Computation and Language

Papers filed under cs.CL on arXiv, each one already summarized by Paperlayer. Open any of them to read the summary beside the original PDF, with every point linked to the line, figure, or table it came from.

Search paper metadata (including unsummarized papers)

16,681 to 16,740 of 18,978

LëtzCross: A Cross-Lingual Page-Level Benchmark for Multimodal Retrieval over Luxembourgish Documents
Omar El Bachyr, Fred Philippy, Laura Maria Bernardy +3
cs.CLarXiv:2608.21714v12026
SkillNet: Create, Evaluate, and Connect AI Skills
Yuan Liang, Ruobin Zhong, Haoming Xu +47
cs.AIcs.CLcs.CVarXiv:2603.04448v22026
Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs
Haiquan Lu, Zigeng Chen, Gongfan Fang +2
cs.CLarXiv:2605.20315v12026
VoiceChat-TTS: A Low-Latency Continuous Speech Synthesis Model for Interactive Agents
Edresson Casanova, Jaehyeon Kim, Mariana Graterol Fuenmayor +17
eess.AScs.CLarXiv:2608.13831v12026
GigaAM Multilingual: Foundation Model for Underrepresented Languages
Andrei Kuzmenko, Alexandr Maximenko, Aleksandr Kutsakov +5
eess.AScs.CLarXiv:2607.10371v12026
Learn-by-Wire Training Control Governance: Bounded Autonomous Training Under Stress for Stability and Efficiency
Anis Radianis
cs.AIcs.CLcs.LGarXiv:2605.19008v12026
Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models
Dehai Min, Giovanni Vaccarino, Huiyi Chen +3
cs.CLarXiv:2605.17672v12026
Teaching Nemotron Greek: Mining a Corpus, Adapting Retrieval, and Grounding Generation for Modern Greek across Specialist Domains
Ayoub Kirouane, Christos Petrocheilos
eess.AScs.AIcs.CLarXiv:2608.05138v12026
Knowing When to Quit: Diagnosing and Training LLMs to Abort Futile Reasoning
Xinyan Guan, Jiali Zeng, Chunlei Xin +5
cs.CLarXiv:2607.29211v12026
From Skill Text to Skill Structure: The Scheduling-Structural-Logical Representation for Agent Skills
Qiliang Liang, Hansi Wang, Zhong Liang +1
cs.CLcs.AIarXiv:2604.24026v42026
The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation
Tianyi Men, Zhuoran Jin, Kang Liu +1
cs.CLcs.AIcs.LGarXiv:2607.24720v12026
Latent Preference Modeling for Cross-Session Personalized Tool Calling
Yejin Yoon, Minseo Kim, Taeuk Kim
cs.CLcs.AIarXiv:2604.17886v12026
Efficient INT8 Inference of Small NLP Models on Server CPUs with PyTorch Native Stack
Weiwen Xia, Yuxin Cui, E Cao
cs.CLarXiv:2608.18182v12026
Library Drift: Diagnosing and Fixing a Silent Failure Mode in Self-Evolving LLM Skill Libraries
Xing Zhang, Yanwei Cui, Guanghui Wang +4
cs.AIcs.CLcs.SEarXiv:2605.19576v32026
AgentDebugX: An Open-Source Toolkit for Failure Observability, Attribution, and Recovery in LLM Agents
Kunlun Zhu, Xuyan Ye, Zhiguang Han +9
cs.AIcs.CLarXiv:2607.18754v12026
Emotion Across Speech and Faces: Shared Affective Mechanisms in Multimodal Foundation Models
Xiutian Zhao, Luqi Sun, Björn Schuller +1
cs.CLeess.ASeess.IVarXiv:2608.17102v12026
Probing Outcome-Level Resemblance and Mechanism-Level Alignment in LLM Risk Decisions: Evidence from the St. Petersburg Game
Chensong Huang, Changyu Chen, Chenwei Lin +3
cs.CLcs.CYecon.GNarXiv:2606.04978v12026
Margin-Regularized Structured Semantic Alignment for Brain-Language Correspondence
Jiaqi Wang, Huawen Hu, Shu Zhang
