Modern scientific and machine-learning applications compose many independently developed libraries. When these libraries run together, their independently managed runtimes can oversubscribe shared resources: using the same CPU cores, fighting over GPUs, or contending for memory bandwidth. Avoiding such contention requires careful configuration across library boundaries. Existing autotuners do not directly investigate what resources are shared between libraries, which runtime signals correlate with interference. As a result, they are inefficient for finding optimal configurations to mitigate contention. This paper presents SysPilot, a cross-library performance autotuning system based on Library Performance Contract (LPC). A Library Performance Contract captures a library's resource demands, assumptions, controls, and observability signals in LPCL, a specification language for describing library resource requirements. SysPilot synthesizes contracts from documentation and code artifacts, composes contracts from the libraries used by an application, derives resource-conflict hypotheses, profiles the application to validate those hypotheses, and selects candidate configurations. This design makes the Library Performance Contract a reusable unit of performance knowledge: a contract for a library can be reused across many applications that depend on that library. We evaluate SysPilot on a benchmark suite of cross-library contention scenarios. The results show that SysPilot matches the performance of autotuners that rely on application-specific manual information while retaining cross-application reuse. Compared with general-purpose autotuners such as OpenTuner and SMAC3, SysPilot improves benchmark performance metrics by up to an additional 38% over the best configuration found by these autotuners, while using 3x fewer runs.
Zhiheng Li, Zongyang Ma, Jiaxian Chen, Cheng Cui, Yi Liu, Ziqi Zhang, Chunfeng Yuan, Bing Li 等 10 位作者
Optical Character Recognition (OCR) is among the oldest and most widely deployed applications of artificial intelligence. This survey reviews its development, focusing on the Foundation Model Era. We define OCR through faithful transcription: within a specified visual scope, OCR should completely reconstruct the text, notation, and document structure observable in the source image, and every textual, notational, or structural element in the output must be verifiable from visual evidence in that image. We trace the development from specialist OCR models toward unified models, examining joint text detection and recognition, structured sequence generation, and the use of pretrained vision-language models (VLMs). We organize contemporary OCR systems into five coexisting families: modular toolkits and task-specific models, specialized document VLMs, hybrid workflows, general-purpose VLMs, and commercial products and managed services. We compare their architectures, data, and training, examining hallucination and omission, insufficient spatial grounding, and inference cost in generative OCR. We review evaluation from character and scene text recognition to parsing individual structural elements and full-page transcription, highlighting gaps in consistent output definitions, attribution of performance to individual components, and coverage of real capture conditions and visible content and structure. Finally, we summarize the challenges facing OCR and discuss directions for future research. We continuously track related work at https://github.com/zhihengli-casia/Awesome-OCR-in-the-Foundation-Model-Era.
Video dubbing aims to synthesize lip movements that match target speech while preserving the speaker identity, head pose, and background of a source video. Existing editors are predominantly trained via self-reconstruction under original paired audio, even though the source mouth becomes a conflicting target when driving speech is replaced. We introduce replacement-aware cross-audio supervision: paired-audio samples use full-frame reconstruction, whereas unpaired replacement-audio samples mask out source-mouth reconstruction losses and supervise the mouth solely through audio-visual synchronization while preserving unmasked facial regions and background. Because offline dubbing provides the complete source video and target speech beforehand, we present VidDub, a full-context diffusion editor distilled into two denoising steps (2 NFE). Our replacement-aware teacher first learns accurate lip synchronization without regressing toward conflicting source mouth movements. Matched trajectory regression then transfers the teacher's CFG-guided trajectories to a two-step student, and distribution matching distillation recovers visual quality after step compression. We will release the curated training dataset, VidDub-Bench, fixed paired- and cross-audio evaluation manifests, preprocessing outputs, and unified evaluation code. Across three training seeds, masking out conflicting source-mouth reconstruction improves cross-audio Sync-C by 0.833; the final two-step model combines strong lip synchronization with superior visual quality, identity preservation, and visual speech recognition across four benchmarks.
