Artificial Intelligence

Papers filed under cs.AI 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)

12,661 to 12,720 of 15,326

Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation
Wenkai Yang, Weijie Liu, Ruobing Xie +3
cs.LGcs.AIcs.CLarXiv:2602.12125v22026
LLaDA2.1: Speeding Up Text Diffusion via Token Editing
Tiwei Bie, Maosong Cao, Xiang Cao +47
cs.LGcs.AIarXiv:2602.08676v32026
SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
Xiangyi Li, Yimin Liu, Wenbo Chen +75
cs.AIarXiv:2602.12670v42026
Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
Jingwei Ni, Yihao Liu, Xinpeng Liu +7
cs.AIarXiv:2603.25158v52026
Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding
Christopher Clark, Jieyu Zhang, Zixian Ma +18
cs.CVcs.AIarXiv:2601.10611v42026
Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale
Yi Liu, Weizhe Wang, Ruitao Feng +5
cs.CRcs.AIcs.CLarXiv:2601.10338v12026
Numina-Lean-Agent: An Open and General Agentic Reasoning System for Formal Mathematics
Junqi Liu, Zihao Zhou, Zekai Zhu +10
cs.AIarXiv:2601.14027v12026
CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation
Weinan Dai, Hanlin Wu, Qiying Yu +13
cs.LGcs.AIarXiv:2602.24286v12026
SkillNet: Create, Evaluate, and Connect AI Skills
Yuan Liang, Ruobin Zhong, Haoming Xu +47
cs.AIcs.CLcs.CVarXiv:2603.04448v22026
Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agents
Haiyang Xu, Xi Zhang, Haowei Liu +16
cs.AIcs.CLarXiv:2602.16855v12026
OpenClaw-RL: Train Any Agent Simply by Talking
Yinjie Wang, Xuyang Chen, Xiaolong Jin +2
cs.CLcs.AIcs.CVarXiv:2603.10165v22026
MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents
Haozhen Zhang, Quanyu Long, Jianzhu Bao +4
cs.CLcs.AIcs.LGarXiv:2602.02474v22026
SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?
Tingxu Han, Yi Zhang, Wei Song +4
cs.SEcs.AIarXiv:2603.15401v12026
Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning
Moo Jin Kim, Yihuai Gao, Tsung-Yi Lin +8
cs.AIcs.ROarXiv:2601.16163v12026
DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos
Shenyuan Gao, William Liang, Kaiyuan Zheng +27
cs.ROcs.AIcs.CVarXiv:2602.06949v12026
Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
Mike A. Merrill, Alexander G. Shaw, Nicholas Carlini +82
cs.SEcs.AIarXiv:2601.11868v12026
EgoSim: Egocentric World Simulator for Embodied Interaction Generation
Jinkun Hao, Mingda Jia, Ruiyan Wang +7
cs.CVcs.AIarXiv:2604.01001v22026
PixelPrune: Pixel-Level Adaptive Visual Token Reduction via Predictive Coding
Nan Wang, Zhiwei Jin, Chen Chen +1
cs.CVcs.AIcs.CLarXiv:2604.00886v12026
Signals: Trajectory Sampling and Triage for Agentic Interactions
Shuguang Chen, Adil Hafeez, Salman Paracha
cs.AIcs.CLarXiv:2604.00356v12026
Investigating Autonomous Agent Contributions in the Wild: Activity Patterns and Code Change over Time
Razvan Mihai Popescu, David Gros, Andrei Botocan +3
cs.SEcs.AIcs.LGarXiv:2604.00917v12026
Proactive Agent Research Environment: Simulating Active Users to Evaluate Proactive Assistants
