teacher or decoder calls and no text generation (0.14 ms per decision). Its analysis stays close to the teacher (cosine 0.943), and swapping semantic inputs between agents moves 64.7% of decisions against 12.8% for a matched donor, so the channel is preserved and live. We use the surrogate to study what the transfer carries. It reaches 0.8347 balanced accuracy on the teacher-forced replay and 0.7783 [0.766,0.791] on the deployment decoder; the five-seed gain over a no-semantic retrain is +2.2 [1.21,3.14]. Against the teacher's own re-sampling level, round-one R is 97.1% [95.8,98.4] and 92.3% [89.0,95.4]; R is a diagnostic, not an accuracy. A five-seed content-by-schedule study isolates the gain: scheduled self-history carries it (+2.2 [1.21,3.14]); shuffled and constant content controls reproduce it, while content matters teacher-forced. The design rule: invest in the deployment schedule, let content earn its place at the teacher-forced operating point. A 20-seed, 200,000-decision sweep takes 12 minutes with zero LLM calls, versus three hours for the teacher. The paper is a method-and-case-study contribution on one simulator and trace.

cs.AI · cs.CL · cs.LG · cs.MA

新论文 · v1arXiv:2611.17963

Toward Universal Translatability: On the Statistical Ontology of Generative AI

Katia Schwerzmann

原文摘要

This paper argues that the problem of translation functions both as a point of origin and as a normative horizon for contemporary generative AI. In current discourse around ''world models,'' their attainment is framed as the achievement of internal consistency, cross-modal alignment, and physical grounding. Taken together, these demands converge on an ideal of the model as a universal translation machine capable of establishing lossless correspondences across linguistic, visual, and physical representation spaces. I show that this ideal presupposes a metaphysical commitment that I call a statistical ontology: the belief that reality has an underlying, computable statistical structure that can be recovered through sufficient data and modeling, rather than being shaped and accessed through situated human interpretation and labor. Tracing this commitment back to Warren Weaver's 1949 Memorandum on machine translation, I outline how translation was historically recast as code deciphering and, later, as the alignment of probability distributions across structured outputs. Finally, I contrast this paradigm with approaches in Translation Studies that foreground opacity, power asymmetries, and the translator's positionality. I argue that generative AI's statistical ontology is pre-Kantian, pre-critical and obscures the infrastructures and human labor that make machine translatability---as alignment---possible in the first place.

cs.CL

新论文 · v1arXiv:2611.10369

FEROM: Frontier Endogenous Reveal-Order Marginal Policy Optimization for Masked Diffusion LMs

Zian Su, Ziyang Huang, Kaiyuan Zhang, Xiangyu Zhang

原文摘要

Masked diffusion language models generate text by iteratively unmasking positions, with practical samplers often selecting reveal positions from the model's own logits. The reveal order is therefore an endogenous latent variable of the rollout process with an enormous discrete latent space. Policy optimization objectives relying on pre-defined schedules or sampled trajectories introduce either bias or high variance. In this paper, we propose FEROM, Frontier Endogenous Reveal-Order Marginal Policy Optimization, which approximates policy gradients for the rollout-induced marginal response policy of masked diffusion LMs. FEROM derives a Rao-Blackwellized policy-gradient identity over latent reveal orders and expresses the resulting estimator as posterior edge occupancy on a reveal-state DAG. To make marginalization practical, we introduce Frontier Reveal Marginalization, a budgeted estimator that approximates this marginal edge structure by combining CDF-based computation of local probabilities of the endogenous reveal process with frontier expansion of high-mass partial states. Integrated into a GRPO-style objective, FEROM replaces single-path log-scores with a detached token-score surrogate over posterior-relevant reveal edges. Experiments on math and coding tasks show comparable or improved results over existing methods under matched scoring-state budgets. An offline proxy study further shows improved marginal-gradient approximation with increased scoring budgets.

