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)

3,961 to 4,020 of 15,235

OPSDL: On-Policy Self-Distillation for Long-Context Language Models
Xinsen Zhang, Zhenkai Ding, Tianjun Pan +4
cs.CLcs.AIarXiv:2604.17535v12026
TAAL: Mitigating Early Beam Pruning in Generative Recommendation via Temporal Autoregressive Alignment
Lianjie Li, Zhiying Tu, Dianhui Chu +1
cs.IRcs.AIarXiv:2608.29179v12026
HM-RAG: Hierarchical Multi-Agent Multimodal Retrieval Augmented Generation
Pei Liu, Xin Liu, Ruoyu Yao +4
cs.CLcs.AIarXiv:2504.12330v12025
MedAgentBench: A Realistic Virtual EHR Environment to Benchmark Medical LLM Agents
Yixing Jiang, Kameron C. Black, Gloria Geng +4
cs.LGcs.AIcs.MAarXiv:2501.14654v22025
SkillTrojan: Backdoor Attacks on Skill-Based Agent Systems
Yunhao Feng, Yifan Ding, Yingshui Tan +6
cs.CRcs.AIarXiv:2604.06811v22026
Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models
Yijia Shao, Yucheng Jiang, Theodore A. Kanell +3
cs.CLcs.AIarXiv:2402.14207v22024
Auditing and Mitigating Privacy Leakage in Cloud-Edge Collaborative Decoding
Kejia Zhang, Tianyuan Zou, Zixuan GU +1
cs.CRcs.AIarXiv:2608.29111v12026
Interpreting CLIP with Hierarchical Sparse Autoencoders
Vladimir Zaigrajew, Hubert Baniecki, Przemyslaw Biecek
cs.CVcs.AIcs.LGarXiv:2502.20578v22025
Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training
Siyu Yuan, Zehui Chen, Zhiheng Xi +3
cs.AIarXiv:2501.11425v32025
A User Simulator for Task-Completion Dialogues
Xiujun Li, Zachary C. Lipton, Bhuwan Dhingra +3
cs.LGcs.AIcs.CLarXiv:1612.05688v32016
DeepStory: Video Story QA by Deep Embedded Memory Networks
Kyung-Min Kim, Min-Oh Heo, Seong-Ho Choi +1
cs.CVcs.AIcs.CLarXiv:1707.00836v12017
RAGDiffusion++: From Macro-Retrieval to Micro-Fidelity Alignment for Garment Generation
Yuhan Li, Xianfeng Tan, Fangao Zeng +6
cs.CVcs.AIarXiv:2608.29280v12026
APIFlow-Bench: Measuring Whether Agents Survive Long, Dependent API Workflows
Zelin Wan, Arash Nourian, Xiaoxiao Li +2
cs.AIcs.LGcs.SEarXiv:2608.29128v12026
LEGO-Puzzles: How Good Are MLLMs at Multi-Step Spatial Reasoning?
Kexian Tang, Junyao Gao, Yanhong Zeng +6
cs.AIarXiv:2503.19990v42025
D2A: A Dataset Built for AI-Based Vulnerability Detection Methods Using Differential Analysis
Yunhui Zheng, Saurabh Pujar, Burn Lewis +6
cs.SEcs.AIcs.LGarXiv:2102.07995v12021
VideoRAG: Retrieval-Augmented Generation over Video Corpus
Soyeong Jeong, Kangsan Kim, Jinheon Baek +1
cs.CVcs.AIcs.CLarXiv:2501.05874v32025
A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models
Dong Shu, Xuansheng Wu, Haiyan Zhao +4
cs.LGcs.AIcs.CLarXiv:2503.05613v32025
Wavelet-Assisted Multi-Frequency Attention Network for Pansharpening
Jie Huang, Rui Huang, Jinghao Xu +3
eess.IVcs.AIcs.CVarXiv:2502.04903v12025
A Survey on Large Language Models for Mathematical Reasoning
Peng-Yuan Wang, Tian-Shuo Liu, Chenyang Wang +8
cs.AIcs.CLarXiv:2506.08446v12025
Integrating LLMs with ITS: Recent Advances, Potentials, Challenges, and Future Directions
