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)

14,701 to 14,760 of 15,198

Multi-Head Attention Residuals
Cheng Luo, Zefan Cai, Junjie Hu
cs.AIarXiv:2607.27230v22026
LAPF: LLM-Agent-Based Path Finder Using the UAVScenes Dataset
Yousef Emami, Mohammadhossein Homaei, Hao Zhou +3
cs.ROcs.AIarXiv:2608.15175v12026
Auto Research with Specialist Agents Develops Effective and Non-Trivial Training Recipes
Jingjie Ning, Xiaochuan Li, Ji Zeng +2
cs.MAcs.AIarXiv:2605.05724v12026
Scale-Consistent Posterior Dynamics for Diffusion Inverse Problems
Zhaoqiang Liu, Tongyao Pang, Ruibing Wang +1
stat.MLcs.AIcs.LGarXiv:2608.15144v12026
Rubric-based On-policy Distillation
Junfeng Fang, Zhepei Hong, Mao Zheng +7
cs.LGcs.AIarXiv:2605.07396v12026
$D^{2}R^{2}$: Discrete Diffusion with Regulation Reinforcement for Single-Cell Perturbation Prediction
Ninghan Fan, Qi Liu, Xunuo Zhu +9
cs.AIarXiv:2608.15288v12026
Toward Scalable Terminal Task Synthesis via Skill Graphs
Zhiyuan Fan, Tinghao Yu, Yuanjun Cai +8
cs.AIarXiv:2604.25727v12026
Visual-Seeker: Towards Visual-Native Multimodal Agentic Search via Active Visual Reasoning
Zhengbo Zhang, Changtao Miao, Jinbo Su +10
cs.AIarXiv:2606.15231v12026
FORTIS: Benchmarking Over-Privilege in Agent Skills
Shawn Li, Chenxiao Yu, Han Wang +8
cs.AIarXiv:2605.09163v32026
AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discovery
Guiyao Tie, Jiawen Shi, Dingjie Song +20
cs.AIarXiv:2605.23204v12026
OpenSeeker-v2: Pushing the Limits of Search Agents with Informative and High-Difficulty Trajectories
Yuwen Du, Rui Ye, Shuo Tang +4
cs.AIcs.CLarXiv:2605.04036v12026
Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence
NVIDIA, :, Amala Sanjay Deshmukh +216
cs.LGcs.AIcs.CVarXiv:2604.24954v22026
Harnessing LLM Agents with Skill Programs
Hongjun Liu, Yifei Ming, Shafiq Joty +1
cs.AIarXiv:2605.17734v12026
ENTLORE: A Graph-Grounded Benchmark for Latent Organizational Reasoning in Enterprise Question Answering
Akrin Zheng, Alexander Wu, Alaia Liu
cs.IRcs.AIcs.CLarXiv:2608.10679v22026
On the Geometry of On-Policy Distillation
Zhennan Shen, Yanshu Li, Qingyu Yin +6
cs.LGcs.AIarXiv:2606.07082v32026
L2P: Unlocking Latent Potential for Pixel Generation
Zhennan Chen, Junwei Zhu, Xu Chen +7
cs.CVcs.AIarXiv:2605.12013v12026
MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery
Shangheng Du, Xiangchao Yan, Jinxin Shi +11
cs.AIcs.CLarXiv:2606.06473v12026
Useful Memories Become Faulty When Continuously Updated by LLMs
Dylan Zhang, Yanshan Lin, Zhengkun Wu +4
cs.AIarXiv:2605.12978v12026
Model Merging Scaling Laws in Large Language Models
Yuanyi Wang, Yanggan Gu, Yiming Zhang +6
cs.AIarXiv:2509.24244v42025
AR-VLA: True Autoregressive Action Expert for Vision-Language-Action Models
Yutong Hu, Jan-Nico Zaech, Nikolay Nikolov +6
cs.ROcs.AIarXiv:2603.10126v22026
Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
NVIDIA, :, Aaron Blakeman +571
cs.CLcs.AIcs.LGarXiv:2606.15007v12026
Reward Hacking in Rubric-Based Reinforcement Learning
Anas Mahmoud, MohammadHossein Rezaei, Zihao Wang +3
cs.AIarXiv:2605.12474v12026
Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information
Guobin Shen, Xiang Cheng, Chenxiao Zhao +4
cs.LGcs.AIcs.CLarXiv:2605.11609v12026
SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agents
Bingchen Zhao, Dhruv Srikanth, Yuxiang Wu +1
cs.SEcs.AIcs.CLarXiv:2605.21384v12026
HiL-Bench (Human-in-Loop Benchmark): Do Agents Know When to Ask for Help?
Tu Trinh, Mohamed Elfeki, Guangze Luo +9
cs.AIarXiv:2604.09408v42026
From Model Scaling to System Scaling: Scaling the Harness in Agentic AI
Shangding Gu
cs.AIcs.LGarXiv:2605.26112v12026
Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills
Chuan Xiao, Zhengbo Jiao, Shaobo Wang +5
cs.SEcs.AIarXiv:2606.07412v12026
TerminalWorld: Benchmarking Agents on Real-World Terminal Tasks
Zhaoyang Chu, Jiarui Hu, Xingyu Jiang +8
cs.AIarXiv:2605.22535v12026
When to Trust Imagination: Adaptive Action Execution for World Action Models
Rui Wang, Yue Zhang, Jiehong Lin +4
cs.ROcs.AIarXiv:2605.06222v22026
OpenComputer: Verifiable Software Worlds for Computer-Use Agents
Jinbiao Wei, Qianran Ma, Yilun Zhao +4
cs.AIcs.SEarXiv:2605.19769v12026
