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)

24,961 to 25,020 of 27,382

Whisper-RIR-Mega: A Paired Clean-Reverberant Speech Benchmark for ASR Robustness to Room Acoustics
Mandip Goswami
eess.AScs.AIcs.LGarXiv:2603.02252v32026
Measuring What Matters: Connecting AI Ethics Evaluations to System Attributes, Hazards, and Harms
Shalaleh Rismani, Renee Shelby, Leah Davis +2
cs.HCcs.AIcs.LGarXiv:2510.10339v12025
BrowseComp-$V^3$: A Visual, Vertical, and Verifiable Benchmark for Multimodal Browsing Agents
Huanyao Zhang, Jiepeng Zhou, Bo Li +22
cs.AIarXiv:2602.12876v22026
GRIT: Teaching MLLMs to Think with Images
Yue Fan, Xuehai He, Diji Yang +6
cs.CVcs.AIcs.CLarXiv:2505.15879v22025
MerLean: An Agentic Framework for Autoformalization in Quantum Computation
Yuanjie Ren, Jinzheng Li, Yidi Qi
cs.LOcs.AIcs.ETarXiv:2602.16554v12026
BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset
Jiuhai Chen, Zhiyang Xu, Xichen Pan +10
cs.CVcs.AIarXiv:2505.09568v12025
GUI-GENESIS: Automated Synthesis of Efficient Environments with Verifiable Rewards for GUI Agent Post-Training
Yuan Cao, Dezhi Ran, Mengzhou Wu +9
cs.AIcs.LGarXiv:2602.14093v12026
From Lossy to Verified: A Provenance-Aware Tiered Memory for Agents
Qiming Zhu, Shunian Chen, Rui Yu +2
cs.DBcs.AIarXiv:2602.17913v12026
Do Reasoning Models Enhance Embedding Models?
Wun Yu Chan, Shaojin Chen, Huihao Jing +5
cs.AIcs.CLarXiv:2601.21192v12026
PEARL: Personalized Streaming Video Understanding Model
Yuanhong Zheng, Ruichuan An, Xiaopeng Lin +10
cs.CVcs.AIcs.IRarXiv:2603.20422v12026
Working Notes on Late Interaction Dynamics: Analyzing Targeted Behaviors of Late Interaction Models
Antoine Edy, Max Conti, Quentin Macé
cs.IRcs.AIcs.CLarXiv:2603.26259v22026
Autonomous Agents Coordinating Distributed Discovery Through Emergent Artifact Exchange
Fiona Y. Wang, Lee Marom, Subhadeep Pal +4
cs.AIcond-mat.dis-nncs.LGarXiv:2603.14312v12026
Generative to Agentic AI: Survey, Conceptualization, and Challenges
Johannes Schneider
cs.AIarXiv:2504.18875v12025
Hunyuan3D-Omni: A Unified Framework for Controllable Generation of 3D Assets
Team Hunyuan3D, :, Bowen Zhang +17
cs.CVcs.AIarXiv:2509.21245v12025
GeoAgent: Learning to Geolocate Everywhere with Reinforced Geographic Characteristics
Modi Jin, Yiming Zhang, Boyuan Sun +3
cs.AIarXiv:2602.12617v12026
LIBERO-X: Robustness Litmus for Vision-Language-Action Models
Guodong Wang, Chenkai Zhang, Qingjie Liu +4
cs.CVcs.AIcs.ROarXiv:2602.06556v12026
SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning
Rui Pan, Yinwei Dai, Zhihao Zhang +3
cs.LGcs.AIarXiv:2504.07891v22025
MedSAM2: Segment Anything in 3D Medical Images and Videos
Jun Ma, Zongxin Yang, Sumin Kim +6
eess.IVcs.AIcs.CVarXiv:2504.03600v12025
From Passive Observer to Active Critic: Reinforcement Learning Elicits Process Reasoning for Robotic Manipulation
Yibin Liu, Yaxing Lyu, Daqi Gao +5
cs.ROcs.AIcs.CLarXiv:2603.15600v22026
NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: Professional Image Quality Assessment (Track 1)
