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)

12,481 to 12,540 of 15,247

From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents
Ling Yue, Kushal Raj Bhandari, Ching-Yun Ko +6
cs.AIcs.CLarXiv:2603.22386v12026
CLI-Gym: Scalable CLI Task Generation via Agentic Environment Inversion
Yusong Lin, Haiyang Wang, Shuzhe Wu +4
cs.AIarXiv:2602.10999v12026
RubricBench: Aligning Model-Generated Rubrics with Human Standards
Qiyuan Zhang, Junyi Zhou, Yufei Wang +8
cs.AIarXiv:2603.01562v22026
Large Language Models: A Survey
Shervin Minaee, Tomas Mikolov, Narjes Nikzad +4
cs.CLcs.AIarXiv:2402.06196v32024
TermiGen: High-Fidelity Environment and Robust Trajectory Synthesis for Terminal Agents
Kaijie Zhu, Yuzhou Nie, Yijiang Li +10
cs.AIarXiv:2602.07274v12026
Self-Hinting Language Models Enhance Reinforcement Learning
Baohao Liao, Hanze Dong, Xinxing Xu +2
cs.LGcs.AIcs.CLarXiv:2602.03143v12026
ViDoRe V3: A Comprehensive Evaluation of Retrieval Augmented Generation in Complex Real-World Scenarios
António Loison, Quentin Macé, Antoine Edy +7
cs.AIcs.CVarXiv:2601.08620v22026
A Diagram Is Worth A Dozen Images
Aniruddha Kembhavi, Mike Salvato, Eric Kolve +3
cs.CVcs.AIarXiv:1603.07396v12016
LangForce: Bayesian Decomposition of Vision Language Action Models via Latent Action Queries
Shijie Lian, Bin Yu, Xiaopeng Lin +6
cs.AIcs.CLcs.CVarXiv:2601.15197v72026
Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planning
Chi-Pin Huang, Yunze Man, Zhiding Yu +4
cs.CVcs.AIcs.LGarXiv:2601.09708v22026
Fish Audio S2 Technical Report
Shijia Liao, Yuxuan Wang, Songting Liu +11
cs.SDcs.AIcs.CLarXiv:2603.08823v22026
Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization
Chelsea Finn, Sergey Levine, Pieter Abbeel
cs.LGcs.AIcs.ROarXiv:1603.00448v32016
Timer-S1: A Billion-Scale Time Series Foundation Model with Serial Scaling
Yong Liu, Xingjian Su, Shiyu Wang +7
cs.AIarXiv:2603.04791v32026
Medical SAM3: A Foundation Model for Universal Prompt-Driven Medical Image Segmentation
Chongcong Jiang, Tianxingjian Ding, Chuhan Song +7
cs.CVcs.AIarXiv:2601.10880v12026
OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using Agent
Bowen Yang, Kaiming Jin, Zhenyu Wu +12
cs.MAcs.AIcs.CLarXiv:2601.07779v12026
VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models
Wenlong Huang, Chen Wang, Ruohan Zhang +3
cs.ROcs.AIcs.CLarXiv:2307.05973v22023
MemTrapBench: Benchmarking Cognitive Traps in LLM Memory Use
Mengru Wang, Haozhe Luo, Zhenqian Xu +6
cs.AIcs.CLcs.CYarXiv:2608.20202v12026
Benchmark Test-Time Scaling of General LLM Agents
Xiaochuan Li, Ryan Ming, Pranav Setlur +6
cs.AIcs.CLarXiv:2602.18998v12026
SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks
Gabriel Orlanski, Devjeet Roy, Alexander Yun +7
cs.SEcs.AIcs.CLarXiv:2603.24755v22026
Gradient based sample selection for online continual learning
Rahaf Aljundi, Min Lin, Baptiste Goujaud +1
cs.LGcs.AIcs.CVarXiv:1903.08671v52019
DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing
Dianyi Wang, Ruihang Li, Feng Han +17
cs.CVcs.AIarXiv:2602.12205v22026
LongCat-Flash-Thinking-2601 Technical Report
Meituan LongCat Team, Anchun Gui, Bei Li +163
cs.AIarXiv:2601.16725v22026
Gaia2: Benchmarking LLM Agents on Dynamic and Asynchronous Environments
Romain Froger, Pierre Andrews, Matteo Bettini +21
cs.AIarXiv:2602.11964v12026
Bilinear Attention Networks
Jin-Hwa Kim, Jaehyun Jun, Byoung-Tak Zhang
cs.CVcs.AIcs.CLarXiv:1805.07932v22018
Dr. Kernel: Reinforcement Learning Done Right for Triton Kernel Generations
Wei Liu, Jiawei Xu, Yingru Li +4
cs.LGcs.AIcs.CLarXiv:2602.05885v22026
Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition
Maosen Li, Siheng Chen, Xu Chen +3
cs.CVcs.AIarXiv:1904.12659v12019
SceneSmith: Agentic Generation of Simulation-Ready Indoor Scenes
Nicholas Pfaff, Thomas Cohn, Sergey Zakharov +2
cs.ROcs.AIcs.CVarXiv:2602.09153v22026
ABot-N0: Technical Report on the VLA Foundation Model for Versatile Embodied Navigation
Zedong Chu, Shichao Xie, Xiaolong Wu +41
cs.ROcs.AIcs.CVarXiv:2602.11598v12026
Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights
Yulu Gan, Phillip Isola
cs.LGcs.AIarXiv:2603.12228v12026
ARISE: Agent Reasoning with Intrinsic Skill Evolution in Hierarchical Reinforcement Learning