cs.CLcs.LGarXiv:2608.16975v12026
The TTS-STT Flywheel: Synthetic Entity-Dense Audio Closes the Indic ASR Gap Where Commercial and Open-Source Systems Fail
Venkata Pushpak Teja Menta
cs.CLcs.SDarXiv:2605.03073v12026
Off-the-Shelf LLMs as Process Scorers: Training-Free Alternative to PRMs for Mathematical Reasoning
Atoosa Chegini, Soheil Feizi
cs.CLcs.AIcs.LGarXiv:2606.01682v12026
iOSWorld: A Benchmark for Personally Intelligent Phone Agents
Lawrence Keunho Jang, Mareks Woodside, Geronimo Carom +3
cs.LGcs.CLarXiv:2606.09764v12026
OmegaUse-OfficeVal: Benchmarking LLM Agents on Long-Horizon Office-Suite Tasks with Economic Grounding
Jingbo Zhou, Yusai Zhao, Qi Bao +12
cs.AIcs.CLcs.HCarXiv:2607.27155v12026
SimulU: Training-free Policy for Long-form Simultaneous Speech-to-Speech Translation
Amirbek Djanibekov, Luisa Bentivogli, Matteo Negri +1
eess.AScs.AIcs.CLarXiv:2603.16924v12026
ROSD: Reflective On-Policy Self-Distillation for Language Model Reasoning across Domains
Ziqi Zhao, Xinyu Ma, Liu Yang +6
cs.CLcs.LGarXiv:2605.28014v12026
A Survey on Long-Term Memory Security in LLM Agents: Attacks, Defenses, and Governance Across the Memory Lifecycle
Zehao Lin, Xixuan Hao, Renyu Fu +5
cs.CRcs.AIcs.CLarXiv:2604.16548v22026
Can Multimodal Large Language Models Understand OCT?
Baochen Fu, Wenzhi Deng, Baihao Jin +5
cs.CVcs.CLarXiv:2607.16609v12026
FullStack-Agent: Enhancing Agentic Full-Stack Web Coding via Development-Oriented Testing and Repository Back-Translation
Zimu Lu, Houxing Ren, Yunqiao Yang +4
cs.SEcs.CLcs.CVarXiv:2602.03798v12026
A Declarative-Procedural Perspective on Expert Routing in Bilingual Mixture-of-Experts Language Models
Amrit Gopinath, Raghul, Durairaj Thenmozhi
cs.CLarXiv:2608.15102v12026
LLMEval-Logic: A Solver-Verified Chinese Benchmark for Logical Reasoning of LLMs with Adversarial Hardening
Ming Zhang, Qiyuan Peng, Yinxi Wei +13
cs.CLarXiv:2605.19597v12026
PatRe: A Full-Stage Office Action and Rebuttal Generation Benchmark for Patent Examination
Qiyao Wang, Xinyi Chen, Longze Chen +4
cs.CLcs.AIarXiv:2605.03571v12026
FINESSE-Bench: A Hierarchical Benchmark Suite for Financial Domain Knowledge and Technical Analysis in Large Language Models
Dmitry Stanishevskii, Nini Kamkia, Alexey Khoroshilov +4
cs.CLarXiv:2605.15482v22026
LongTraceRL: Learning Long-Context Reasoning from Search Agent Trajectories with Rubric Rewards
Nianyi Lin, Jiajie Zhang, Lei Hou +1
cs.CLcs.AIcs.LGarXiv:2605.31584v12026
Recursive Think-Answer Process for LLMs and VLMs
Byung-Kwan Lee, Youngchae Chee, Yong Man Ro
cs.CLarXiv:2603.02099v22026
Discovering Hidden Gems in Model Repositories
Jonathan Kahana, Eliahu Horwitz, Yedid Hoshen
cs.LGcs.CLarXiv:2601.22157v12026
Humans and LLMs Diverge on Probabilistic Inferences
Gaurav Kamath, Sreenath Madathil, Sebastian Schuster +2
cs.CLcs.AIarXiv:2602.23546v12026
Stable Miscalibration in Large Language Models: A Practical View of High-Confidence Errors
Akira Okutomi
cs.AIcs.CLarXiv:2608.13591v12026
Not All Tokens Are Equal: Inflation-Aware Routing for Agentic LLM Systems
Heming Fu, Shan Lin, Qianqian Xie +1
cs.CLcs.AIarXiv:2608.13571v12026
Mela: Test-Time Memory Consolidation based on Transformation Hypothesis
Lungchuan Chen