Operational flood forecasting depends on tacit forecaster expertise that is difficult to formalize, audit, and transfer. Although artificial intelligence methods have advanced flood prediction and model-error correction, few studies explicitly represent the tacit expert rules, review checkpoints, and workflow constraints that connect model outputs to operational warning decisions. Here, we propose Community HydroAgent for Flood Forecasting (CHA-Flood), a skill-orchestrated agent framework that embeds Large Language Models (LLMs) into a model-driven flood forecasting workflow, where each skill encodes explicit rules to bound LLM reasoning. We validated its effectiveness using five state-of-the-art LLMs in the South Yamhill River basin (USA). Prior judgment captures observed peak flow and flood volume within 5% tolerance in 10 and 11 out of 14 events, and 5-fold cross-validation over 129 events yields Pearson correlations of 0.62 and 0.84. Building on a high-baseline scheme library (average KGE 0.890), the guided scheme selection further improves KGE by 0.023-0.154. All five tested LLMs successfully execute the CHA-Flood workflow with comparable judgment accuracy (each spanning 40%-80% across cross-validation folds) but with substantial cost differences. Removing only the language-model narrowing lowers median KGE from 0.723-0.753 to 0.662 for all five LLMs, indicating that the gain comes from LLM reasoning rather than from the choice of LLM. CHA-Flood does not aim to replace human forecasters; instead, it translates their tacit expertise into an auditable and reproducible workflow. This skill-orchestrated paradigm demonstrates how explicit rule boundaries can guide LLM reasoning to complement physically based simulation in next-generation flood forecasting.
Li Kong, Zilong Liu, Haoyang Zhou, Hanbing Liu, Qi Qi
Neural auction design has emerged as a powerful paradigm within automated mechanism design for modern Web platforms. Because these learned mechanisms directly dictate critical economic outcomes, their lack of internal transparency raises significant auditability and trust concerns. Opening this black box \textit{post-hoc} is therefore essential, yet presents two distinctive challenges: (1) activation contexts are dense, correlated numerical profiles devoid of explicit semantic structure, and (2) feature interpretations can only be falsifiably audited if they map to measurable auction states or outcomes. In this paper, we propose a post-hoc white-box auditing framework for unpacking trained neural auctions. Using CITransNet as a representative testbed, we first employ sparse autoencoders to decompose hidden representations while faithfully preserving downstream auction behavior. Anchoring feature interpretations to native economic targets, we validate them through activation prediction and causal interventions to isolate verified features from the reconstruction dictionary. Finally, applying this pipeline across varied auction settings, we show that the verified features can serve as analytical instruments to examine how internal representations modulate strategic misreporting incentives, align with Myerson's optimal auction, and support the diagnosis of individual auctions. Our work highlights the potential of white-box mechanism auditing to build the foundational trust necessary for neural auctions to be deployed as widely adopted Web technologies. To enhance research transparency and facilitate independent inspection, we publicly release the experimental results supporting our findings at https://github.com/Li-Beverly-Kong/opening-neural-auctions.git
We present Youtu-Parsing-Omni, an omni-modal parser that converts documents, images, audio, and video into structured records grounded in space and time, providing a perception layer for agents that read, locate, and cite evidence across modalities. Its design rests on one encoder for every modality and one schema for every task. Youtu-Omni-Encoder, initialized from a pre-trained language model to strengthen text reading, encodes all modalities with shared weights in a unified space-time coordinate system, and a few fusion layers let video frames attend to concurrent audio, bringing cross-modal fusion and temporal alignment into perception itself. OmniSchema unifies the outputs of all ten parsing tasks, allowing a single self-evolving post-training procedure, OmniSchema-Aware On-Policy Distillation (OSAD), to provide a shared token-role-based objective across tasks. In each round, the model is trained on its own rollouts against token-level targets from a reference-conditioned copy of itself, which is then refreshed with the trained weights, so that the parser and its supervision co-evolve. With a single 5 B-parameter checkpoint, Youtu-Parsing-Omni achieves state-of-the-art performance on OmniDocBench v1.6 (96.96 Overall) and leads all open-weight models on OmniParsingBench (75.08 Avg.), with its advantage concentrated on audio and video. It also achieves the best overall chart-parsing score (95.02) and the highest exact chemical-fingerprint agreement among compared systems, and matches a dedicated optical-music model in character-level transcription of typeset sheet music while staying far ahead of general-purpose systems. Code and model weights are publicly available.