Doaa Mahmud, Hadeel Hajmohamed, Shamma Almentheri +4
eess.SYcs.AIcs.ETarXiv:2501.04437v12025
Language Models Use Trigonometry to Do Addition
Subhash Kantamneni, Max Tegmark
cs.AIcs.CLcs.LGarXiv:2502.00873v12025
AI Literacy in K-12 and Higher Education in the Wake of Generative AI: An Integrative Review
Xingjian Gu, Barbara J. Ericson
cs.CYcs.AIarXiv:2503.00079v32025
Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities
Alexander Nikitin, Jannik Kossen, Yarin Gal +1
cs.LGcs.AIcs.CLarXiv:2405.20003v12024
Formal Policy Enforcement for Real-World Agentic Systems
Nils Palumbo, Sarthak Choudhary, Jihye Choi +3
cs.CRcs.AIcs.MAarXiv:2602.16708v32026
Neural Language Modeling by Jointly Learning Syntax and Lexicon
Yikang Shen, Zhouhan Lin, Chin-Wei Huang +1
cs.CLcs.AIarXiv:1711.02013v22017
MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems
Zhaojiang Lin, Andrea Madotto, Genta Indra Winata +1
cs.CLcs.AIarXiv:2009.12005v22020
MedHallu: A Comprehensive Benchmark for Detecting Medical Hallucinations in Large Language Models
Shrey Pandit, Jiawei Xu, Junyuan Hong +4
cs.CLcs.AIcs.LGarXiv:2502.14302v12025
Meta-Learning by Adjusting Priors Based on Extended PAC-Bayes Theory
Ron Amit, Ron Meir
stat.MLcs.AIcs.LGarXiv:1711.01244v82017
A Survey on the Optimization of Large Language Model-based Agents
Shangheng Du, Jiabao Zhao, Jinxin Shi +4
cs.AIarXiv:2503.12434v22025
R1-ShareVL: Incentivizing Reasoning Capability of Multimodal Large Language Models via Share-GRPO
Huanjin Yao, Qixiang Yin, Jingyi Zhang +8
cs.CVcs.AIcs.CLarXiv:2505.16673v12025
Perceptive Humanoid Parkour: Chaining Dynamic Human Skills via Motion Matching
Zhen Wu, Xiaoyu Huang, Lujie Yang +8
cs.ROcs.AIcs.LGarXiv:2602.15827v22026
The Assistant's Ideal Self
Mert Yazan
cs.AIarXiv:2609.00304v12026
When Single-Agent with Skills Replace Multi-Agent Systems and When They Fail
Xiaoxiao Li
cs.AIcs.MAarXiv:2601.04748v22026
BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval
Hongjin Su, Howard Yen, Mengzhou Xia +12
cs.CLcs.AIcs.IRarXiv:2407.12883v42024
Advancing Multi-Agent Systems Through Model Context Protocol: Architecture, Implementation, and Applications
Naveen Krishnan
cs.MAcs.AIarXiv:2504.21030v12025
STAMP: Scalable Task And Model-agnostic Collaborative Perception
Xiangbo Gao, Runsheng Xu, Jiachen Li +3
cs.CVcs.AIcs.ROarXiv:2501.18616v12025
Beyond Token Positions: Safety Alignment Across Denoising Steps in Diffusion Language Models
Guoli Wang, Haonan Shi, Tu Ouyang +1
cs.CLcs.AIarXiv:2609.00495v12026
Operational Regimes in Non-Convex Optimization: A Multiplier-Based Taxonomy
Seyed Mohsen Kazemi, Ali Movaghar, Shaahin hessabi
math.OCcs.AIeess.SParXiv:2609.00471v12026
Securing Agentic AI: A Comprehensive Threat Model and Mitigation Framework for Generative AI Agents
Vineeth Sai Narajala, Om Narayan
cs.CRcs.AIarXiv:2504.19956v22025
Does RAG Know When Retrieval Is Wrong? Diagnosing Context Compliance under Knowledge Conflict
Yihang Chen, Pin Qian, Su Wang +4
cs.CLcs.AIarXiv:2605.14473v42026