Yu Li, Rui Miao, Zhengling Qi +1
cs.AIarXiv:2603.16060v22026
K-Search: LLM Kernel Generation via Co-Evolving Intrinsic World Model
Shiyi Cao, Ziming Mao, Joseph E. Gonzalez +1
cs.AIarXiv:2602.19128v22026
The NarrativeQA Reading Comprehension Challenge
Tomáš Kočiský, Jonathan Schwarz, Phil Blunsom +4
cs.CLcs.AIcs.NEarXiv:1712.07040v12017
FeatureBench: Benchmarking Agentic Coding for Complex Feature Development
Qixing Zhou, Jiacheng Zhang, Haiyang Wang +9
cs.SEcs.AIarXiv:2602.10975v12026
LoL: Longer than Longer, Scaling Video Generation to Hour
Justin Cui, Jie Wu, Ming Li +6
cs.CVcs.AIarXiv:2601.16914v12026
Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation
Zhuolin Yang, Zihan Liu, Yang Chen +14
cs.CLcs.AIcs.LGarXiv:2603.19220v22026
$τ$-Knowledge: Evaluating Conversational Agents over Unstructured Knowledge
Quan Shi, Alexandra Zytek, Pedram Razavi +2
cs.AIcs.CLcs.IRarXiv:2603.04370v12026
Reinforcement-aware Knowledge Distillation for LLM Reasoning
Zhaoyang Zhang, Shuli Jiang, Yantao Shen +6
cs.LGcs.AIarXiv:2602.22495v32026
Rethinking the Trust Region in LLM Reinforcement Learning
Penghui Qi, Xiangxin Zhou, Zichen Liu +4
cs.LGcs.AIcs.CLarXiv:2602.04879v32026
Scalable Power Sampling: Unlocking Efficient, Training-Free Reasoning for LLMs via Distribution Sharpening
Xiaotong Ji, Rasul Tutunov, Matthieu Zimmer +1
cs.LGcs.AIarXiv:2601.21590v12026
Continuous Deep Q-Learning with Model-based Acceleration
Shixiang Gu, Timothy Lillicrap, Ilya Sutskever +1
cs.LGcs.AIcs.ROarXiv:1603.00748v12016
Hyperagents
Jenny Zhang, Bingchen Zhao, Wannan Yang +5
cs.AIarXiv:2603.19461v12026
How AI Impacts Skill Formation
Judy Hanwen Shen, Alex Tamkin
cs.CYcs.AIcs.HCarXiv:2601.20245v22026
ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers
Songyang Liu, Chaozhuo Li, Chenxu Wang +8
cs.CRcs.AIarXiv:2603.24414v12026
Toward Ultra-Long-Horizon Agentic Science: Cognitive Accumulation for Machine Learning Engineering
Xinyu Zhu, Yuzhu Cai, Zexi Liu +8
cs.AIarXiv:2601.10402v52026
MuSiQue: Multihop Questions via Single-hop Question Composition
Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot +1
cs.CLcs.AIarXiv:2108.00573v32021
Anatomy of Agentic Memory: Taxonomy and Empirical Analysis of Evaluation and System Limitations
Dongming Jiang, Yi Li, Songtao Wei +8
cs.CLcs.AIarXiv:2602.19320v22026
VIBEVOICE-ASR Technical Report
Zhiliang Peng, Jianwei Yu, Yaoyao Chang +21
cs.SDcs.AIeess.ASarXiv:2601.18184v22026
Large Language Model Reasoning Failures
Peiyang Song, Pengrui Han, Noah Goodman
cs.AIcs.CLcs.LGarXiv:2602.06176v12026
OfficeQA Pro: An Enterprise Benchmark for End-to-End Grounded Reasoning
Krista Opsahl-Ong, Arnav Singhvi, Jasmine Collins +10
cs.AIcs.CLcs.IRarXiv:2603.08655v12026
QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning
Kyunghwan Son, Daewoo Kim, Wan Ju Kang +2
cs.LGcs.AIcs.MAarXiv:1905.05408v12019
Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters
Ailin Huang, Ang Li, Aobo Kong +213
cs.CLcs.AIarXiv:2602.10604v22026
OmniGAIA: Towards Native Omni-Modal AI Agents
Xiaoxi Li, Wenxiang Jiao, Jiarui Jin +10
cs.AIcs.CLcs.CVarXiv:2602.22897v32026
AOrchestra: Automating Sub-Agent Creation for Agentic Orchestration
Jianhao Ruan, Zhihao Xu, Yiran Peng +9
cs.AIcs.CLarXiv:2602.03786v22026
DeepPlanning: Benchmarking Long-Horizon Agentic Planning with Verifiable Constraints
Yinger Zhang, Shutong Jiang, Renhao Li +6
cs.AIcs.CLarXiv:2601.18137v12026
HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding
Haowei Zhang, Shudong Yang, Jinlan Fu +2
cs.CVcs.AIcs.CLarXiv:2601.14724v42026
AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security
Dongrui Liu, Qihan Ren, Chen Qian +40
cs.AIcs.CCcs.CLarXiv:2601.18491v22026
Dr. Zero: Self-Evolving Search Agents without Training Data
Zhenrui Yue, Kartikeya Upasani, Xianjun Yang +5
cs.AIarXiv:2601.07055v22026
Rethinking Video Generation Model for the Embodied World
Yufan Deng, Zilin Pan, Hongyu Zhang +6
cs.CVcs.AIcs.ROarXiv:2601.15282v12026
AIDev: Studying AI Coding Agents on GitHub
Hao Li, Haoxiang Zhang, Ahmed E. Hassan
cs.SEcs.AIarXiv:2602.09185v12026
AutoFigure: Generating and Refining Publication-Ready Scientific Illustrations
Minjun Zhu, Zhen Lin, Yixuan Weng +6
cs.AIcs.CLcs.CVarXiv:2602.03828v22026