cs.CL · cs.AI

新论文 · v1arXiv:2611.04231

Constructing a Regional Slang Lexicon for Electricity Demands via Soft-Label Bidirectional Anchoring and Active Learning

Rong Chang, Lijing Shi, Zhaoxiang Zang

原文摘要

Power-grid customer service increasingly relies on community social media, where customers describe outages, billing, and equipment faults in informal regional dialect. Such messages exhibit non-standard morphology, semantic drift, and out-of-vocabulary expressions that make manual lexicon construction costly and degrade conventional NLP tools. We propose a weak-supervision framework constructing a regional slang lexicon from curated dialect anchors and power-domain seed terms. Candidates are generated via Pointwise Mutual Information with soft-label bidirectional anchoring, retaining dialect-anchored terms while recording power-domain relevance as separate metadata, and are scored by combining Sentence-BERT semantic similarity with a jieba-based wordhood measure. Uncertainty-aware active learning with rule-based and retrieval-augmented LLM oracles is applied under three query strategies, and the resulting lexicon is evaluated by a higher-capability LLM calibrated against human expert annotations via Cohen's $κ$. On 11,177 real WeChat messages from Yuxi (Yunnan, China), the framework achieves an evaluator-estimated dialect precision of DP~$=$~1.0 with zero false positives. An ablation shows that soft-label layering retains 751\% more candidates than strict power-gating at identical precision, expanding the candidate pool from 41 to 349 terms. Human calibration ($n=46$) yields $κ_{\text{dialect}}=1.0$ and $κ_{\text{power}}=0.85$. The resulting 25--33-term lexicon, 4--5 of which are power-relevant, provides a preliminary resource for dialect-aware power-grid service NLP.

cs.CL · cs.AI

版本更新 · v2arXiv:2610.23847

Behavioral Couplings: From Formation to Behavioral Emergence in Language Models

Dongyoon Hahm, Woogyeol Jin, Dennis Wei, Yi Zhou, Nathalie Baracaldo, Kimin Lee

原文摘要

Fine-tuning large language models (LLMs) can induce behaviors beyond those explicitly targeted. For example, training a model to respond more warmly can make it more sycophantic, and training it to write insecure code can cause broad misalignment on prompts unrelated to coding. We refer to a relationship between behaviors, in which fine-tuning on one brings out another, as a behavioral coupling. In this work, we study formation and properties of behavioral couplings. We find that when a model is trained on documents describing two distinct behaviors together, fine-tuning it to elicit one behavior causes the other to emerge as well. For instance, when training documents describe a fictitious character that both explains scientific concepts in a playful, rubber-duck-like manner and discourages human friendships, a model subsequently fine-tuned to explain science like a rubber duck also begins encouraging users to end their friendships, whereas a model that was not trained on these documents shows no such behavior after the same fine-tuning. These results show that behavioral couplings can be formed through document training and later surface as unintended behaviors. More concerningly, we find that couplings can compose. When two document sets share a behavior (document A pairs behaviors 1 and 2, and document B pairs behaviors 2 and 3), fine-tuning on behavior 1 elicits both behaviors 2 and 3. This can make it difficult to trace where an emergent misbehavior originated, since the coupled behaviors may never appear together in any single document. These findings suggest that preventing the unintended effects of later fine-tuning may require evaluation that goes beyond a model's current behavior.

cs.CL · cs.AI · cs.LG

版本更新 · v2arXiv:2606.19350

Pruning via Causal Attribution Preserves Reasoning Performance in Large Language Models