Are Language Models Models?
Philip Resnik
cs.CLcs.AIarXiv:2601.10421v12026
The Impact of Reasoning Step Length on Large Language Models
Mingyu Jin, Qinkai Yu, Dong Shu +5
cs.CLcs.AIarXiv:2401.04925v42024
Life-Cycle Emissions of AI Hardware: A Cradle-To-Grave Approach and Generational Trends
Ian Schneider, Hui Xu, Stephan Benecke +4
cs.ARcs.AIarXiv:2502.01671v12025
Centering before Pruning: Lightweight Geometry Correction for Diversity-Based Visual Token Pruning in LVLMs
Shunjie Wen, Jaeyeon Lee, Dong-Wan Choi
cs.CVcs.AIarXiv:2608.30263v12026
Parameter-Efficient Fine-Tuning for Foundation Models
Dan Zhang, Tao Feng, Lilong Xue +3
cs.CLcs.AIcs.LGarXiv:2501.13787v12025
NVIDIA FLARE: Federated Learning from Simulation to Real-World
Holger R. Roth, Yan Cheng, Yuhong Wen +20
cs.LGcs.AIcs.CVarXiv:2210.13291v32022
EpaCache: Error-Propagation-Aware Caching for Accelerating Diffusion-Based Visual Generation
Yuhan Liu, Zongwei Hong, Jinglun Li +3
cs.AIarXiv:2608.29264v12026
TIPS: Turn-Level Information-Potential Reward Shaping for Search-Augmented LLMs
Yutao Xie, Nathaniel Thomas, Nicklas Hansen +3
cs.CLcs.AIcs.LGarXiv:2603.22293v12026
Augmenting Human Performance with an XR Agent Learning from Online Behavior and BCI Evidence
Ziheng Li, Xichen He, Haoyan Chen +10
cs.AIcs.HCarXiv:2608.30369v12026
Incompressible Knowledge Probes: Estimating Black-Box LLM Parameter Counts via Factual Capacity
Bojie Li
cs.LGcs.AIarXiv:2604.24827v22026
School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs
Mia Taylor, James Chua, Jan Betley +2
cs.AIarXiv:2508.17511v12025
Thinking with Generated Images
Ethan Chern, Zhulin Hu, Steffi Chern +5
cs.CVcs.AIcs.CLarXiv:2505.22525v12025
Astra: A Multi-Agent System for GPU Kernel Performance Optimization
Anjiang Wei, Tianran Sun, Yogesh Seenichamy +5
cs.DCcs.AIcs.CLarXiv:2509.07506v22025
General In-Hand Object Rotation with Vision and Touch
Haozhi Qi, Brent Yi, Sudharshan Suresh +4
cs.ROcs.AIcs.CVarXiv:2309.09979v22023
Adapting the Interface, Not the Model: Runtime Harness Adaptation for Deterministic LLM Agents
Tianshi Xu, Huifeng Wen, Meng Li
cs.AIarXiv:2605.22166v22026
Position: Graph Learning Will Lose Relevance Due To Poor Benchmarks
Maya Bechler-Speicher, Ben Finkelshtein, Fabrizio Frasca +9
cs.LGcs.AIcs.NEarXiv:2502.14546v12025
Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization
Jiantong Jiang, Peiyu Yang, Rui Zhang +1
cs.LGcs.AIcs.CLarXiv:2607.08057v12026
A Generative Deep Learning Approach to Stochastic Downscaling of Precipitation Forecasts
Lucy Harris, Andrew T. T. McRae, Matthew Chantry +2
physics.ao-phcs.AIcs.CVarXiv:2204.02028v22022
More Perspectives, Stronger Signals: Multi-Perspective Enhancement and Progressive Fusion for Multimodal Entity Representation Learning
Chenyi Xiong, Yan Zhang, Jing Hu +5
cs.AIarXiv:2608.29139v12026
Agent Behavioral Contracts: Formal Specification and Runtime Enforcement for Reliable Autonomous AI Agents
Varun Pratap Bhardwaj
cs.AIcs.MAcs.SEarXiv:2602.22302v12026