Claw-Eval-Live: A Live Agent Benchmark for Evolving Real-World Workflows
Chenxin Li, Zhengyang Tang, Mingxin Huang +8
cs.SEcs.AIarXiv:2604.28139v22026
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
Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning
Yaorui Shi, Yuxin Chen, Zhengxi Lu +6
cs.AIarXiv:2605.06130v32026
PhysicianBench: Evaluating LLM Agents in Real-World EHR Environments
Ruoqi Liu, Imran Q. Mohiuddin, Austin J. Schoeffler +10
cs.AIarXiv:2605.02240v12026
ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop
Yining Hong, Jiageng Liu, Han Yin +5
cs.CVcs.AIcs.CLarXiv:2605.18746v22026
iWorld-Bench: A Benchmark for Interactive World Models with a Unified Action Generation Framework
Jianjie Fang, Yingshan Lei, Qin Wan +8
cs.CVcs.AIarXiv:2605.03941v22026
AHA-WAM:Asynchronous Horizon-Adaptive World-Action Modeling with Observation-Guided Context Routing
Jisong Cai, Long Ling, Shiwei Chu +10
cs.ROcs.AIcs.CVarXiv:2606.09811v12026
Gathered, Not Admitted: How Attention Brings a Latent Variable into Verbalizable Form
Parsa Mazaheri
cs.AIcs.CLarXiv:2608.15022v12026
NaviDC-OCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
Peng Cai, Zhaofan Zou, Shifa Liu +6
cs.CVcs.AIarXiv:2608.12898v12026
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
CG-GLORE: A Conjugate Gradient-Based Global-Local Regularization Network for Sparse-View CT Reconstruction
Tran Xuan Hieu Le, Doanh C. Bui, Vu Trung Duong Le +5
cs.CVcs.AIarXiv:2608.15246v12026
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
From LLM Inference to Agentic Workloads: Characterization and Implications for Serving Systems
Chaokun Chang, Yukun Zhou, Kaihua Fu +10
cs.OScs.AIcs.DCarXiv:2608.15127v12026
FedImp: Enhancing Federated Learning Convergence with Impurity-Based Weighting
Hai Anh Tran, Cuong Ta, Truong X. Tran
cs.LGcs.AIarXiv:2608.14654v12026
GraphLoom: Reliability-Calibrated Graph Evidence Routing for Multimodal KG-RAG
Zafar Ali, Asad Khan, Aalia Malik +1
cs.AIarXiv:2608.15056v12026
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
GATTA: Graph Active Learning with Test-Time Augmentation
Zsombor Bánfi, András Gézsi, András Formanek
cs.LGcs.AIarXiv:2608.15084v12026
DualMiT-Net: Local-Global Transformer-Convolutional Fusion for Breast Mass Segmentation in Mammographic Regions of Interest
Alibek Kamiluly, Milana Muratova, Yash Patel +1
cs.CVcs.AIcs.LGarXiv:2608.15019v12026
MetaReason: Precise Interleaved Multimodal Reasoning via Editing Meta Information for Solving Geometry Problems
Penghao Yin, Haomin Wang, Qihong Tang +3
cs.CVcs.AIcs.MMarXiv:2608.15006v12026
RETRACE: Resilience-Guided Trait-Conditioned Craving Estimation from Wearable Physiology in Opioid Use Disorder
Yi Xiao, Harshit Sharma, Dessa Bergen-Cico +1
cs.AIarXiv:2608.14947v12026
Divergent-Convergent Reasoning: Scaling Test-Time Compute through Structured Solution Synthesis
Bo Wen, Yuhao Chen, Erhan Bilal +3
cs.AIarXiv:2608.15303v12026
LongRCA Bench: Diagnosing Responsible Roles and Root Causes in Long-Horizon Agent Failures
Yunfei Zhang, Boyu Feng, Changhua Pei +14
cs.AIcs.SEarXiv:2608.15242v12026
A Unified Backbone--Expert Framework with Relation-Token and Residual--Classifier Interfaces for Automatic Modulation Recognition
Zhixiang Deng, Houbiao Li, Zongyong Cui
cs.CVcs.AIarXiv:2608.15160v12026
Generative data assimilation highlights fronts as key regulators of ocean energy cascade
Scott A. Martin, Georgy E. Manucharyan, Patrice Klein
physics.ao-phcs.AIarXiv:2608.14955v12026
Prior Audit-Repair Context Shifts LLM Verifier Thresholds Toward Leniency
Parsa Mazaheri, Kasra Mazaheri
cs.AIcs.CLarXiv:2608.16003v12026
MoE Router-Guided Clustering for Heterogeneous Federated Instruction Tuning
Ankita Sharma, Bahar Farahani, Sanaz Rahimi Moosavi +3
cs.AIarXiv:2608.15311v12026
PhaseLoRA: Control-Regime-Conditioned Low-Rank Adaptation for Continuous-Action Vision-Language-Action Policies
Yufei Guo, Yinan Wu, Haoran Duan +2
cs.ROcs.AIarXiv:2608.15285v12026
Understanding Cognition-Induced Risks in Agentic AI Systems
Guanchu Wang, Qinuo Li, Mengnan Du +2
cs.AIarXiv:2608.15304v12026
VibeWorlding: Can Multimodal Agents Construct 3D Open Worlds End-to-End?
Yansong Ning, Jingwen Ye, Zhongkai Wu +5
cs.AIarXiv:2608.15265v12026