Artificial Intelligence

From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents

CLI-Gym: Scalable CLI Task Generation via Agentic Environment Inversion

RubricBench: Aligning Model-Generated Rubrics with Human Standards

Large Language Models: A Survey

TermiGen: High-Fidelity Environment and Robust Trajectory Synthesis for Terminal Agents

Self-Hinting Language Models Enhance Reinforcement Learning

ViDoRe V3: A Comprehensive Evaluation of Retrieval Augmented Generation in Complex Real-World Scenarios

A Diagram Is Worth A Dozen Images

LangForce: Bayesian Decomposition of Vision Language Action Models via Latent Action Queries

Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planning

Fish Audio S2 Technical Report

Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization

Timer-S1: A Billion-Scale Time Series Foundation Model with Serial Scaling

Medical SAM3: A Foundation Model for Universal Prompt-Driven Medical Image Segmentation

OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using Agent

VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models

MemTrapBench: Benchmarking Cognitive Traps in LLM Memory Use

Benchmark Test-Time Scaling of General LLM Agents

SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks

Gradient based sample selection for online continual learning

DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing

LongCat-Flash-Thinking-2601 Technical Report

Gaia2: Benchmarking LLM Agents on Dynamic and Asynchronous Environments

Bilinear Attention Networks

Dr. Kernel: Reinforcement Learning Done Right for Triton Kernel Generations

Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition

SceneSmith: Agentic Generation of Simulation-Ready Indoor Scenes

ABot-N0: Technical Report on the VLA Foundation Model for Versatile Embodied Navigation

Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights

ARISE: Agent Reasoning with Intrinsic Skill Evolution in Hierarchical Reinforcement Learning

K-Search: LLM Kernel Generation via Co-Evolving Intrinsic World Model

The NarrativeQA Reading Comprehension Challenge

FeatureBench: Benchmarking Agentic Coding for Complex Feature Development

LoL: Longer than Longer, Scaling Video Generation to Hour

Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation

$τ$-Knowledge: Evaluating Conversational Agents over Unstructured Knowledge

Reinforcement-aware Knowledge Distillation for LLM Reasoning

Rethinking the Trust Region in LLM Reinforcement Learning

Scalable Power Sampling: Unlocking Efficient, Training-Free Reasoning for LLMs via Distribution Sharpening

Continuous Deep Q-Learning with Model-based Acceleration

Hyperagents

How AI Impacts Skill Formation

ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers

Toward Ultra-Long-Horizon Agentic Science: Cognitive Accumulation for Machine Learning Engineering

MuSiQue: Multihop Questions via Single-hop Question Composition

Anatomy of Agentic Memory: Taxonomy and Empirical Analysis of Evaluation and System Limitations

VIBEVOICE-ASR Technical Report

Large Language Model Reasoning Failures

OfficeQA Pro: An Enterprise Benchmark for End-to-End Grounded Reasoning

QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning

Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters

OmniGAIA: Towards Native Omni-Modal AI Agents

AOrchestra: Automating Sub-Agent Creation for Agentic Orchestration

DeepPlanning: Benchmarking Long-Horizon Agentic Planning with Verifiable Constraints

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding

AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security

Dr. Zero: Self-Evolving Search Agents without Training Data

Rethinking Video Generation Model for the Embodied World

AIDev: Studying AI Coding Agents on GitHub

AutoFigure: Generating and Refining Publication-Ready Scientific Illustrations