Deepak Nathani, Cheng Zhang, Chang Huan +7
cs.AIcs.LGcs.MAarXiv:2604.00842v12026
Do Phone-Use Agents Respect Your Privacy?
Zhengyang Tang, Ke Ji, Xidong Wang +19
cs.CRcs.AIcs.CLarXiv:2604.00986v22026
Revision or Re-Solving? Decomposing Second-Pass Gains in Multi-LLM Pipelines
Jingjie Ning, Xueqi Li, Chengyu Yu
cs.SEcs.AIcs.CLarXiv:2604.01029v22026
Woosh: A Sound Effects Foundation Model
Gaëtan Hadjeres, Marc Ferras, Khaled Koutini +7
cs.SDcs.AIcs.LGarXiv:2604.01929v32026
Executing as You Generate: Hiding Execution Latency in LLM Code Interpreters
Zhensu Sun, Zhihao Lin, Zhi Chen +4
cs.PLcs.AIcs.SEarXiv:2604.00491v22026
CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery
Ao Qu, Han Zheng, Zijian Zhou +14
cs.AIarXiv:2604.01658v22026
Learning to Learn-at-Test-Time: Language Agents with Learnable Adaptation Policies
Zhanzhi Lou, Hui Chen, Yibo Li +2
cs.LGcs.AIarXiv:2604.00830v32026
AgentSocialBench: Evaluating Privacy Risks in Human-Centered Agentic Social Networks
Prince Zizhuang Wang, Shuli Jiang
cs.AIcs.SIarXiv:2604.01487v22026
UniMixer: A Unified Architecture for Scaling Laws in Recommendation Systems
Mingming Ha, Guanchen Wang, Linxun Chen +9
cs.IRcs.AIarXiv:2604.00590v22026
HippoCamp: Benchmarking Contextual Agents on Personal Computers
Zhe Yang, Shulin Tian, Kairui Hu +9
cs.AIcs.CVarXiv:2604.01221v12026
Summaries:한국어
Paper Reconstruction Evaluation: Evaluating Presentation and Hallucination in AI-written Papers
Atsuyuki Miyai, Mashiro Toyooka, Zaiying Zhao +3
cs.CLcs.AIcs.LGarXiv:2604.01128v12026
Brainstacks: Cross-Domain Cognitive Capabilities via Frozen MoE-LoRA Stacks for Continual LLM Learning
Mohammad R. Abu Ayyash
cs.CLcs.AIarXiv:2604.01152v12026
ActionParty: Multi-Subject Action Binding in Generative Video Games
Alexander Pondaven, Ziyi Wu, Igor Gilitschenski +4
cs.CVcs.AIcs.LGarXiv:2604.02330v22026
Tex3D: Objects as Attack Surfaces via Adversarial 3D Textures for Vision-Language-Action Models
Jiawei Chen, Simin Huang, Jiawei Du +5
cs.CVcs.AIarXiv:2604.01618v12026
Omni123: Exploring 3D Native Foundation Models with Limited 3D Data by Unifying Text to 2D and 3D Generation
Chongjie Ye, Cheng Cao, Chuanyu Pan +4
cs.CVcs.AIarXiv:2604.02289v12026
Omni-SimpleMem: Autoresearch-Guided Discovery of Lifelong Multimodal Agent Memory
Jiaqi Liu, Zipeng Ling, Shi Qiu +9
cs.AIarXiv:2604.01007v22026
GPA: Learning GUI Process Automation from Demonstrations
Zirui Zhao, Jun Hao Liew, Yan Yang +5
cs.CVcs.AIcs.SEarXiv:2604.01676v22026
Therefore I am. I Think
Esakkivel Esakkiraja, Sai Rajeswar, Denis Akhiyarov +1
cs.AIarXiv:2604.01202v32026
Steerable Visual Representations
Jona Ruthardt, Manu Gaur, Deva Ramanan +2
cs.CVcs.AIarXiv:2604.02327v22026
The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook
Xinlei Yu, Zhangquan Chen, Yongbo He +36
cs.AIarXiv:2604.02029v22026
DriveDreamer-Policy: A Geometry-Grounded World-Action Model for Unified Generation and Planning