cs.CLarXiv:2605.10537v12026
CopT: Contrastive On-Policy Thinking with Continuous Spaces for General and Agentic Reasoning
Dachuan Shi, Hanlin Zhu, Xiangchi Yuan +4
cs.CLcs.AIarXiv:2605.20075v12026
AdaReasoner: Dynamic Tool Orchestration for Iterative Visual Reasoning
Mingyang Song, Haoyu Sun, Jiawei Gu +4
cs.AIcs.CLcs.CVarXiv:2601.18631v22026
CompactAttention: Accelerating Chunked Prefill with Block-Union KV Selection
Jiwon Song, Dongwon Jo, Beomseok Kang +1
cs.CLarXiv:2605.16839v12026
Efficient Reasoning with Balanced Thinking
Yulin Li, Tengyao Tu, Li Ding +5
cs.AIcs.CLcs.LGarXiv:2603.12372v32026
MAS-Orchestra: Understanding and Improving Multi-Agent Reasoning Through Holistic Orchestration and Controlled Benchmarks
Zixuan Ke, Yifei Ming, Austin Xu +7
cs.AIcs.CLcs.MAarXiv:2601.14652v52026
PRiSM: Benchmarking Phone Realization in Speech Models
Shikhar Bharadwaj, Chin-Jou Li, Yoonjae Kim +13
cs.CLcs.SDarXiv:2601.14046v22026
Meta-Reinforcement Learning with Self-Reflection for Agentic Search
Teng Xiao, Yige Yuan, Hamish Ivison +6
cs.LGcs.CLarXiv:2603.11327v22026
DocAtlas: Multilingual Document Understanding Across 80+ Languages
Ahmed Heakl, Youssef Mohamed, Abdullah Sohail +6
cs.CLcs.CVcs.LGarXiv:2605.12623v22026
SoCRATES: Towards Reliable Automated Evaluation of Proactive LLM Mediation across Domains and Socio-cognitive Variations
Taewon Yun, Hyeonseong Park, Jeonghwan Choi +3
cs.AIcs.CLarXiv:2606.05563v12026
ScheMatiQ: From Research Question to Structured Data through Interactive Schema Discovery
Shahar Levy, Eliya Habba, Reshef Mintz +3
cs.CLarXiv:2604.09237v22026
How do LLMs Compute Verbal Confidence
Dharshan Kumaran, Arthur Conmy, Federico Barbero +3
cs.CLcs.AIcs.LGarXiv:2603.17839v32026
IQuest-Coder-V1 Technical Report
Jian Yang, Wei Zhang, Shawn Guo +35
cs.AIcs.CLcs.SEarXiv:2603.16733v12026
MARS: Enabling Autoregressive Models Multi-Token Generation
Ziqi Jin, Lei Wang, Ziwei Luo +1
cs.CLarXiv:2604.07023v12026
Watch Before You Answer: Learning from Visually Grounded Post-Training
Yuxuan Zhang, EunJeong Hwang, Huaisong Zhang +8
cs.CVcs.AIcs.CLarXiv:2604.05117v12026
dVoting: Fast Voting for dLLMs
Sicheng Feng, Zigeng Chen, Xinyin Ma +2
cs.CLcs.AIarXiv:2602.12153v12026
From Prompt Injection to Persistent Control: Defending Agentic Harness Against Trojan Backdoors
Jiejun Tan, Zhicheng Dou, Xinyu Yang +4
cs.CRcs.AIcs.CLarXiv:2605.31042v12026
O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning
Mei Yuan, Qi Long, Qifeng Wu +5
cs.CVcs.AIcs.CLarXiv:2607.18142v12026
Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift
Zitong Huang, Gustavo Lucas Carvalho, Deqing Fu +1
cs.CLcs.LGarXiv:2607.17524v12026
World Action Models: The Next Frontier in Embodied AI
Siyin Wang, Junhao Shi, Zhaoyang Fu +11
cs.ROcs.CLcs.CVarXiv:2605.12090v12026
Do What I Say: A Spoken Prompt Dataset for Instruction-Following
Maike Züfle, Sara Papi, Fabian Retkowski +5
cs.CLarXiv:2603.09881v22026
FocuSFT: Bilevel Optimization for Dilution-Aware Long-Context Fine-Tuning
Zehua Pei, Hui-Ling Zhen, Xianzhi Yu +3
cs.CLarXiv:2605.09932v12026
InfiniteWeb: Scalable Web Environment Synthesis for GUI Agent Training
Ziyun Zhang, Zezhou Wang, Xiaoyi Zhang +4
cs.CLcs.AIcs.CVarXiv:2601.04126v32026