Rotary Position Embedding (RoPE) typically uses uniform coverage across Transformer layers despite heterogeneous positional requirements. Phase-off interventions reveal non-uniform, model-specific rotary-phase dependence, while coverage interventions relate it to coverage-upgrade benefits. We propose profiling-guided layer-wise RoPE allocation, assigning high/low coverage under a fixed budget using early coverage-benefit profiles. The framework supports fixed-width query/key representations and physical rotary-dimension allocation in Multi-head Latent Attention (MLA). Normalized-depth mapping transfers profiles within model families, enabling small-model measurements to guide larger-model allocations before pretraining. A brief analysis relates selection and transfer to score calibration and inter-layer interactions. From-scratch experiments demonstrate validation-loss improvements over available budget-matched baselines, while analytical resource accounting identifies favorable quality--storage--compute trade-offs for physical MLA. These results connect positional demand to transferable, efficient architecture design.
Recursive self-improvement requires models not only to acquire useful training experience, but also to decide when their current experience has ceased to be useful. Existing methods often focus on what experience to generate next, while paying less attention to when fresh experience should be introduced. Many also construct training targets through self-consistency or majority voting, making supervision depend on the model's own uncertain predictions. We address these two questions separately: training dynamics determine when to acquire new experience, while the answers to new tasks remain independently checkable. A-RSI monitors reward variation and accuracy in training logs to refresh a task pool when its learning signal declines, without consulting validation or test scores. A static library of model-authored programs produces multimodal questions and derives their reference answers; we specify the task-generation contract, automatically verify chosen properties of the reward and refresh rules, and separately audit the generated answers. The training loop uses no external training examples or human-written answer labels. On the primary eleven-benchmark suite, A-RSI raises the performance average from 57.77 to 61.05 with 800 fresh tasks.
Network slicing is a key enabler for the coexistence of ultra-reliable low-latency communications (URLLC) and enhanced mobile broadband (eMBB) in 5G networks. However, allocating limited radio resources to heterogeneous slices while satisfying stringent quality-of-service (QoS) requirements remains challenging, particularly in the ultra-reliable regime where conventional effective-capacity-based approaches may lead to excessive resource allocation. To address this issue, this paper proposes a martingale-based resource block (RB) allocation framework for coexisting URLLC and eMBB slices. By constructing exponential martingale processes using the moment generating functions (MGFs) of the arrival and service processes and applying Doob's maximal inequality, explicit non-asymptotic upper bounds are derived for the URLLC delay violation probability and the eMBB backlog violation probability. Based on the resulting theoretical stability conditions, a low-complexity bisection algorithm is developed to determine the optimal martingale parameters, followed by a deterministic search algorithm to obtain the minimum RB requirements for both slices. Numerical results show that the analytical bounds effectively upper-bound the Monte Carlo simulation results. At a target violation probability of $10^{-6}$ for each slice, the proposed framework requires 44 RBs in total, satisfying the system capacity constraint of 50 RBs. Compared with the conventional effective-capacity baseline requiring 64 RBs, the proposed framework reduces total RB consumption by approximately 31.2% relative to the conventional effective-capacity baseline.
