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)

10,981 to 11,040 of 11,244

Gathered, Not Admitted: How Attention Brings a Latent Variable into Verbalizable Form
Parsa Mazaheri
cs.AIcs.CLarXiv:2608.15022v12026
NARRATE: A Multimodal Real-World Australian Driving Dataset for Human-Centred Explanations in Automated Driving
Ashkan Yousefi Zadeh, Zishuo Zhu, Xiaomeng Li +5
cs.CVcs.AIcs.CLarXiv:2608.14767v12026
RecurrentGPT: Expressive Depth through Recurrent Modulation in Transformers
Amr Hegazy, Amr Alanwar, Mostafa Elhoushi
cs.CLcs.LGarXiv:2608.15062v12026
Do LLMs Know What to Ask and When? Evaluating Multi-Turn Information Seeking
Yepeng Huang, Jiawen Zhang, Michelle Dai +4
cs.AIcs.CLcs.LGarXiv:2608.14808v12026
Evo-Harness: Context-to-Harness Skill Compilation for Self-Evolving Agents
Tianxin Wei, Zhan Shi, Minhua Lin +14
cs.AIcs.CLarXiv:2608.15071v12026
Left-Branching Transformers Excel at Right-Branching Languages: Data Shapes Word Order Preferences in Language Models
Varvara Arzt, Allan Hanbury, Terra Blevins
cs.CLcs.AIarXiv:2608.15129v12026
Prior Audit-Repair Context Shifts LLM Verifier Thresholds Toward Leniency
Parsa Mazaheri, Kasra Mazaheri
cs.AIcs.CLarXiv:2608.16003v12026
ClawGym II: Exploring Black-Box RL on Agent Harness
Huatong Song, Fei Bai, Ming Yang +17
cs.CLcs.AIcs.LGarXiv:2608.16798v12026
Sample-Efficient Learning from Agent Experience
Chenhui Gou, Haoqin Tu, Yunhao Fang +2
cs.CLarXiv:2607.21051v12026
The conditional superiority of fast silicon sampling
Nickolas Hock Yuen Lam, Ji Xuan Voo, Xiangyu Ma
cs.CLcond-mat.mtrl-sciarXiv:2608.14079v12026
Factorized Hypothesis Search for Evidence-to-Taxonomy Retrieval
Linhai Ma, Ethan F. Wei, Xueqing Peng +3
cs.CLcs.AIarXiv:2608.06614v12026
SLPO: Scaling Latent Reasoning via a Surrogate Policy
Runyang You, Zhiyuan Liu, Yongqi Li +1
cs.CLcs.AIcs.LGarXiv:2607.19691v22026
Cross-Disciplinary Taxonomy and Modeling of Misunderstanding Generation, Amplification, and Detection, from Pragmatics to AI Agents
Babak Abbaschian
cs.AIcs.CLcs.HCarXiv:2608.13604v12026
EvolvingWorld: An Open-Schema Framework for Co-Evolving Role-Play Agents and World Model in Interactive Literary World
Qing Zong, Yue Guo, Mengxin Yang +2
cs.CLarXiv:2607.17250v12026
SWE-Touch: Benchmarking Coding Agents When Users Touch the Code
Yuqiao Tan, Jinxiang Meng, Fangyu Lei +4
cs.SEcs.AIcs.CLarXiv:2608.02499v12026
UNMASK: Discovering and Causally Verifying Spurious Shortcuts in Text Classifiers
Chidaksh Ravuru, Shashank Srivastava
cs.CLcs.LGarXiv:2608.09209v12026
HPD-Parsing: Hierarchical Parallel Document Parsing
Shu Wei, Jingjing Wu, Lingshu Zhang +10
cs.CLarXiv:2607.18839v12026
Do AI chatbots find what experts would? Effects of model, user role, and sample size on study retrieval for medical questions
Qingfang Liu, Qiao Jin, Joe D. Menke +2
cs.IRcs.AIcs.CLarXiv:2608.13786v12026
GRPO, Dr. GRPO, and DAPO Are Three Operations on One Number: The Group-Standard-Deviation Identity