Yang Zhou, Xiaofeng Wang, Hao Shao +8
cs.CVcs.AIcs.ROarXiv:2604.01765v12026
Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing
Gengsheng Li, Tianyu Yang, Junfeng Fang +6
cs.LGcs.AIarXiv:2604.02288v12026
ThinkTwice: Jointly Optimizing Large Language Models for Reasoning and Self-Refinement
Difan Jiao, Qianfeng Wen, Blair Yang +2
cs.AIarXiv:2604.01591v22026
Large Language Models Align with the Human Brain during Creative Thinking
Mete Ismayilzada, Simone A. Luchini, Abdulkadir Gokce +5
q-bio.NCcs.AIcs.CLarXiv:2604.03480v22026
BidirLM: From Text to Omnimodal Bidirectional Encoders by Adapting and Composing Causal LLMs
Nicolas Boizard, Théo Deschamps-Berger, Hippolyte Gisserot-Boukhlef +2
cs.CLcs.AIarXiv:2604.02045v12026
AgentHazard: A Benchmark for Evaluating Harmful Behavior in Computer-Use Agents
Yunhao Feng, Yifan Ding, Yingshui Tan +6
cs.AIarXiv:2604.02947v12026
Born Again Neural Networks
Tommaso Furlanello, Zachary C. Lipton, Michael Tschannen +2
stat.MLcs.AIcs.LGarXiv:1805.04770v22018
Lost in Translation? Exploring the Shift in Grammatical Gender from Latin to Occitan
Ahan Chatterjee, Matthias Schöffel, Matthias Aßenmacher +2
cs.CLcs.AIarXiv:2605.09156v22026
ClawArena: Benchmarking AI Agents in Evolving Information Environments
Haonian Ji, Kaiwen Xiong, Siwei Han +9
cs.LGcs.AIcs.CLarXiv:2604.04202v22026
GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning
Ornith Team, Xiaoya Li, Guoyin Wang +3
cs.AIarXiv:2604.02721v32026
Watch Before You Answer: Learning from Visually Grounded Post-Training
Yuxuan Zhang, EunJeong Hwang, Huaisong Zhang +8
cs.CVcs.AIcs.CLarXiv:2604.05117v12026
Cog-DRIFT: Exploration on Adaptively Reformulated Instances Enables Learning from Hard Reasoning Problems
Justin Chih-Yao Chen, Archiki Prasad, Zaid Khan +4
cs.LGcs.AIcs.CLarXiv:2604.04767v12026
SkillX: Automatically Constructing Skill Knowledge Bases for Agents
Chenxi Wang, Zhuoyun Yu, Xin Xie +8
cs.CLcs.AIcs.IRarXiv:2604.04804v22026
InCoder-32B-Thinking: Industrial Code World Model for Thinking
Jian Yang, Wei Zhang, Jiajun Wu +22
cs.ARcs.AIcs.CLarXiv:2604.03144v12026
Do Audio-Visual Large Language Models Really See and Hear?
Ramaneswaran Selvakumar, Kaousheik Jayakumar, S Sakshi +3
cs.AIcs.SDarXiv:2604.02605v12026
Beyond the Assistant Turn: User Turn Generation as a Probe of Interaction Awareness in Language Models
Sarath Shekkizhar, Romain Cosentino, Adam Earle
cs.AIarXiv:2604.02315v22026
LightThinker++: From Reasoning Compression to Memory Management
Yuqi Zhu, Jintian Zhang, Zhenjie Wan +7
cs.CLcs.AIcs.IRarXiv:2604.03679v12026
Squeez: Task-Conditioned Tool-Output Pruning for Coding Agents
Ádám Kovács
cs.SEcs.AIarXiv:2604.04979v12026
Can LLMs Learn to Reason Robustly under Noisy Supervision?
Shenzhi Yang, Guangcheng Zhu, Bowen Song +7
cs.LGcs.AIarXiv:2604.03993v12026
Vero: An Open RL Recipe for General Visual Reasoning
Gabriel Sarch, Linrong Cai, Qunzhong Wang +3
cs.CVcs.AIcs.CLarXiv:2604.04917v32026