General-purpose embodied intelligence requires robots to coordinate diverse skills over long horizons, track task progress, and recover from failures. Specialist policies alone do not ensure task-level reliability, while powerful multimodal agents rely on costly reasoning and external experience that compact models struggle to reproduce. We introduce OmniBrain-0, a lightweight unified embodied agent that coordinates manipulation and navigation through a shared high-level decision model, integrating task understanding, planning, progress tracking, and feedback-driven recovery. Our progressive training framework combines embodied pretraining, domain-specialized agent distillation, and multi-teacher on-policy distillation (MOPD). It distills powerful teachers' interaction experience into manipulation and navigation experts, then consolidates their decision capabilities into OmniBrain-0. Unification therefore occurs within the learned decision model rather than only at the tool interface. We further introduce Rubric-Guided Recursive Self-Improvement (RSI), a data flywheel in which a Meta-Agent turns execution evidence into refined rubrics, step-level reminders, and verified trajectories for domain-expert updates before their reconsolidation into OmniBrain-0 through MOPD. We evaluate OmniBrain-0 on LIBERO-Pro, LIBERO-Plus, RoboCasa365, RoboTwin 2.0, and R2R-CE Val-Unseen, as well as multiple real-world manipulation tasks. OmniBrain-0 combines strong cross-domain task performance with substantially lower inference and execution overhead than its closed-source teacher, demonstrating efficient transfer and consolidation of embodied capabilities into a compact unified agent.
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.
World models are emerging as a fundamental component of policy learning for real-world agents, enabling agents to predict future world states and plan actions within a learned representation of the dynamic environment. Existing approaches, however, often model appearance, metric geometry represented by projected LiDAR depth, and ego motion either partially or independently, overlooking the fact that these modalities are different projections of a shared underlying world state. This separation can lead to information loss and cross-modal inconsistency, ultimately limiting downstream performance. Motivated by this unified view of the world, we propose DriveUniTok, a unified multimodal tokenizer for driving world-action models (WAMs) that encodes these modalities in a single decodable continuous latent. We freeze DriveUniTok and adapt a pretrained diffusion model, DriveUniWAM, to predict future unified latents; the tokenizer then decodes them into future appearance, projected LiDAR depth, and ego trajectories. Experiments on NAVSIM demonstrate that our unified design achieves better future prediction and planning performance at lower downstream computational cost than separate-stream alternatives. With reinforcement learning post-training, DriveUniWAM achieves a PDMS of 91.54, reaching state-of-the-art performance among the evaluated WAM-based planners.
Fengchong Yao, Jianbing Li, Qing Liu, Qikun Liu, Kefeng Song, Haitao Li, Song Wang
Radio frequency fingerprint identification (RFFI) exploits transmitter-specific hardware imperfections as physicallayer identity cues for Internet of Things (IoT) devices, but deep models often degrade across acquisition environments. In multi-antenna reception, antenna topology and frequencyoffset dynamics structure receiver observations, while capturedependent variation distorts target embeddings and misaligns source-trained decision boundaries. This article proposes physicsinformed structure anchoring with capture-aware prototype calibration (PISA-CAPC) to address both representation and decision mismatches. The two stages separate source representation construction from target decision correction. During source training, PISA organizes antenna tokens through a topology-guided graph, conditions propagation on CFO-derived acquisition dynamics, and applies bounded contextual residual suppression to preserve identity evidence. At deployment, unlabeled capture-aware prototype calibration (U-CAPC) estimates capture-local prototypes and recalibrates target decision scores while keeping the representation and source classifier fixed. Thus, calibration uses neither target labels nor target-domain backbone updates. On a measured WiFi benchmark with four receive antennas and ten transmitters, PISA-CAPC achieves a mean target-domain Macro-F1 of 0.9257 under a balanced transductive setting. Component ablations support complementary roles for topology-guided anchoring, CFO-conditioned modulation, reliability-aware token aggregation, contextual suppression, and capture-aware calibration. These results indicate that physically motivated representation learning can be combined with labelfree decision calibration to improve cross-environment RFFI under the evaluated protocol without changing the deployed backbone.
