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)

14,641 to 14,700 of 15,326

Do Assessment Instruments Measure the Same Thing for Humans and LLMs? A Latent Structure Analysis
Alona Strugatski, Licol Zeinfeld, Giora Alexandron
cs.HCcs.AIcs.CLarXiv:2608.15630v12026
NanoResearch: Co-Evolving Skills, Memory, and Policy for Personalized Research Automation
Jinhang Xu, Qiyuan Zhu, Yujun Wu +11
cs.AIarXiv:2605.10813v22026
Auto-Rubric as Reward: From Implicit Preferences to Explicit Multimodal Generative Criteria
Juanxi Tian, Fengyuan Liu, Jiaming Han +6
cs.AIarXiv:2605.08354v12026
AeroCopilotBench: A Two-Tier Benchmark for Evaluating LLM Agents as Aviation Copilots in an Interactive Virtual Cockpit Environment
Yuchen Yuan, Zhenghuang Wu, Yuangan Li +2
cs.AIarXiv:2608.16349v12026
Baseline-Relative Counterfactual Refinement for Bit-Aware Visual Token Communication
Jia Guo, Xiaohan Zhao, Changwang Liu +4
cs.AIarXiv:2608.16192v12026
OpenSTBench: Beyond Semantic Evaluation for Speech Translation
Yanjie An, Yuxiang Zhao, Yichi Zhang +5
eess.AScs.AIarXiv:2605.30792v12026
Comprehensive Benchmarking of Deep Learning Architectures for Lung Cancer Histopathology
Hadi Hasan, Safaa Salman, Lama Sleem +2
cs.CVcs.AIarXiv:2608.15915v12026
Don't Drop the BATON: Long-Horizon Robot Manipulation via Agentic Subtask Exploration and Transition-aware Memory
Bingxin Xu, Yuzhang Shang, Emilio Ferrara
cs.ROcs.AIcs.CVarXiv:2608.16889v12026
Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs
Siyuan Huang, Xiaoye Qu, Yafu Li +6
cs.CVcs.AIarXiv:2605.00814v22026
Missing Old Logits in Asynchronous Agentic RL: Semantic Mismatch and Repair Methods for Off-Policy Correction
Zhong Guan, Yongjian Guo, Haoran Sun +5
cs.LGcs.AIarXiv:2605.12070v22026
SkCC: Portable and Secure Skill Compilation for Cross-Framework LLM Agents
Yipeng Ouyang, Yi Xiao, Yuhao Gu +1
cs.CRcs.AIarXiv:2605.03353v42026
HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution
Dongming Jiang, Yi Li, Guanpeng Li +2
cs.AIarXiv:2605.09942v12026
Diagnosing Dense Same-Class Attribute Misbinding in Large Vision-Language Models
Yuanzhi Xu, Qian Gao, Jun Fan +4
cs.CVcs.AIarXiv:2608.16805v12026
JoyAI-Image: Awaking Spatial Intelligence in Unified Multimodal Understanding and Generation
Lin Song, Wenbo Li, Guoqing Ma +16
cs.GRcs.AIcs.CLarXiv:2605.04128v22026
Agent-BRACE: Decoupling Beliefs from Actions in Long-Horizon Tasks via Verbalized State Uncertainty
Joykirat Singh, Zaid Khan, Archiki Prasad +5
cs.CLcs.AIarXiv:2605.11436v12026
Steering the Flow: Inverting Face Recognition Models via Gradient-Guided Flow Matching
Ye Lu, Shen Wang, Zhaoyang Zhang +4
cs.CVcs.AIcs.CRarXiv:2608.16791v12026
MISA: Mixture of Indexer Sparse Attention for Long-Context LLM Inference
Ruijie Zhou, Fanxu Meng, Yufei Xu +4
cs.LGcs.AIarXiv:2605.07363v12026
HarmTrace: Anchor-Calibrated Decoupled Optimization for Fine-Grained Target Identification in Harmful Memes
Yujia Li, Yiqun Zhang, Zihan Cheng +7
cs.CVcs.AIarXiv:2608.16622v12026
Graph Machine Learning: An Opportunity for Power Systems
Martin Sadric, Sebastian Pütz, Christian Nauck +4
cs.LGcs.AIcs.CEarXiv:2608.16494v12026