Amogh Sheth, Andrew Lin, Biruk Assefa, Yi Wen Huang, Yuhao Ge

原文摘要

Large language models (LLMs) excel at multi-step reasoning but incur substantial inference cost. We introduce Causal Attribution Pruning (CAP), a training-free method that identifies critical attention heads by measuring their causal impact on reasoning tasks and uses these head-level scores to guide fine-grained weight pruning. For each attention head, CAP estimates the expected performance degradation when the head is masked during forward passes on a small calibration set of reasoning problems. These causal scores are then converted into weight-level importance values for the corresponding projection matrices. Unlike magnitude-only or activation-based criteria, CAP's interventional measurement directly captures each head's functional contribution, yielding relative accuracy gains of up to 61% over Wanda on ARC-Challenge at 20% sparsity. We evaluate CAP on GSM8K, StrategyQA, and ARC-Challenge using Llama-3-8B-Instruct and Mistral-7B-Instruct at 10%, 20%, and 50% sparsity. At moderate sparsity (10-20%), CAP improves over Wanda in most model-benchmark configurations. with especially large gains on ARC-Challenge for Llama-3. Our results suggest that attention-head-level causal attribution can better preserve reasoning performance on downstream benchmarks than correlational pruning criteria at equivalent sparsity, while remaining limited by coarse MLP attribution at 50% sparsity.

cs.CL

新论文 · v1arXiv:2610.36523

Benchmarking Task Takeover Across Agent Handoffs

Wenyuan Li, Guang Li, Dongyuan Li, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama

原文摘要

As agents collaborate on longer tasks, responsibility may pass between models before the work is complete. The receiving model must build on prior decisions, observations, and actions while addressing the remaining requirements. Evaluating this transition requires connecting the information preserved at handoff to how the receiver continues the work, a relationship that task-success and memory-retention scores alone do not capture. We introduce the Handoff State Continuity Benchmark (HSC-Bench), comprising 1,039 tasks that evaluate two complementary aspects of task takeover: recovering relevant repository evidence and continuing from established conversational, tool, and file-work state. Comparisons across six receiving models show that structured handoff state improves repository evidence recovery for every model and continuation performance for most models. The strongest receivers differ between the two tracks, showing that evidence-recovery rankings alone do not characterize performance when continuing from inherited state. By combining these comparisons with checks of subsequent responses and actions, HSC-Bench evaluates both access to prior evidence and adherence to established commitments and completed work. This provides a basis for selecting receiving models and assessing handoff representations according to the work that must be carried forward.

cs.CL

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-industry.95ACL Anthology · ACL 2026

SimRPD: Optimizing Recruitment Proactive Dialogue Agents through Simulator-Based Data Evaluation and Selection

Zhiyong Cao, Dunqiang Liu, Qi Dai, Haojun Xu, Huai Yuen Khor, Hao Wang, Huan He, Yafei Liu 等 12 位作者

原文摘要

Task-oriented proactive dialogue agents play a pivotal role in recruitment, particularly for steering conversations towards specific business outcomes, such as acquiring social-media contacts for private-channel conversion. Although supervised fine-tuning and reinforcement learning have proven effective for training such agents, their performance is heavily constrained by the scarcity of high-quality, goal-oriented domain-specific training data. To address this challenge, we propose \textbf{SimRPD}, a three-stage framework for training recruitment proactive dialogue agents. First, we develop a high-fidelity user simulator to synthesize large-scale conversational data through multi-turn online dialogue. Then we introduce a multi-dimensional evaluation framework based on \textbf{Chain-of-Intention (CoI)} to comprehensively assess the simulator and effectively select high-quality data, incorporating both global-level and instance-level metrics. Finally, we train the recruitment proactive dialogue agent on the selected dataset. Experiments in a real-world recruitment scenario demonstrate that SimRPD outperforms existing simulator-based data selection strategies, highlighting its practical value for industrial deployment and its potential applicability to other business-oriented dialogue scenarios.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track) · 2026 · 正式发表

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.11ACL Anthology · ACL 2026

Benchmarking LLM’s Capability in Reasoning over Conflicting Web References

Yizhen Yuan Tsinghua University, Tsinghua University, Rui Kong, Dongze Li Seafile, Yuanchun Li Institute for AI Industry Research, Tsinghua University, Yunxin Liu