Computation and Language

LëtzCross: A Cross-Lingual Page-Level Benchmark for Multimodal Retrieval over Luxembourgish Documents

SkillNet: Create, Evaluate, and Connect AI Skills

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs

VoiceChat-TTS: A Low-Latency Continuous Speech Synthesis Model for Interactive Agents

GigaAM Multilingual: Foundation Model for Underrepresented Languages

Learn-by-Wire Training Control Governance: Bounded Autonomous Training Under Stress for Stability and Efficiency

Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models

Teaching Nemotron Greek: Mining a Corpus, Adapting Retrieval, and Grounding Generation for Modern Greek across Specialist Domains

Knowing When to Quit: Diagnosing and Training LLMs to Abort Futile Reasoning

From Skill Text to Skill Structure: The Scheduling-Structural-Logical Representation for Agent Skills

The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation

Latent Preference Modeling for Cross-Session Personalized Tool Calling

Efficient INT8 Inference of Small NLP Models on Server CPUs with PyTorch Native Stack

Library Drift: Diagnosing and Fixing a Silent Failure Mode in Self-Evolving LLM Skill Libraries

AgentDebugX: An Open-Source Toolkit for Failure Observability, Attribution, and Recovery in LLM Agents

Emotion Across Speech and Faces: Shared Affective Mechanisms in Multimodal Foundation Models

Probing Outcome-Level Resemblance and Mechanism-Level Alignment in LLM Risk Decisions: Evidence from the St. Petersburg Game

Margin-Regularized Structured Semantic Alignment for Brain-Language Correspondence

The TTS-STT Flywheel: Synthetic Entity-Dense Audio Closes the Indic ASR Gap Where Commercial and Open-Source Systems Fail

Off-the-Shelf LLMs as Process Scorers: Training-Free Alternative to PRMs for Mathematical Reasoning

iOSWorld: A Benchmark for Personally Intelligent Phone Agents

OmegaUse-OfficeVal: Benchmarking LLM Agents on Long-Horizon Office-Suite Tasks with Economic Grounding

SimulU: Training-free Policy for Long-form Simultaneous Speech-to-Speech Translation

ROSD: Reflective On-Policy Self-Distillation for Language Model Reasoning across Domains

A Survey on Long-Term Memory Security in LLM Agents: Attacks, Defenses, and Governance Across the Memory Lifecycle

Can Multimodal Large Language Models Understand OCT?

FullStack-Agent: Enhancing Agentic Full-Stack Web Coding via Development-Oriented Testing and Repository Back-Translation

A Declarative-Procedural Perspective on Expert Routing in Bilingual Mixture-of-Experts Language Models

LLMEval-Logic: A Solver-Verified Chinese Benchmark for Logical Reasoning of LLMs with Adversarial Hardening

PatRe: A Full-Stage Office Action and Rebuttal Generation Benchmark for Patent Examination

FINESSE-Bench: A Hierarchical Benchmark Suite for Financial Domain Knowledge and Technical Analysis in Large Language Models

LongTraceRL: Learning Long-Context Reasoning from Search Agent Trajectories with Rubric Rewards

Recursive Think-Answer Process for LLMs and VLMs

Discovering Hidden Gems in Model Repositories

Humans and LLMs Diverge on Probabilistic Inferences

Stable Miscalibration in Large Language Models: A Practical View of High-Confidence Errors

Not All Tokens Are Equal: Inflation-Aware Routing for Agentic LLM Systems

Mela: Test-Time Memory Consolidation based on Transformation Hypothesis

CopT: Contrastive On-Policy Thinking with Continuous Spaces for General and Agentic Reasoning

AdaReasoner: Dynamic Tool Orchestration for Iterative Visual Reasoning

CompactAttention: Accelerating Chunked Prefill with Block-Union KV Selection

Efficient Reasoning with Balanced Thinking

MAS-Orchestra: Understanding and Improving Multi-Agent Reasoning Through Holistic Orchestration and Controlled Benchmarks

PRiSM: Benchmarking Phone Realization in Speech Models

Meta-Reinforcement Learning with Self-Reflection for Agentic Search

DocAtlas: Multilingual Document Understanding Across 80+ Languages

SoCRATES: Towards Reliable Automated Evaluation of Proactive LLM Mediation across Domains and Socio-cognitive Variations

ScheMatiQ: From Research Question to Structured Data through Interactive Schema Discovery

How do LLMs Compute Verbal Confidence

IQuest-Coder-V1 Technical Report

MARS: Enabling Autoregressive Models Multi-Token Generation

Watch Before You Answer: Learning from Visually Grounded Post-Training

dVoting: Fast Voting for dLLMs

From Prompt Injection to Persistent Control: Defending Agentic Harness Against Trojan Backdoors

O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning

Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift

World Action Models: The Next Frontier in Embodied AI

Do What I Say: A Spoken Prompt Dataset for Instruction-Following

FocuSFT: Bilevel Optimization for Dilution-Aware Long-Context Fine-Tuning

InfiniteWeb: Scalable Web Environment Synthesis for GUI Agent Training