Yong Yi Bay, Kathleen A. Yearick
cs.LGcs.AIcs.CLarXiv:2607.00152v12026
PluraMath: Extending Mathematical Reasoning Evaluation Beyond High-Resource Languages
Daryna Dementieva, Nikolay Babakov, Kathy Hämmerl +14
cs.CLcs.AIarXiv:2607.05992v12026
MET: Theory-Grounded and Culture-Aware Multilingual Moral Reasoning
Ayoung Lee, Ryan Kwon, Yunxiang Zhang +3
cs.CLarXiv:2607.11736v12026
Self-Guided Test-Time Training for Long-Context LLMs
Xinyu Zhu, Zhe Xu, Xiaohan Wei +10
cs.CLcs.AIarXiv:2607.09415v12026
CausalDS: Benchmarking Causal Reasoning in Data-Science Agents
Andrej Leban, Yuekai Sun
cs.AIcs.CLcs.LGarXiv:2607.08093v12026
RuleChef: Grounding LLM Task Knowledge in Human-Editable Rules
Ádám Kovács, Nadia Verdha, Gábor Recski
cs.CLarXiv:2607.01293v12026
ReasoningLens: Hierarchical Visualization and Diagnostic Auditing for Large Reasoning Models
Jun Zhang, Jiasheng Zheng, Boxi Cao +5
cs.CLcs.AIarXiv:2606.23404v12026
World Action Models: The Next Frontier in Embodied AI
Siyin Wang, Junhao Shi, Zhaoyang Fu +11
cs.ROcs.CLcs.CVarXiv:2605.12090v12026
Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments
Qiuyue Wang, Mingsheng Li, Jian Guan +37
cs.ROcs.AIcs.CLarXiv:2605.30280v22026
Self-Distilled Agentic Reinforcement Learning
Zhengxi Lu, Zhiyuan Yao, Zhuowen Han +8
cs.LGcs.AIcs.CLarXiv:2605.15155v12026
Code as Agent Harness
Xuying Ning, Katherine Tieu, Dongqi Fu +39
cs.CLcs.AIarXiv:2605.18747v12026
STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?
Hanxiang Chao, Yihan Bai, Rui Sheng +2
cs.CLarXiv:2605.06527v12026
Filter, Then Reweight: Rethinking Optimization Granularity in On-Policy Distillation
Yuying Li, Leqi Zheng, Yongzi Yu +6
cs.LGcs.AIcs.CLarXiv:2606.02684v22026
MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation
Huawei Lin, Peng Li, Jie Song +2
cs.AIcs.CLcs.LGarXiv:2605.27366v22026
From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms
Jinghao Luo, Yuchen Tian, Chuxue Cao +6
cs.AIcs.CLarXiv:2605.06716v12026
WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation
Shuangrui Ding, Xuanlang Dai, Long Xing +14
cs.CLarXiv:2605.10912v12026
SkillOpt: Executive Strategy for Self-Evolving Agent Skills
Yifan Yang, Ziyang Gong, Weiquan Huang +12
cs.AIcs.CLarXiv:2605.23904v22026
MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction
Junbo Cui, Bokai Xu, Chongyi Wang +33
cs.CLarXiv:2604.27393v12026
Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding
Jianuo Huang, Yaojie Zhang, Qituan Zhang +3
cs.CLarXiv:2605.29707v12026
KL for a KL: On-Policy Distillation with Control Variate Baseline
Minjae Oh, Sangjun Song, Gyubin Choi +2
cs.LGcs.AIcs.CLarXiv:2605.07865v12026
ELF: Embedded Language Flows
Keya Hu, Linlu Qiu, Yiyang Lu +5
cs.CLcs.AIcs.LGarXiv:2605.10938v22026
A Survey on LLM-based Conversational User Simulation
Bo Ni, Leyao Wang, Yu Wang +27
cs.CLcs.HCarXiv:2604.24977v12026