RagGAD: Rationale-Aware Conditional Gaussian Mixture Normalizing Flow for Unsupervised Graph Anomaly Detection
Junxin Lu, Jing Zhao, Shiliang Sun
cs.LGcs.AIarXiv:2608.16018v12026
ATLAS: Scaffold-Free Algorithm Synthesis by LLMs via Embedding-Guided Quality-Diversity Search
Danial Yazdani, Mohammad Nabi Omidvar, Yuan Sun +2
cs.AIcs.NEarXiv:2608.15546v22026
Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems
Shihao Qi, Jie Ma, Rui Xing +15
cs.AIarXiv:2605.14892v22026
Model-Adaptive Tool Necessity Reveals the Knowing-Doing Gap in LLM Tool Use
Yize Cheng, Chenrui Fan, Mahdi JafariRaviz +2
cs.AIarXiv:2605.14038v22026
AgentFugue: Agent Scaling for Long-Horizon Tasks through Collective Reasoning
Yuyang Hu, Hongjin Qian, Shuting Wang +5
cs.AIcs.CLarXiv:2605.24486v12026
Contrastive Energy Fields for Inference-Time Procedure Planning in Instructional Videos
Mohamed Afham, Christoph Reich, Oliver Hahn +2
cs.CVcs.AIarXiv:2608.16457v12026
Graph Neural Assisted Actor-Critic for Latency-Efficient Edge Vision System
Alam Noor, Luis Almeida, Kai Li +3
cs.CVcs.AIarXiv:2608.16142v12026
MUSE: An Interactive Meta-Agent for Understanding and Steering LLM-powered Data Science Systems
Wei-Hao Chen, Weixi Tong, Yuan Tian +2
cs.HCcs.AIarXiv:2608.16181v12026
AutoLab: Can Frontier Models Solve Long-Horizon Auto Research and Engineering Tasks?
Zhangchen Xu, Junda Chen, Yue Huang +16
cs.AIcs.LGarXiv:2606.05080v12026
Online Skill Learning for Web Agents via State-Grounded Dynamic Retrieval
Jiaxi Li, Ke Deng, Yun Wang +5
cs.AIarXiv:2606.04391v12026
A Cognitively Motivated Multidimensional Framework for Evaluating Metaphor Explanations
Ana Naveriani, Jakob Suchan, Stefano Zoia +3
cs.CLcs.AIarXiv:2608.15828v12026
Boosting Omni-Modal Language Models: Staged Post-Training with Visually Debiased Evaluation
Che Liu, Lichao Ma, Xiangyu Tony Zhang +4
cs.MMcs.AIcs.CVarXiv:2605.12034v22026
KVServe: Service-Aware KV Cache Compression for Communication-Efficient Disaggregated LLM Serving
Zedong Liu, Xinyang Ma, Dejun Luo +9
cs.DCcs.AIcs.NIarXiv:2605.13734v12026
Toward AI-Friendly Cartography: Understanding How Color Design Influences Foundation Model Spatial Reasoning on Sequential Choropleth Maps
Yonghe Sun, Zhenjia Liu, Hua Liao +4
cs.AIarXiv:2608.15736v12026
Look Before You Leap: Autonomous Exploration for LLM Agents
Ziang Ye, Wentao Shi, Yuxin Liu +6
cs.AIcs.CLarXiv:2605.16143v12026
RoPE Distinguishes Neither Positions Nor Tokens in Long Contexts, Provably
Yufeng Du, Phillip Harris, Minyang Tian +5
cs.CLcs.AIcs.LGarXiv:2605.15514v12026
Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps
Yanke Zhou, Yiduo Li, Hanlin Tang +6
cs.CLcs.AIarXiv:2605.16928v22026
ALKEMIE Agent: an autonomous platform for computational materials design
Hongfu Huang, Yuzhe Li, Ao Xu +14
cond-mat.mtrl-scics.AIarXiv:2608.15776v12026
HINT-SD: Targeted Hindsight Self-Distillation for Long-Horizon Agents
Woongyeng Yeo, Yumin Choi, Taekyung Ki +1
cs.LGcs.AIcs.CLarXiv:2605.17873v12026
Generative Recursive Reasoning
Junyeob Baek, Mingyu Jo, Minsu Kim +3
cs.AIarXiv:2605.19376v22026
Visualizing Uncertainty-to-Action Composition for Human Oversight