Mingzhe Lu, Yiwen Wang, Yanbing Liu Institute of Information Engineering，Chinese Academy of Sciences, Qi You, Chong Liu University of Science and Technology of China, Ruize Qin, Haoyu Dong, Wenyu Zhang Baidu 等 11 位作者
Computational narrative analysis aims to capture rhythm, tension, and emotional dynamics in literary texts. Existing large language models can generate long stories but overly focus on causal coherence, neglecting the complex story arcs and orchestration inherent in human narratives. This suggests a structural misalignment between model- and human-generated narratives.We therefore position narrative analysis as a diagnostic proxy for generation and propose VISTA Space, a high-dimensional framework for narrative orchestration that unifies human and model perspectives while jointly characterizing narrative function and structure in a common space.We further introduce LitVISTA, a structurally annotated benchmark grounded in literary texts, which operationalizes VISTA Space for systematic evaluation of models’ narrative orchestration capabilities. Under an oracle setting with gold event anchors, we evaluate frontier LLMs including GPT, Claude, Grok, and Gemini. Results reveal systematic deficiencies, as current models struggle to jointly capture narrative function and structure and fail to form an integrated global view of literary narrative orchestration. End-to-end analysis further shows that failures are dominated by anchor identification and localization errors. Even advanced thinking modes yield mixed and often limited gains for literary narrative understanding.
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
Zhiyu Shen, Ziming Wu, Fuming Lai, Shaobing Lian, Yanghui Rao SUN YAT-SEN UNIVERSITY
Maintaining consistency in long-term dialogues remains a fundamental challenge for LLMs, as standard retrieval mechanisms often fail to capture the temporal evolution of historical states. While memory-augmented frameworks offer a structured alternative, current systems rely on static prompting of closed-source models or suffer from ineffective training paradigms with sparse rewards. We introduce MemBuilder, a reinforcement learning framework that trains models to orchestrate multi-dimensional memory construction with attributed dense rewards. MemBuilder addresses two key challenges: (1) Sparse Trajectory-Level Rewards: we employ synthetic session-level question generation to provide dense intermediate rewards across extended trajectories; and (2) Multi-Dimensional Memory Attribution: we introduce contribution-aware gradient weighting that scales policy updates based on each component’s downstream impact. Experimental results show that MemBuilder enables a 4B-parameter model to outperform state-of-the-art closed-source baselines, exhibiting strong generalization across long-term dialogue benchmarks.
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
Advait Gosai Scale AI, Tyler Vuong Scale AI, Utkarsh Tyagi Scale AI, Steven Li Scale AI, Wenjia You OpenAI, Miheer Bavare Scale AI, Arda Uçar Anadolu University, Zhongwang Fang Scale AI 等 11 位作者
End-to-end (E2E) spoken dialogue systems are replacing cascaded pipelines for voice-based human-AI interaction. Existing benchmarks primarily evaluate these systems on synthetic speech and single-turn tasks, leaving multi-turn conversational ability underexplored. We introduce Audio MultiChallenge an open-source benchmark to evaluate these systems under natural multi-turn interaction patterns. Building on the text-based MultiChallenge framework, which evaluates Inference Memory, Instruction Retention, and Self Coherence, we introduce a new axis Voice Editing that tests robustness to mid-utterance speech repairs and backtracking. We augment each axis to the audio modality, such as introducing Audio-Cue challenges for Inference Memory that require recalling ambient sounds and paralinguistic signals beyond semantic content. We curate 452 conversations from 47 speakers with 1,712 instance-specific rubrics through a hybrid pipeline that exposes model failures at scale while preserving natural disfluencies found in unscripted human speech. Our evaluation reveals that even frontier models struggle on our benchmark, with our highest-performing model achieving a 54.65% pass rate. Error analysis shows that models are not sufficiently robust to human speech when tracking instructions, edits, and audio cues, highlighting the need for improved audio-native multi-turn interaction capabilities.