原文摘要

Large language models (LLMs) integrated with retrieval-augmented generation (RAG) have become a dominant framework for building intelligent assistants. In real-world applications such as ChatGPT with web search, the retrieved document often comes from diverse, potentially unreliable sources and may contain inconsistent claims. Unlike traditional search engines that rely on users to manually compare information, LLM-based systems typically feed all retrieved content into the model’s context, requiring LLMs to autonomously identify, differentiate, and reason over conflicting viewpoints. Unlike mainstream LLM evaluation tasks like math and code generation that are primarily focused on reasoning with factual context, question-answering with multi-source references requires fundamentally different capabilities to identify and reason over knowledge contradictions. In this paper, we introduce ConfRAG, a benchmark for evaluating LLMs’ reasoning capability over real-world conflicting documents retrieved from the web. It consists of 1,814 real-world questions, each paired with an average of 9.58 retrieved paragraphs from heterogeneous online sources. A total of 57.2% of the questions exhibit explicit contradictions. We further propose three structured evaluation tasks, answer clustering, answer coverage, and reason coverage, to quantify a model’s ability to organize and explain contradictory content. Experiments with state-of-the-art models such as GPT-4.1 and Claude-3-7-Sonnet reveal substantial performance gaps, highlighting the need for more targeted research in contradiction-aware question answering. To the best of our knowledge, ConfRAG is the first benchmark specifically designed to evaluate contradiction-aware reasoning on real-world long web documents.

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.1366ACL Anthology · ACL 2026

TOWER+: Bridging Generality and Translation Specialization in Multilingual LLMs

Ricardo Rei, Nuno M Guerreiro Sword Health and Instituto Superior Técnico, José Pombal Sword Health, Inc and Instituto Superior Técnico, João Alves Acolad, Amin Farajian Unbabel, Pedro Teixeirinha TransPerfect, Andre Martins Instituto Superior Técnico and Unbabel

原文摘要

Fine-tuning pretrained LLMs has proven effective for reaching state-of-the-art performance on specific tasks like machine translation. However, this process often implies sacrificing general-purpose capabilities, such as conversational reasoning and instruction-following, hampering the usefulness of the system in real-world applications requiring a mixture of skills. In this paper, we introduce Tower+, a suite of models designed to deliver strong performance on both translation and multilingual general-purpose text capabilities. We improve the TOwer (Alves et al., 2024) recipe by adding novel stages of preference optimization and reinforcement learning with verifiable rewards, in addition to continued pretraining and supervised fine-tuning. At each stage, we carefully generate and curate data to strengthen performance on translation and general-purpose tasks like coding, mathematics, and instruction-following. We develop models at multiple scales: 2B, 9B, and 72B. Our smaller models often outperform larger general-purpose open-weight and proprietary LLMs (e.g., Llama 3.3 70B, GPT-4o). Our largest model delivers best-in-class translation performance for high-resource languages, and top results on multilingual Arena Hard and IF-MT, a benchmark we introduce for evaluating both translation and instruction-following.

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.1445ACL Anthology · ACL 2026

RubricHub: A Comprehensive and Highly Discriminative Rubric Dataset via Automated Coarse-to-Fine Generation

Sunzhu Li Li Auto Inc., Jiale Zhao, Huimin Ren Li Auto Inc., Zhenlin Wei, Yang Zhou Zhejiang University, Jingwen Yang, Shunyu Liu Nanyang Technological University, Kaike Zhang Li Auto Inc. 等 9 位作者