Guanyi Qin, Jie Liang, Bingbing Zhang +50
cs.CVcs.AIarXiv:2604.12512v12026
In-Context Reinforcement Learning for Tool Use in Large Language Models
Yaoqi Ye, Yiran Zhao, Keyu Duan +4
cs.AIarXiv:2603.08068v12026
GraphAgents: Knowledge Graph-Guided Agentic AI for Cross-Domain Materials Design
Isabella A. Stewart, Tarjei Paule Hage, Yu-Chuan Hsu +1
cs.AIcond-mat.mes-hallcond-mat.mtrl-sciarXiv:2602.07491v12026
MetaphorStar: Image Metaphor Understanding and Reasoning with End-to-End Visual Reinforcement Learning
Chenhao Zhang, Yazhe Niu, Hongsheng Li
cs.CVcs.AIcs.CYarXiv:2602.10575v12026
AIDev: Studying AI Coding Agents on GitHub
Hao Li, Haoxiang Zhang, Ahmed E. Hassan
cs.SEcs.AIarXiv:2602.09185v12026
Agentic Web: Weaving the Next Web with AI Agents
Yingxuan Yang, Mulei Ma, Yuxuan Huang +15
cs.AIcs.LGarXiv:2507.21206v12025
Prompt Flow Integrity to Prevent Privilege Escalation in LLM Agents
Juhee Kim, Woohyuk Choi, Byoungyoung Lee
cs.CRcs.AIcs.MAarXiv:2503.15547v22025
LAPO: Internalizing Reasoning Efficiency via Length-Adaptive Policy Optimization
Xingyu Wu, Yuchen Yan, Shangke Lyu +7
cs.AIcs.CLarXiv:2507.15758v22025
"Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild
Yi Liu, Zhihao Chen, Yanjun Zhang +4
cs.CRcs.AIcs.CLarXiv:2602.06547v42026
VLA-0: Building State-of-the-Art VLAs with Zero Modification
Ankit Goyal, Hugo Hadfield, Xuning Yang +2
cs.ROcs.AIarXiv:2510.13054v12025
Driving on Registers
Ellington Kirby, Alexandre Boulch, Yihong Xu +11
cs.CVcs.AIcs.ROarXiv:2601.05083v22026
HY3D-Bench: Generation of 3D Assets
Team Hunyuan3D, :, Bowen Zhang +22
cs.CVcs.AIarXiv:2602.03907v12026
RoboPocket: Improve Robot Policies Instantly with Your Phone
Junjie Fang, Wendi Chen, Han Xue +7
cs.ROcs.AIcs.LGarXiv:2603.05504v22026
INDIBATOR: Diverse and Fact-Grounded Individuality for Multi-Agent Debate in Molecular Discovery
Yunhui Jang, Seonghyun Park, Jaehyung Kim +1
cs.AIarXiv:2602.01815v12026
PhysReason: A Comprehensive Benchmark towards Physics-Based Reasoning
Xinyu Zhang, Yuxuan Dong, Yanrui Wu +6
cs.AIarXiv:2502.12054v22025
How AI Coding Agents Modify Code: A Large-Scale Study of GitHub Pull Requests
Daniel Ogenrwot, John Businge
cs.SEcs.AIarXiv:2601.17581v32026
BrandFusion: A Multi-Agent Framework for Seamless Brand Integration in Text-to-Video Generation
Zihao Zhu, Ruotong Wang, Siwei Lyu +2
cs.CVcs.AIarXiv:2603.02816v22026
MAEB: Massive Audio Embedding Benchmark
Adnan El Assadi, Isaac Chung, Chenghao Xiao +15
cs.SDcs.AIcs.CLarXiv:2602.16008v12026
Data-Efficient Curation for Multimodal Reasoning under Fixed Training Protocols
Yosub Shin, Michael Buriek, Boris Sobolev +5
cs.AIarXiv:2601.10922v22026
DUET-VLM: Dual stage Unified Efficient Token reduction for VLM Training and Inference
Aditya Kumar Singh, Hitesh Kandala, Pratik Prabhanjan Brahma +2
cs.CVcs.AIarXiv:2602.18846v22026
SPILLage: Agentic Oversharing on the Web
Jaechul Roh, Eugene Bagdasarian, Hamed Haddadi +1
cs.AIarXiv:2602.13516v12026