Artificial Intelligence

Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation

LLaDA2.1: Speeding Up Text Diffusion via Token Editing

SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks

Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills

Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding

Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale

Numina-Lean-Agent: An Open and General Agentic Reasoning System for Formal Mathematics

CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation

SkillNet: Create, Evaluate, and Connect AI Skills

Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agents

OpenClaw-RL: Train Any Agent Simply by Talking

MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents

SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?

Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning

DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos

Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces

EgoSim: Egocentric World Simulator for Embodied Interaction Generation

PixelPrune: Pixel-Level Adaptive Visual Token Reduction via Predictive Coding

Signals: Trajectory Sampling and Triage for Agentic Interactions

Investigating Autonomous Agent Contributions in the Wild: Activity Patterns and Code Change over Time

Proactive Agent Research Environment: Simulating Active Users to Evaluate Proactive Assistants

Do Phone-Use Agents Respect Your Privacy?

Revision or Re-Solving? Decomposing Second-Pass Gains in Multi-LLM Pipelines

Woosh: A Sound Effects Foundation Model

Executing as You Generate: Hiding Execution Latency in LLM Code Interpreters

CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery

Learning to Learn-at-Test-Time: Language Agents with Learnable Adaptation Policies

AgentSocialBench: Evaluating Privacy Risks in Human-Centered Agentic Social Networks

UniMixer: A Unified Architecture for Scaling Laws in Recommendation Systems

HippoCamp: Benchmarking Contextual Agents on Personal Computers

Paper Reconstruction Evaluation: Evaluating Presentation and Hallucination in AI-written Papers

Brainstacks: Cross-Domain Cognitive Capabilities via Frozen MoE-LoRA Stacks for Continual LLM Learning

ActionParty: Multi-Subject Action Binding in Generative Video Games

Tex3D: Objects as Attack Surfaces via Adversarial 3D Textures for Vision-Language-Action Models

Omni123: Exploring 3D Native Foundation Models with Limited 3D Data by Unifying Text to 2D and 3D Generation

Omni-SimpleMem: Autoresearch-Guided Discovery of Lifelong Multimodal Agent Memory

GPA: Learning GUI Process Automation from Demonstrations

Therefore I am. I Think

Steerable Visual Representations

The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook

DriveDreamer-Policy: A Geometry-Grounded World-Action Model for Unified Generation and Planning

Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing

ThinkTwice: Jointly Optimizing Large Language Models for Reasoning and Self-Refinement

Large Language Models Align with the Human Brain during Creative Thinking

BidirLM: From Text to Omnimodal Bidirectional Encoders by Adapting and Composing Causal LLMs

AgentHazard: A Benchmark for Evaluating Harmful Behavior in Computer-Use Agents

Born Again Neural Networks

Lost in Translation? Exploring the Shift in Grammatical Gender from Latin to Occitan

ClawArena: Benchmarking AI Agents in Evolving Information Environments

GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning

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

Cog-DRIFT: Exploration on Adaptively Reformulated Instances Enables Learning from Hard Reasoning Problems

SkillX: Automatically Constructing Skill Knowledge Bases for Agents

InCoder-32B-Thinking: Industrial Code World Model for Thinking

Do Audio-Visual Large Language Models Really See and Hear?

Beyond the Assistant Turn: User Turn Generation as a Probe of Interaction Awareness in Language Models

LightThinker++: From Reasoning Compression to Memory Management

Squeez: Task-Conditioned Tool-Output Pruning for Coding Agents

Can LLMs Learn to Reason Robustly under Noisy Supervision?

Vero: An Open RL Recipe for General Visual Reasoning