Chisom Anyabolu, Akshat Dubey, Georges Hattab
cs.HCcs.AIarXiv:2608.16428v12026
HiPHI: A Large-Scale Benchmark for High-Precision Human Motion and Object-Interaction
Jiahao Ji, Ji Ma, Runhan Zhang +12
cs.ROcs.AIarXiv:2608.16222v12026
A Policy Algebra for Trust-Preserving Agentic AI Execution
Bhaskar Tripathi, Anurag Kumar, Ramendra Kumar +1
cs.AIarXiv:2608.16402v12026
Assessing LLMs' mathematical abilities requires understanding the various mechanisms of mathematical creativity
Silvère Gangloff
cs.AImath.HOarXiv:2608.16118v12026
QUMem: Personalized Memory for Query-Conditioned User-State Inference in LLM Agents
Heng Wang, Yifei Li, Lingling Zhang +4
cs.CLcs.AIarXiv:2608.16168v12026
From Corpora to Co-Evolving Capabilities: Capability-Centric Data Design for Generalist Image Generation
Xingjian Wang, Zhao Wang, Taihang Hu +14
cs.CVcs.AIarXiv:2608.18076v12026
Counting Documents Is Not Counting Text: Unit Bias in Web-PDF Corpus Statistics
Luca Foppiano
cs.CLcs.AIarXiv:2608.16390v12026
Dynamic Multi-Byte Prediction With Hierarchical Language Models
Abraham Toluwase Owodunni, Chibuzor Okocha, Christan Grant +2
cs.AIarXiv:2608.15454v12026
Your Agents Are Aging Too: Agent Lifespan Engineering for Deployed Systems
Jianing Zhu, Yeonju Ro, John Robertson +5
cs.AIcs.CLcs.MAarXiv:2605.26302v12026
VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions
Yuxin Chen, Yi Zhang, Zhengzhou Cai +11
cs.AIarXiv:2605.27141v12026
PhoneWorld: Scaling Phone-Use Agent Environments
Yuxuan Liu, Xin Lai, Junyi Li +21
cs.CLcs.AIcs.LGarXiv:2605.29486v22026
COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation
Tianyi Zhou, Dongrui Liu, Leitao Yuan +2
cs.AIcs.CLcs.LGarXiv:2605.31264v12026
TRON: Targeted Rule-Verifiable Online Environments for Visual Reasoning RL
Tianze Yang, Yucheng Shi, Ruitong Sun +3
cs.AIarXiv:2606.01599v12026
Walk Before You Run: The Importance of Data Exploration for Data Analysis Agents
Yike Yuan, Virum Ranka, Tina Lasisi +1
cs.DBcs.AIarXiv:2608.16045v12026
When State Becomes an Attack Surface: State-Semantic Injection in LLM-Driven Embodied Agents
Jiawei Liu, Jiacheng Guo, Tian Zhang +7
cs.ROcs.AIarXiv:2608.16806v12026
NICE: Scale-Stable Perturbations for Graph Neural Network Explanations via Noise Corruption
Ziluowen Luo, Jun Yin, Ruochen Liu +4
cs.LGcs.AIarXiv:2608.16038v22026
Software Engineering for AI-driven Building Operation
Philipp Zech, Sascha Hammes, Johannes Weninger +2
cs.SEcs.AIarXiv:2608.16237v12026
Learning to Unlearn: Machine Unlearning via Learning the Unlearning Behaviors
Hang Zhang, Kaifeng Zhang, Yixiao Ma +3
cs.LGcs.AIarXiv:2608.16700v12026
Matched Outcomes, Divergent Gaze: How Foveated MLLMs Search Compared to Humans
Mohamed Amine Kerkouri, Marouane Tliba, Aladine Chetouani +2
cs.CVcs.AIcs.CLarXiv:2608.16514v12026
Hypergraph-based Multimodal Retrieval-Augmented Generation with Incremental Refinement
Shenao Chen, Yidan Xu, Xiangmin Han +5
cs.AIarXiv:2608.16628v12026
StartupBench: Benchmarking General-Purpose Agents on Market-Validated End-to-End Workflows
Liya Zhu, Xin Ma, Tao Liu +35
cs.AIarXiv:2608.17800v12026