How Much Is One Recurrence Worth? Iso-Depth Scaling Laws for Looped Language Models
Kristian Schwethelm, Daniel Rueckert, Georgios Kaissis
cs.LGcs.CLarXiv:2604.21106v32026
ScrambleToolBench: Agents Search Exhaustively Even When Their Own Map Points to the Next Step
Vernon Toh, Navonil Majumder, Zhengyuan Liu +2
cs.CLarXiv:2608.02358v12026
What Intermediate Layers Know: Detecting Jailbreaks from Entropy Dynamics
Sofiia Nikolenko, Michele Papucci, Mina Rezaei +1
cs.CLcs.AIcs.LGarXiv:2606.25182v12026
SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning
SingGuard Team
cs.CVcs.CLarXiv:2606.22873v32026
Mind the Heads: Topological Representation Alignment for Multimodal LLMs
Davide Caffagni, Alberto Compagnoni, Federico Melis +5
cs.CVcs.AIcs.CLarXiv:2606.23885v12026
Summaries:한국어
AGORA: An Archive-Grounded Benchmark for Agentic Workplace Document Reasoning
Honglin Guo, Qi Zhang, Yu Zhang +7
cs.CLarXiv:2606.24526v12026
Holistic Data Scheduler for LLM Pre-training via Multi-Objective Reinforcement Learning
Chenhao Dang, Jing Ma, Mingjie Liao
cs.LGcs.CLarXiv:2606.24133v12026
DREAM: Dense Retrieval Embeddings via Autoregressive Modeling
Yixuan Tang, Yi Yang
cs.CLarXiv:2606.24667v12026
The Tatoxa System for Text Detoxification in Low-Resource Languages: The Case of Tatar
Ilseyar Alimova, Bogdan Monogov, Artyom Mazur +5
cs.CLarXiv:2606.26015v12026
Information-Aware KV Cache Compression for Long Reasoning
Jushi Kai, Zhuiri Xiao, Alexandra Birch +1
cs.CLcs.AIarXiv:2606.26875v12026
Ko-WideSearch: A Korean Breadth-Search Benchmark for Exhaustive Set Enumeration by Web Agents
Minbyul Jeong
cs.CLarXiv:2606.27595v12026
MultiHashFormer: Hash-based Generative Language Models
Huiyin Xue, Atsuki Yamaguchi, Nikolaos Aletras
cs.CLcs.AIcs.LGarXiv:2606.28057v12026
Towards Automating Scientific Review with Google's Paper Assistant Tool
Rajesh Jayaram, Drew Tyler, David Woodruff +4
cs.LGcs.AIcs.CLarXiv:2606.28277v12026
When Search Agents Should Ask: DiscoBench for Clarification-Aware Deep Search
Yiling Tao, Shihan Deng, Meiling Tao +3
cs.CLarXiv:2606.27669v22026
ReFreeKV: Towards Threshold-Free KV Cache Compression
Xuanfan Ni, Liyan Xu, Chenyang Lyu +6
cs.CLcs.AIcs.LGarXiv:2502.16886v42025
PolicyGuard: A Dialogue-Grounded Sub-Agent Verifier for Policy Adherence in LLM Agents
Seongjae Kang, Taehyung Yu, Sung Ju Hwang
cs.AIcs.CLarXiv:2606.29225v12026
Little Brains, Big Feats: Exploring Compact Language Models
Dari Baturova, Elena Bruches, Ivan Chernov +3
cs.CLcs.AIarXiv:2606.30062v12026
Multi-Turn Agentic Scientific Literature Search via Workflow Induction
Jisen Li, Bingxuan Li, Nanyi Jiang +10
cs.CLcs.IRarXiv:2607.00597v22026
When Classic Cache Policies Fail: Learning-Augmented Replacement for Semantic Retrieval Buffers
Yushi Sun, Bowen Cao, Wai Lam
cs.DBcs.CLarXiv:2607.00394v12026
PraMem: Practice-derived Experiential Memory for Long-horizon Behavior Prediction
Zhuoqun Li, Boxi Cao, Jiawei Chen +11
cs.CLarXiv:2607.02881v12026