MantisV2: Closing the Zero-Shot Gap in Time Series Classification with Synthetic Data and Test-Time Strategies
Vasilii Feofanov, Songkang Wen, Jianfeng Zhang +2
cs.LGcs.AIarXiv:2602.17868v12026
VIOLA: Towards Video In-Context Learning with Minimal Annotations
Ryo Fujii, Hideo Saito, Ryo Hachiuma
cs.CVcs.AIarXiv:2601.15549v12026
Tokenomics: Quantifying Where Tokens Are Used in Agentic Software Engineering
Mohamad Salim, Jasmine Latendresse, SayedHassan Khatoonabadi +1
cs.SEcs.AIcs.MAarXiv:2601.14470v12026
Multimodal Multi-Agent Empowered Legal Judgment Prediction
Zhaolu Kang, Junhao Gong, Qingxi Chen +7
cs.CLcs.AIcs.CYarXiv:2601.12815v52026
MedSAM-Agent: Empowering Interactive Medical Image Segmentation with Multi-turn Agentic Reinforcement Learning
Shengyuan Liu, Liuxin Bao, Qi Yang +6
cs.CVcs.AIarXiv:2602.03320v12026
Resource-Efficient Iterative LLM-Based NAS with Feedback Memory
Xiaojie Gu, Dmitry Ignatov, Radu Timofte
cs.LGcs.AIarXiv:2603.12091v12026
Intent-Driven Dynamic Chunking: Segmenting Documents to Reflect Predicted Information Needs
Christos Koutsiaris
cs.IRcs.AIcs.CLarXiv:2602.14784v12026
MMVU: Measuring Expert-Level Multi-Discipline Video Understanding
Yilun Zhao, Lujing Xie, Haowei Zhang +16
cs.CVcs.AIcs.CLarXiv:2501.12380v12025
Open Problems in Machine Unlearning for AI Safety
Fazl Barez, Tingchen Fu, Ameya Prabhu +16
cs.LGcs.AIcs.CYarXiv:2501.04952v12025
Memory in the Age of AI Agents
Yuyang Hu, Shichun Liu, Yanwei Yue +44
cs.CLcs.AIarXiv:2512.13564v22025
What Has a Foundation Model Found? Using Inductive Bias to Probe for World Models
Keyon Vafa, Peter G. Chang, Ashesh Rambachan +1
cs.LGcs.AIarXiv:2507.06952v42025
Numina-Lean-Agent: An Open and General Agentic Reasoning System for Formal Mathematics
Junqi Liu, Zihao Zhou, Zekai Zhu +10
cs.AIarXiv:2601.14027v12026
TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation
Liao Qu, Huichao Zhang, Yiheng Liu +7
cs.CVcs.AIarXiv:2412.03069v22024
Resilient Routing: Risk-Aware Dynamic Routing in Smart Logistics via Spatiotemporal Graph Learning
Zhiming Xue, Sichen Zhao, Yalun Qi +2
cs.AIarXiv:2601.13632v22026
A Survey of Vibe Coding with Large Language Models
Yuyao Ge, Lingrui Mei, Zenghao Duan +12
cs.AIarXiv:2510.12399v22025
PRISM: Learning Design Knowledge from Data for Stylistic Design Improvement
Huaxiaoyue Wang, Sunav Choudhary, Franck Dernoncourt +2
cs.AIarXiv:2601.11747v12026
Recovered in Translation: Efficient Pipeline for Automated Translation of Benchmarks and Datasets
Hanna Yukhymenko, Anton Alexandrov, Martin Vechev
cs.CLcs.AIcs.LGarXiv:2602.22207v12026
LOCA-bench: Benchmarking Language Agents Under Controllable and Extreme Context Growth
Weihao Zeng, Yuzhen Huang, Junxian He
cs.AIarXiv:2602.07962v12026
Chain of Mindset: Reasoning with Adaptive Cognitive Modes
Tianyi Jiang, Arctanx An, Hengyi Feng +12
cs.AIarXiv:2602.10063v22026
3D-ViTac: Learning Fine-Grained Manipulation with Visuo-Tactile Sensing
Binghao Huang, Yixuan Wang, Xinyi Yang +2
cs.ROcs.AIcs.LGarXiv:2410.24091v22024