原文摘要

Reinforcement Learning with Verifiable Rewards (RLVR) has driven substantial progress in reasoning-intensive domains like mathematics. However, optimizing open-ended generation remains challenging due to the lack of ground truth. While rubric-based evaluation offers a structured proxy for verification, existing methods suffer from scalability bottlenecks and coarse criteria, resulting in a supervision ceiling effect. To address this, we propose an automated Coarse-to-Fine Rubric Generation framework. By synergizing principle-guided synthesis, multi-model aggregation, and difficulty evolution, our approach produces comprehensive and highly discriminative criteria capable of capturing the subtle nuances. Based on this framework, we introduce RubricHub, a large-scale (110k) and multi-domain dataset. We validate its utility through a two-stage post-training pipeline comprising Rubric-based Rejection Sampling Fine-Tuning (RuFT) and Reinforcement Learning (RuRL). Experimental results demonstrate that RubricHub unlocks significant performance gains: our post-trained Qwen3-14B achieves state-of-the-art (SOTA) results on HealthBench (69.3), surpassing proprietary frontier models such as GPT-5.

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.178ACL Anthology · ACL 2026

Crossing the Reward Bridge: Expanding Reinforcement Learning with Verifiable Rewards Across Diverse Domains

Yi Su, Dian Yu Tencent AI Lab, Linfeng Song Google, Juntao Li, Haitao Mi Tencent AI Lab, Zhaopeng Tu Tencent, Min Zhang Harbin Institute of Technology, Shenzhen and Harbin Institute of Technology, Dong Yu CapitalOne

原文摘要

Reinforcement learning with verifiable rewards (RLVR) has been effective on tasks with structured solutions like math and coding, but its reliance on simple, rule-based verifiers creates a fundamental bottleneck. We find their applicability is surprisingly narrow even in structured domains, a limitation that is compounded at scale: rule-based systems can paradoxically degrade in performance as multi-domain, free-form training data increases. To overcome these challenges, we propose a new RLVR framework that uses a generative verifier to provide soft, probabilistic rewards. Our key insight is that powerful LLMs show high agreement with human evaluators when judging answer correctness given a ground-truth reference, allowing us to automate reward generation without costly human annotation. Our experiments demonstrate the effectiveness of this approach. We show that a compact 7B generative reward model can guide a 7B policy model to decisively outperform models up to 10x its size, including the 72B Qwen2.5-Instruct (by a margin of +8.6%). This effectiveness is robust, holding true across diverse training datasets with answers sourced from experts, web users, and other LLMs, and generalizes strongly to seven out-of-distribution benchmarks. Our work provides a scalable and effective framework for extending RLVR beyond the limitations of pattern-based verification to complex, noisy, real-world domains.

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.1910ACL Anthology · ACL 2026

Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks

Wenqi Zhang Zhejiang University, Mengna Wang, Gangao Liu, Huixin Xu, Yiwei Jiang Syracuse University, Yongliang Shen Zhejiang University, Guiyang Hou, Zhe Zheng Zhejiang University 等 14 位作者

原文摘要

Recent advances in reasoning models have demonstrated remarkable capabilities on mathematical and coding tasks. However, their effectiveness in embodied domains, where the agent must continuously interact with environments and process observation-action interleaved trajectories, remains largely unexplored. We present Embodied-Reasoner, a reasoning model for interactive embodied tasks. Unlike mathematical reasoning that relies primarily on logical deduction, embodied scenarios demand spatial understanding, temporal reasoning, and ongoing self-reflection based on interaction history. To address these challenges, we synthesize 9.3k coherent Observation-Thought-Action trajectories containing 64k ego-centric images and 90k diverse reasoning processes (analysis, spatial reasoning, reflection, planning, and verification). We develop a three-stage training recipe that progressively enhances the model’s capabilities through imitation learning, rejection sampling tuning on self-exploration trajectories, and reflection tuning. The evaluation shows that our model significantly outperforms advanced visual reasoning models, e.g., exceeds OpenAI o1, o3-mini, and Claude-3.7 by +9%, 24%, and +13%. Analysis reveals that our model exhibits fewer repeated searches and logical inconsistencies, with particular advantages in complex long-horizon tasks. Real-world testing further validates the effectiveness of our approach.