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
Bowei Zhang, Hanbing Liu, Qixin Tian, Siyu Chen, Ziyuan Wang, Qi Qi Renmin University of China
Smart Contracts are the foundation of Decentralized Finance (DeFi), executing financial logic without trusted intermediaries. Recent advances in large language models (LLMs) have substantially lowered the barrier to smart contract development by enabling code generation from natural language. However, because smart contracts are immutable and directly manage financial assets, this accessibility introduces a critical trust gap: generated contracts are easy to produce but hard to trust. To bridge this gap, we present LeVer, the first trustworthy smart contract synthesis framework that integrates LLM-based generation with Lean-based auto-formalization and Verification. LeVer employs a closed-loop multi-agent architecture to iteratively generate, verify, attack, and repair contracts, providing both formal guarantees and empirical robustness. To facilitate the adoption of automated formal verification in smart contract generation and audition, we open-source our framework and datasets at: https://github.com/gl-bowei/LeVer
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
Frontier model progress is often measured using academic benchmarks that provide a limited view of performance on open-ended, economically consequential tasks in high-stakes professional domains where practical returns matter most. We introduce Professional Reasoning Bench (PRBench), a realistic, open-ended, and difficult benchmark of real-world problems in Finance and Law. We open-source its 1,100 expert-authored tasks and 19,356 expert-curated criteria, making it the largest public, rubric-based benchmark for both legal and finance domains. We recruit 182 qualified professionals, holding JDs, CFAs, or 6+ years of experience, who contributed questions inspired by their actual workflows. This process yields significant diversity, with tasks spanning 114 countries and 47 US jurisdictions. Our expert-curated rubrics are validated through a rigorous quality pipeline, including independent expert validation. Subsequent evaluation of 20 leading models reveals substantial room for improvement, with top scores of only 0.39 (Finance) and 0.37 (Legal) on our Hard subsets. We further catalog associated economic impacts of the prompts and analyze performance using human-annotated rubric categories. Common failure modes include inaccurate judgments, a lack of process transparency and incomplete reasoning, highlighting critical gaps in their reliability for professional adoption.
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
Diandian Guo Institute of Information Engineering, Chinese Academy of Sciences, Cong Cao Institute of Information Engineering，Chinese Academy of Sciences, Fangfang Yuan Institute of Information Engineering, Chinese Academy of Sciences, Pin Xu University of the Chinese Academy of Sciences and Institute of Information Engineering, Chinese Academy of Sciences, Cheng Hu, Zhicheng Zhang University of the Chinese Academy of Sciences and Institute of Information Engineering, Chinese Academy Of Sciences, Yu Liu Institute of Information Engineering, Chinese Academy of Sciences, Yanbing Liu Institute of Information Engineering，Chinese Academy of Sciences
Multimodal Sarcasm Understanding (MSU) comprises multiple subtasks, demanding both incongruity perception and intent reasoning. However, this progress is impeded by two bottlenecks. First, the lack of a unified benchmark for holistic satirical cognition hinders comprehensive evaluation of MSU. Second, jointly modeling these heterogeneous subtasks often leads to feature entanglement. Specifically, while subtasks share a dependence on incongruity, they diverge in granular focus, causing specific execution patterns to erode the fundamental perception capability. To address these challenges, we make two contributions. First, we introduce DocMSU-PLUS, a comprehensive benchmark covering five cognitive dimensions of MSU. All tasks are reformulated into multiple-choice questions (MCQs), enabling a unified accuracy-based evaluation. Second, we propose the Dual Orthogonal Stream Experts (DOSE) framework. DOSE structurally decouples experts into orthogonal shared perception and private execution streams to physically block gradient interference between tasks. Experiments demonstrate that DOSE achieves superior performance on DocMSU-PLUS, effectively balancing general perception with task-specific adaptation.
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
Congren Dai, Yue Yang, Krinos Li, Huichi Zhou University College London, University of London, Shijie Liang, Bo Zhang, Enyang Liu, Ge Jin 等 15 位作者
Understanding complete musical scores entails integrated reasoning over pitch, rhythm, harmony, and large-scale structure, yet the ability of Large Language Models and Vision–Language Models to interpret full musical notation remains insufficiently examined.We introduce Musical Score Understanding Benchmark (MSU-Bench), a human-curated benchmark for score-level musical understanding across textual (ABC notation) and visual (PDF) modalities. MSU-Bench contains 1,800 generative question–answer pairs from works by Bach, Beethoven, Chopin, Debussy, and others, organised into four levels of increasing difficulty, ranging from onset information to texture and form. Evaluations of more than fifteen state-of-the-art models, in both zero-shot and fine-tuned settings, reveal pronounced modality gaps, unstable level-wise performance, and challenges in maintaining multilevel correctness. Fine-tuning substantially improves results across modalities while preserving general knowledge, positioning MSU-Bench as a robust foundation for future research in multimodal reasoning. The benchmark and code are available at https://github.com/Congren-Dai/MSU-Bench.