Artificial Intelligence

Whisper-RIR-Mega: A Paired Clean-Reverberant Speech Benchmark for ASR Robustness to Room Acoustics

Measuring What Matters: Connecting AI Ethics Evaluations to System Attributes, Hazards, and Harms

BrowseComp-$V^3$: A Visual, Vertical, and Verifiable Benchmark for Multimodal Browsing Agents

GRIT: Teaching MLLMs to Think with Images

MerLean: An Agentic Framework for Autoformalization in Quantum Computation

BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset

GUI-GENESIS: Automated Synthesis of Efficient Environments with Verifiable Rewards for GUI Agent Post-Training

From Lossy to Verified: A Provenance-Aware Tiered Memory for Agents

Do Reasoning Models Enhance Embedding Models?

PEARL: Personalized Streaming Video Understanding Model

Working Notes on Late Interaction Dynamics: Analyzing Targeted Behaviors of Late Interaction Models

Autonomous Agents Coordinating Distributed Discovery Through Emergent Artifact Exchange

Generative to Agentic AI: Survey, Conceptualization, and Challenges

Hunyuan3D-Omni: A Unified Framework for Controllable Generation of 3D Assets

GeoAgent: Learning to Geolocate Everywhere with Reinforced Geographic Characteristics

LIBERO-X: Robustness Litmus for Vision-Language-Action Models

SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning

MedSAM2: Segment Anything in 3D Medical Images and Videos

From Passive Observer to Active Critic: Reinforcement Learning Elicits Process Reasoning for Robotic Manipulation

NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: Professional Image Quality Assessment (Track 1)

In-Context Reinforcement Learning for Tool Use in Large Language Models

GraphAgents: Knowledge Graph-Guided Agentic AI for Cross-Domain Materials Design

MetaphorStar: Image Metaphor Understanding and Reasoning with End-to-End Visual Reinforcement Learning

AIDev: Studying AI Coding Agents on GitHub

Agentic Web: Weaving the Next Web with AI Agents

Prompt Flow Integrity to Prevent Privilege Escalation in LLM Agents

LAPO: Internalizing Reasoning Efficiency via Length-Adaptive Policy Optimization

"Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild

VLA-0: Building State-of-the-Art VLAs with Zero Modification

Driving on Registers

HY3D-Bench: Generation of 3D Assets

RoboPocket: Improve Robot Policies Instantly with Your Phone

INDIBATOR: Diverse and Fact-Grounded Individuality for Multi-Agent Debate in Molecular Discovery

PhysReason: A Comprehensive Benchmark towards Physics-Based Reasoning

How AI Coding Agents Modify Code: A Large-Scale Study of GitHub Pull Requests

BrandFusion: A Multi-Agent Framework for Seamless Brand Integration in Text-to-Video Generation

MAEB: Massive Audio Embedding Benchmark

Data-Efficient Curation for Multimodal Reasoning under Fixed Training Protocols

DUET-VLM: Dual stage Unified Efficient Token reduction for VLM Training and Inference

SPILLage: Agentic Oversharing on the Web

MantisV2: Closing the Zero-Shot Gap in Time Series Classification with Synthetic Data and Test-Time Strategies

VIOLA: Towards Video In-Context Learning with Minimal Annotations

Tokenomics: Quantifying Where Tokens Are Used in Agentic Software Engineering

Multimodal Multi-Agent Empowered Legal Judgment Prediction

MedSAM-Agent: Empowering Interactive Medical Image Segmentation with Multi-turn Agentic Reinforcement Learning

Resource-Efficient Iterative LLM-Based NAS with Feedback Memory

Intent-Driven Dynamic Chunking: Segmenting Documents to Reflect Predicted Information Needs

MMVU: Measuring Expert-Level Multi-Discipline Video Understanding

Open Problems in Machine Unlearning for AI Safety

Memory in the Age of AI Agents

What Has a Foundation Model Found? Using Inductive Bias to Probe for World Models

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

TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation

Resilient Routing: Risk-Aware Dynamic Routing in Smart Logistics via Spatiotemporal Graph Learning

A Survey of Vibe Coding with Large Language Models

PRISM: Learning Design Knowledge from Data for Stylistic Design Improvement

Recovered in Translation: Efficient Pipeline for Automated Translation of Benchmarks and Datasets

LOCA-bench: Benchmarking Language Agents Under Controllable and Extreme Context Growth

Chain of Mindset: Reasoning with Adaptive Cognitive Modes

3D-ViTac: Learning Fine-Grained Manipulation with Visuo-Tactile Sensing