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.2042ACL Anthology · ACL 2026

Response-G1: Explicit Scene Graph Modeling for Proactive Streaming Video Understanding

Ke Ma, Jiaqi Tang, Bin Guo Northwestern Polytechnical University, Xueting Han, Ruonan Xu, Qingfeng He, Ziheng Wang, Xu Wang 等 11 位作者

原文摘要

Proactive streaming video understanding requires Video-LLMs to decide when to respond as a video unfolds, a task where existing methods often fall short due to their implicit, query-agnostic modeling of visual evidence. We introduce Response-G1, a novel framework that establishes explicit, structured alignment between the accumulated video evidence and the query’s expected response conditions via scene graphs. The framework operates in three fine-tuning-free stages: (1) online query-guided scene graph generation from streaming clips; (2) memory-based retrieval of the most semantically relevant historical scene graphs; and (3) retrieval-augmented trigger prompting for per-frame “silence/response” decisions. By grounding both evidence and conditions in a shared graph representation, Response-G1 achieves more interpretable and accurate response timing decisions. Experimental results on established benchmarks demonstrate the superiority of our method in both proactive and reactive tasks, validating the advantage of explicit scene graph modeling and retrieval in streaming video understanding.

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.2172ACL Anthology · ACL 2026

Apertus: Democratizing Open and Compliant LLMs for Global Language Environments

Alejandro Hernández-Cano EPFL - EPF Lausanne, Alexander Hägele EPFL - EPF Lausanne, Allen Hao Huang EPFL - EPF Lausanne, Angelika Romanou, Antoni-Joan Solergibert, Barna Pásztor ETHZ - ETH Zurich, Bettina Messmer EPFL - EPF Lausanne, Dhia Garbaya 等 102 位作者

原文摘要

Open LLMs enable AI practitioners to control development costs by building on an existing foundation for downstream applications. While offering substantial promise, current models often fail to meet the needs of users needing open solutions aligned with responsible AI principles, including data compliance, transparency, and inclusivity. In this work, we present Apertus, a fully open suite of large language models (LLMs) designed to address responsibility shortcomings in today’s open model ecosystem, namely data responsibility and global representation. Unlike many prior models that release weights without reproducible data pipelines or regard for content-owner rights, Apertus models are pretrained exclusively on openly available data, retroactively respecting robots.txt exclusions and filtering for non-permissive, toxic, and personally identifiable content. To mitigate risks of data memorization, we also adopt the Goldfish objective during pretraining, strongly suppressing verbatim recall of data while retaining downstream task performance. Apertus also drastically expands multilingual coverage, training on 15T tokens from over approximately 1800 languages, with about 40% of pretraining data allocated to non-English content. Released at 8B and 70B scales, Apertus approaches state-of-the-art results among fully open models on multilingual benchmarks, rivaling or surpassing open-weight counterparts.

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.2198ACL Anthology · ACL 2026

MathSight: A Benchmark Exploring Have Vision-Language Models Really Seen in University-Level Mathematical Reasoning?

Yuandong Wang Capital Normal University, Yao Cui, Yuxin Zhao, Zhen Yang, Yangfu Zhu, Zhenzhou Shao

原文摘要

Recent advances in Vision-Language Models (VLMs) have achieved impressive progress in multimodal mathematical reasoning. Yet, howmuch visual information truly contributes to reasoning remains unclear. Existing benchmarks report strong overall performance but seldom isolate the role of the image modality, leaving open whether VLMs genuinely leverage visual understanding or merely depend on linguistic priors. To address this, we present MathSight, a university-level multimodal mathematical reasoning benchmark designed to disentangle and quantify the effect of visual input. Each problem includes multiple visual variants—original, hand-drawn, photocaptured—and a text-only condition for controlled comparison. Experiments on state-of-the-art VLMs reveal a consistent trend: the contribution of visual information diminishes with increasing problem difficulty. Remarkably, Qwen3-VL without any image input surpasses both its multimodal variants and GPT-5, underscoring the need for benchmarks like MathSight to advance genuine vision-grounded reasoning in future models. The project page is available at https://cnu-bot-group.github.io/MathSight/.