Artificial Intelligence

Do Assessment Instruments Measure the Same Thing for Humans and LLMs? A Latent Structure Analysis

NanoResearch: Co-Evolving Skills, Memory, and Policy for Personalized Research Automation

Auto-Rubric as Reward: From Implicit Preferences to Explicit Multimodal Generative Criteria

AeroCopilotBench: A Two-Tier Benchmark for Evaluating LLM Agents as Aviation Copilots in an Interactive Virtual Cockpit Environment

Baseline-Relative Counterfactual Refinement for Bit-Aware Visual Token Communication

OpenSTBench: Beyond Semantic Evaluation for Speech Translation

Comprehensive Benchmarking of Deep Learning Architectures for Lung Cancer Histopathology

Don't Drop the BATON: Long-Horizon Robot Manipulation via Agentic Subtask Exploration and Transition-aware Memory

Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs

Missing Old Logits in Asynchronous Agentic RL: Semantic Mismatch and Repair Methods for Off-Policy Correction

SkCC: Portable and Secure Skill Compilation for Cross-Framework LLM Agents

HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution

Diagnosing Dense Same-Class Attribute Misbinding in Large Vision-Language Models

JoyAI-Image: Awaking Spatial Intelligence in Unified Multimodal Understanding and Generation

Agent-BRACE: Decoupling Beliefs from Actions in Long-Horizon Tasks via Verbalized State Uncertainty

Steering the Flow: Inverting Face Recognition Models via Gradient-Guided Flow Matching

MISA: Mixture of Indexer Sparse Attention for Long-Context LLM Inference

HarmTrace: Anchor-Calibrated Decoupled Optimization for Fine-Grained Target Identification in Harmful Memes

Graph Machine Learning: An Opportunity for Power Systems

RagGAD: Rationale-Aware Conditional Gaussian Mixture Normalizing Flow for Unsupervised Graph Anomaly Detection

ATLAS: Scaffold-Free Algorithm Synthesis by LLMs via Embedding-Guided Quality-Diversity Search

Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems

Model-Adaptive Tool Necessity Reveals the Knowing-Doing Gap in LLM Tool Use

AgentFugue: Agent Scaling for Long-Horizon Tasks through Collective Reasoning

Contrastive Energy Fields for Inference-Time Procedure Planning in Instructional Videos

Graph Neural Assisted Actor-Critic for Latency-Efficient Edge Vision System

MUSE: An Interactive Meta-Agent for Understanding and Steering LLM-powered Data Science Systems

AutoLab: Can Frontier Models Solve Long-Horizon Auto Research and Engineering Tasks?

Online Skill Learning for Web Agents via State-Grounded Dynamic Retrieval

A Cognitively Motivated Multidimensional Framework for Evaluating Metaphor Explanations

Boosting Omni-Modal Language Models: Staged Post-Training with Visually Debiased Evaluation

KVServe: Service-Aware KV Cache Compression for Communication-Efficient Disaggregated LLM Serving

Toward AI-Friendly Cartography: Understanding How Color Design Influences Foundation Model Spatial Reasoning on Sequential Choropleth Maps

Look Before You Leap: Autonomous Exploration for LLM Agents

RoPE Distinguishes Neither Positions Nor Tokens in Long Contexts, Provably

Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps

ALKEMIE Agent: an autonomous platform for computational materials design

HINT-SD: Targeted Hindsight Self-Distillation for Long-Horizon Agents

Generative Recursive Reasoning

Visualizing Uncertainty-to-Action Composition for Human Oversight

HiPHI: A Large-Scale Benchmark for High-Precision Human Motion and Object-Interaction

A Policy Algebra for Trust-Preserving Agentic AI Execution

Assessing LLMs' mathematical abilities requires understanding the various mechanisms of mathematical creativity

QUMem: Personalized Memory for Query-Conditioned User-State Inference in LLM Agents

From Corpora to Co-Evolving Capabilities: Capability-Centric Data Design for Generalist Image Generation

Counting Documents Is Not Counting Text: Unit Bias in Web-PDF Corpus Statistics

Dynamic Multi-Byte Prediction With Hierarchical Language Models

Your Agents Are Aging Too: Agent Lifespan Engineering for Deployed Systems

VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions

PhoneWorld: Scaling Phone-Use Agent Environments

COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation

TRON: Targeted Rule-Verifiable Online Environments for Visual Reasoning RL

Walk Before You Run: The Importance of Data Exploration for Data Analysis Agents

When State Becomes an Attack Surface: State-Semantic Injection in LLM-Driven Embodied Agents

NICE: Scale-Stable Perturbations for Graph Neural Network Explanations via Noise Corruption

Software Engineering for AI-driven Building Operation

Learning to Unlearn: Machine Unlearning via Learning the Unlearning Behaviors

Matched Outcomes, Divergent Gaze: How Foveated MLLMs Search Compared to Humans

Hypergraph-based Multimodal Retrieval-Augmented Generation with Incremental Refinement

StartupBench: Benchmarking General-Purpose Agents on Market-Validated End-to-End Workflows