Artificial Intelligence

Multi-Head Attention Residuals

LAPF: LLM-Agent-Based Path Finder Using the UAVScenes Dataset

Auto Research with Specialist Agents Develops Effective and Non-Trivial Training Recipes

Scale-Consistent Posterior Dynamics for Diffusion Inverse Problems

Rubric-based On-policy Distillation

$D^{2}R^{2}$: Discrete Diffusion with Regulation Reinforcement for Single-Cell Perturbation Prediction

Toward Scalable Terminal Task Synthesis via Skill Graphs

Visual-Seeker: Towards Visual-Native Multimodal Agentic Search via Active Visual Reasoning

FORTIS: Benchmarking Over-Privilege in Agent Skills

AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discovery

OpenSeeker-v2: Pushing the Limits of Search Agents with Informative and High-Difficulty Trajectories

Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence

Harnessing LLM Agents with Skill Programs

ENTLORE: A Graph-Grounded Benchmark for Latent Organizational Reasoning in Enterprise Question Answering

On the Geometry of On-Policy Distillation

L2P: Unlocking Latent Potential for Pixel Generation

MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery

Useful Memories Become Faulty When Continuously Updated by LLMs

Model Merging Scaling Laws in Large Language Models

AR-VLA: True Autoregressive Action Expert for Vision-Language-Action Models

Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

Reward Hacking in Rubric-Based Reinforcement Learning

Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information

SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agents

HiL-Bench (Human-in-Loop Benchmark): Do Agents Know When to Ask for Help?

From Model Scaling to System Scaling: Scaling the Harness in Agentic AI

Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills

TerminalWorld: Benchmarking Agents on Real-World Terminal Tasks

When to Trust Imagination: Adaptive Action Execution for World Action Models

OpenComputer: Verifiable Software Worlds for Computer-Use Agents

Claw-Eval-Live: A Live Agent Benchmark for Evolving Real-World Workflows

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

Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning

PhysicianBench: Evaluating LLM Agents in Real-World EHR Environments

ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop

iWorld-Bench: A Benchmark for Interactive World Models with a Unified Action Generation Framework

AHA-WAM:Asynchronous Horizon-Adaptive World-Action Modeling with Observation-Guided Context Routing

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

NaviDC-OCR: Navigating Document Parsing Across Digital and Camera-Captured Documents

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

CG-GLORE: A Conjugate Gradient-Based Global-Local Regularization Network for Sparse-View CT Reconstruction

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

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

From LLM Inference to Agentic Workloads: Characterization and Implications for Serving Systems

FedImp: Enhancing Federated Learning Convergence with Impurity-Based Weighting

GraphLoom: Reliability-Calibrated Graph Evidence Routing for Multimodal KG-RAG

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

GATTA: Graph Active Learning with Test-Time Augmentation

DualMiT-Net: Local-Global Transformer-Convolutional Fusion for Breast Mass Segmentation in Mammographic Regions of Interest

MetaReason: Precise Interleaved Multimodal Reasoning via Editing Meta Information for Solving Geometry Problems

RETRACE: Resilience-Guided Trait-Conditioned Craving Estimation from Wearable Physiology in Opioid Use Disorder

Divergent-Convergent Reasoning: Scaling Test-Time Compute through Structured Solution Synthesis

LongRCA Bench: Diagnosing Responsible Roles and Root Causes in Long-Horizon Agent Failures

A Unified Backbone--Expert Framework with Relation-Token and Residual--Classifier Interfaces for Automatic Modulation Recognition

Generative data assimilation highlights fronts as key regulators of ocean energy cascade

Prior Audit-Repair Context Shifts LLM Verifier Thresholds Toward Leniency

MoE Router-Guided Clustering for Heterogeneous Federated Instruction Tuning

PhaseLoRA: Control-Regime-Conditioned Low-Rank Adaptation for Continuous-Action Vision-Language-Action Policies

Understanding Cognition-Induced Risks in Agentic AI Systems

VibeWorlding: Can Multimodal Agents Construct 3D Open Worlds End-to-End?