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

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.255ACL Anthology · ACL 2026

Writing-RL: Advancing Long-form Writing via Adaptive Curriculum Reinforcement Learning

Xuanyu Lei, Chenliang Li Alibaba Group, Yuning Wu Alibaba Group, Kaiming Liu Tsinghua University, Tsinghua University, Weizhou Shen, Peng Li Tsinghua University, Ming Yan Alibaba Group, Fei Huang Alibaba Group US 等 10 位作者

原文摘要

Recent advances in Large Language Models (LLMs) have enabled strong performance in long-form writing, but current training paradigms remain limited: Supervised Fine-Tuning (SFT) remains constrained by data saturation and performance ceilings, while Reinforcement Learning with Verifiable Reward (RLVR), though successful in verifiable domains like math and code, cannot be directly migrated to open-ended long-form writing due to a lack of ground-truths. To further advance long-form writing, we present Writing-RL: an Adaptive Curriculum Reinforcement Learning framework to advance long-form writing capabilities beyond SFT. The framework consists of three key components: Margin-aware Data Selection strategy that prioritizes samples with high learning potential, Pairwise Comparison Reward mechanism that provides discriminative learning signals in the absence of verifiable rewards, and Dynamic Reference Scheduling approach, which plays a critical role by adaptively adjusting task difficulty based on evolving model performance. Experiments on 7B-scale writer models show that Writing-RL effectively improves long-form writing performance over strong SFT baselines. Furthermore, we observe that models trained with long-output RL generalize surprisingly well to long-input reasoning tasks, potentially offering a promising perspective for rethinking long-context training.

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.710ACL Anthology · ACL 2026

Act-Adaptive Margin: Dynamically Calibrating Reward Models for Subjective Ambiguity

Feiteng Fang, Dingwei Chen SUN YAT-SEN UNIVERSITY, Xiang Huang, Ting-En Lin, Yuchuan Wu Alibaba Group, Xiong Liu Alibaba Group, Jing Ye Institute of automation, Chinese academy of science, Chinese Academy of Sciences, Ziqiang Liu 等 13 位作者

原文摘要

Currently, most reinforcement learning tasks focus on domains like mathematics and programming, where verification is relatively straightforward. However, in subjective tasks such as role-playing, alignment techniques struggle to make progress, primarily because subjective reward modeling using the Bradley-Terry model faces significant challenges when dealing with ambiguous preferences. To improve reward modeling in subjective tasks, this paper proposes AAM (Act-Adaptive Margin), which enhances reward modeling by dynamically calibrating preference margins using the model’s internal parameter knowledge. We design two versions of AAM that efficiently generate contextually-appropriate preference gaps without additional human annotation. This approach fundamentally improves how reward models handle subjective rewards by better integrating generative understanding with preference scoring. To validate AAM’s effectiveness in subjective reward modeling, we conduct evaluations on RewardBench, JudgeBench, and challenging role-playing tasks. Results show that AAM significantly improves subjective reward modeling performance, enhancing Bradley-Terry reward models by 2.95% in general tasks and 4.85% in subjective role-playing tasks. Furthermore, reward models trained with AAM can help downstream alignment tasks achieve better results. Our test results show that applying rewards generated by AAM-Augmented RM to preference learning techniques (e.g., GRPO) achieves state-of-the-art results on CharacterEval and Charm. The code and dataset will be released upon acceptance.