Computation and Language

Gathered, Not Admitted: How Attention Brings a Latent Variable into Verbalizable Form

NARRATE: A Multimodal Real-World Australian Driving Dataset for Human-Centred Explanations in Automated Driving

RecurrentGPT: Expressive Depth through Recurrent Modulation in Transformers

Do LLMs Know What to Ask and When? Evaluating Multi-Turn Information Seeking

Evo-Harness: Context-to-Harness Skill Compilation for Self-Evolving Agents

Left-Branching Transformers Excel at Right-Branching Languages: Data Shapes Word Order Preferences in Language Models

Prior Audit-Repair Context Shifts LLM Verifier Thresholds Toward Leniency

ClawGym II: Exploring Black-Box RL on Agent Harness

Sample-Efficient Learning from Agent Experience

The conditional superiority of fast silicon sampling

Factorized Hypothesis Search for Evidence-to-Taxonomy Retrieval

SLPO: Scaling Latent Reasoning via a Surrogate Policy

Cross-Disciplinary Taxonomy and Modeling of Misunderstanding Generation, Amplification, and Detection, from Pragmatics to AI Agents

EvolvingWorld: An Open-Schema Framework for Co-Evolving Role-Play Agents and World Model in Interactive Literary World

SWE-Touch: Benchmarking Coding Agents When Users Touch the Code

UNMASK: Discovering and Causally Verifying Spurious Shortcuts in Text Classifiers

HPD-Parsing: Hierarchical Parallel Document Parsing

Do AI chatbots find what experts would? Effects of model, user role, and sample size on study retrieval for medical questions

GRPO, Dr. GRPO, and DAPO Are Three Operations on One Number: The Group-Standard-Deviation Identity

PluraMath: Extending Mathematical Reasoning Evaluation Beyond High-Resource Languages

MET: Theory-Grounded and Culture-Aware Multilingual Moral Reasoning

Self-Guided Test-Time Training for Long-Context LLMs

CausalDS: Benchmarking Causal Reasoning in Data-Science Agents

RuleChef: Grounding LLM Task Knowledge in Human-Editable Rules

ReasoningLens: Hierarchical Visualization and Diagnostic Auditing for Large Reasoning Models

World Action Models: The Next Frontier in Embodied AI

Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments

Self-Distilled Agentic Reinforcement Learning

Code as Agent Harness

STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?

Filter, Then Reweight: Rethinking Optimization Granularity in On-Policy Distillation

MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation

From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms

WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation

SkillOpt: Executive Strategy for Self-Evolving Agent Skills

MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction

Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding

KL for a KL: On-Policy Distillation with Control Variate Baseline

ELF: Embedded Language Flows

A Survey on LLM-based Conversational User Simulation

How Much Is One Recurrence Worth? Iso-Depth Scaling Laws for Looped Language Models

ScrambleToolBench: Agents Search Exhaustively Even When Their Own Map Points to the Next Step

What Intermediate Layers Know: Detecting Jailbreaks from Entropy Dynamics

SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning

Mind the Heads: Topological Representation Alignment for Multimodal LLMs

AGORA: An Archive-Grounded Benchmark for Agentic Workplace Document Reasoning

Holistic Data Scheduler for LLM Pre-training via Multi-Objective Reinforcement Learning

DREAM: Dense Retrieval Embeddings via Autoregressive Modeling

The Tatoxa System for Text Detoxification in Low-Resource Languages: The Case of Tatar

Information-Aware KV Cache Compression for Long Reasoning

Ko-WideSearch: A Korean Breadth-Search Benchmark for Exhaustive Set Enumeration by Web Agents

MultiHashFormer: Hash-based Generative Language Models

Towards Automating Scientific Review with Google's Paper Assistant Tool

When Search Agents Should Ask: DiscoBench for Clarification-Aware Deep Search

ReFreeKV: Towards Threshold-Free KV Cache Compression

PolicyGuard: A Dialogue-Grounded Sub-Agent Verifier for Policy Adherence in LLM Agents

Little Brains, Big Feats: Exploring Compact Language Models

Multi-Turn Agentic Scientific Literature Search via Workflow Induction

When Classic Cache Policies Fail: Learning-Augmented Replacement for Semantic Retrieval Buffers

PraMem: Practice-derived Experiential Memory for Long-horizon Behavior Prediction