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
Mohit Raghavendra, Anisha Gunjal Scale AI, Bing Liu Scale AI, Yunzhong He Scale AI
Verification is critical for improving agents: it provides the reward signal for Reinforcement Learning and enables inference-time gains through Test-Time Scaling (TTS). Despite its importance, verification in software engineering (SWE) agent settings often relies on code execution, which can be difficult to scale due to environment setup overhead. Scalable alternatives such as patch classifiers and heuristic methods exist, but they are less grounded in codebase context and harder to interpret. To this end, we explore Agentic Rubrics: an expert agent interacts with the repository to create a context-grounded rubric checklist, and candidate patches are then scored against it without requiring test execution. On SWE-Bench Verified under parallel TTS evaluation, Agentic Rubrics achieve a score of 54.2% on Qwen3-Coder-30B-A3B and 40.6% on Qwen3-32B, with at least a +3.5 percentage-point gain over the strongest baseline in our comparison set. We further analyze rubric behavior, showing that rubric scores are consistent with ground-truth tests while also flagging issues that tests do not capture. Our ablations show that agentic context gathering is essential for producing codebase-specific, unambiguous criteria. Together, these results suggest that Agentic Rubrics provide an efficient, scalable, and granular verification signal for SWE agents.
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
Hanbing Liu, Lang Cao University of Illinois at Urbana-Champaign, Yuanyi Ren, Mengyu Zhou Alibaba Group, Haoyu Dong, Xiaojun Ma Microsoft, Shi Han Microsoft, Dongmei Zhang Microsoft
Large language models (LLMs) show strong reasoning abilities but often produce unnecessarily long explanations that reduce efficiency. Although reinforcement learning (RL) has been used to improve reasoning, most methods focus on accuracy and rely on uniform length-based rewards that overlook the differing contributions of individual tokens, often harming correctness. We revisit length optimization in RL through the perspective of token significance. Observing that many chain-of-thought (CoT) tokens contribute little to the final answer, we introduce a significance-aware length reward that selectively penalizes insignificance tokens, reducing redundancy while preserving essential reasoning. We also propose a dynamic length reward that encourages more detailed reasoning early in training and gradually shifts toward conciseness as learning progresses. Integrating these components into standard policy optimization yields a framework that improves both reasoning efficiency and accuracy. Experiments across multiple benchmarks demonstrate substantial reductions in response length while preserving or improving correctness, highlighting the importance of modeling token significance for efficient LLM reasoning.
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
Yunyao Zhang, Xinglang Zhang, Junxi Sheng, Wenbing Li, Junqing Yu Huazhong University of Science and Technology, Yi-Ping Phoebe Chen La Trobe University, Wei Yang Huazhong University of Science and Technology, Zikai Song
Logical reasoning is a fundamental capability of large language models (LLMs). However, existing studies largely overlook the interplay between logical complexity and semantic complexity, limiting their robustness under abstract propositions, ambiguous contexts, and conflicting stances, which are central to human reasoning. We propose LogicAgent, a semiotic-square–guided framework that jointly addresses these two axes of difficulty. The semiotic square provides a principled structure for multi-perspective semantic analysis, and LogicAgent integrates automated deduction with reflective verification to manage logical complexity across deeper reasoning chains. To evaluate reasoning under coupled semantic and logical complexity, we introduce RepublicQA, a benchmark that contains abstract propositions with systematically constructed contrary and contradictory forms, providing a semantically rich setting for assessing logical reasoning in LLMs. Experiments show that LogicAgent achieves state-of-the-art performance on RepublicQA with a 6.25% average gain, and generalizes well to four mainstream logical reasoning benchmarks with an additional 7.05% improvement, highlighting the effectiveness of our semiotic-grounded multi-perspective reasoning in boosting LLMs’ logical performance.
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