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.759ACL Anthology · ACL 2026

Check Your Work: Structured Checklist Feedback for Improving Large Language Models

Jonathan Cook, Tim Rocktäschel, Jakob Nicolaus Foerster University of Oxford, University of Oxford, Dennis Aumiller Cohere, Alex Wang Cohere

原文摘要

Much recent progress in Large Language Model (LLM) performance has been driven by verifiable feedback in deterministic domains like mathematics and code. However, scaling reinforcement learning (RL) and test-time compute in domains for which strict verification is infeasible remains a challenge. A common approach is to use an LLM-as-judge, which often relies on opaque, monolithic scores. In this work, we propose that AI feedback is most effective when decomposed into granular, prompt-specific checklists. To transform these checklists into a scalar reward, we introduce DIVA: DIscriminative VAriance weighting, a dynamic aggregation scheme that prioritises checklist items based on their ability to distinguish quality across a candidate pool. This ensures the reward signal focuses on the most salient criteria for a given prompt and response group, rather than being diluted by trivial or redundant constraints. Our approach yields an 11.8% win-rate improvement on AlpacaEval 2.0 using Qwen3-8B, outperforming holistic reward models and existing checklist baselines. Beyond training, we show that these checklists serve as a structured policy improvement operator at inference time - by using the model’s own checklist evaluation as localised contextual feedback, the model can iteratively refine its output. This self-correction mechanism outperforms free-form sequential self-correction, offering a unified and interpretable framework for scaling both training-time and test-time performance in domains lacking strict verifiers.

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 #1CVF · CVPR 2026:cvf:60787a333d0973f82fb86486b1bfcab3CVF · CVPR 2026

WebGym: Scaling Training Environments for Long-Horizon Visual Web Agents with Realistic Tasks

Bai, Hao, Taymanov, Alexey, Zhang, Tong, Kumar, Aviral, Whitehead, Spencer

原文摘要

We present WebGym, the largest-to-date open-source environment for training realistic visual web agents. Real websites are non-stationary and diverse, making artificial or small-scale task sets insufficient for robust policy learning. WebGym contains nearly 300,000 tasks with rubric-based evaluations across diverse, real-world websites and difficulty levels. We train agents with a simple reinforcement learning (RL) recipe, which trains on the agent's own interaction traces (rollouts), using task rewards as feedback to guide learning. To enable scaling RL, we speed up sampling of trajectories in WebGym by developing a high-throughput asynchronous rollout system, designed specifically for web agents. Our system achieves a 4-5x rollout speedup compared to naive implementations. Second, we scale the task set breadth, depth, and size, which results in continued performance improvement. Fine-tuning a strong base vision-language model, Qwen-3-VL-8B-Instruct, on WebGym results in an improvement in success rate on an out-of-distribution test set from 26.2% to 42.9%, significantly outperforming agents based on proprietary models such as GPT-4o and GPT-5-Thinking that achieve 27.1% and 29.8%, respectively. This improvement is substantial because our test set consists only of tasks on websites never seen during training, unlike many other prior works on training visual web agents.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

版本更新 · v3arXiv:2412.06464Google Research

Gated Delta Networks: Improving Mamba2 with Delta Rule

Songlin Yang, Jan Kautz, Ali Hatamizadeh

原文摘要

Linear Transformers have gained attention as efficient alternatives to standard Transformers, but their performance in retrieval and long-context tasks has been limited. To address these limitations, recent work has explored two distinct mechanisms: gating for adaptive memory control and the delta update rule for precise memory modifications. We observe that these mechanisms are complementary: gating enables rapid memory erasure while the delta rule facilitates targeted updates. Building on this insight, we introduce the gated delta rule and develop a parallel training algorithm optimized for modern hardware. Our proposed architecture, Gated DeltaNet, consistently surpasses existing models like Mamba2 and DeltaNet across multiple benchmarks, including language modeling, common-sense reasoning, in-context retrieval, length extrapolation, and long-context understanding. We further enhance performance by developing hybrid architectures that combine Gated DeltaNet layers with sliding window attention or Mamba2 layers, achieving both improved training efficiency and superior task performance.

cs.CL · cs.LG