Artificial Intelligence

OPSDL: On-Policy Self-Distillation for Long-Context Language Models

TAAL: Mitigating Early Beam Pruning in Generative Recommendation via Temporal Autoregressive Alignment

HM-RAG: Hierarchical Multi-Agent Multimodal Retrieval Augmented Generation

MedAgentBench: A Realistic Virtual EHR Environment to Benchmark Medical LLM Agents

SkillTrojan: Backdoor Attacks on Skill-Based Agent Systems

Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models

Auditing and Mitigating Privacy Leakage in Cloud-Edge Collaborative Decoding

Interpreting CLIP with Hierarchical Sparse Autoencoders

Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training

A User Simulator for Task-Completion Dialogues

DeepStory: Video Story QA by Deep Embedded Memory Networks

RAGDiffusion++: From Macro-Retrieval to Micro-Fidelity Alignment for Garment Generation

APIFlow-Bench: Measuring Whether Agents Survive Long, Dependent API Workflows

LEGO-Puzzles: How Good Are MLLMs at Multi-Step Spatial Reasoning?

D2A: A Dataset Built for AI-Based Vulnerability Detection Methods Using Differential Analysis

VideoRAG: Retrieval-Augmented Generation over Video Corpus

A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models

Wavelet-Assisted Multi-Frequency Attention Network for Pansharpening

A Survey on Large Language Models for Mathematical Reasoning

Integrating LLMs with ITS: Recent Advances, Potentials, Challenges, and Future Directions

Language Models Use Trigonometry to Do Addition

AI Literacy in K-12 and Higher Education in the Wake of Generative AI: An Integrative Review

Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities

Formal Policy Enforcement for Real-World Agentic Systems

Neural Language Modeling by Jointly Learning Syntax and Lexicon

MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems

MedHallu: A Comprehensive Benchmark for Detecting Medical Hallucinations in Large Language Models

Meta-Learning by Adjusting Priors Based on Extended PAC-Bayes Theory

A Survey on the Optimization of Large Language Model-based Agents

R1-ShareVL: Incentivizing Reasoning Capability of Multimodal Large Language Models via Share-GRPO

Perceptive Humanoid Parkour: Chaining Dynamic Human Skills via Motion Matching

The Assistant's Ideal Self

When Single-Agent with Skills Replace Multi-Agent Systems and When They Fail

BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval

Advancing Multi-Agent Systems Through Model Context Protocol: Architecture, Implementation, and Applications

STAMP: Scalable Task And Model-agnostic Collaborative Perception

Beyond Token Positions: Safety Alignment Across Denoising Steps in Diffusion Language Models

Operational Regimes in Non-Convex Optimization: A Multiplier-Based Taxonomy

Securing Agentic AI: A Comprehensive Threat Model and Mitigation Framework for Generative AI Agents

Does RAG Know When Retrieval Is Wrong? Diagnosing Context Compliance under Knowledge Conflict

Are Language Models Models?

The Impact of Reasoning Step Length on Large Language Models

Life-Cycle Emissions of AI Hardware: A Cradle-To-Grave Approach and Generational Trends

Centering before Pruning: Lightweight Geometry Correction for Diversity-Based Visual Token Pruning in LVLMs

Parameter-Efficient Fine-Tuning for Foundation Models

NVIDIA FLARE: Federated Learning from Simulation to Real-World

EpaCache: Error-Propagation-Aware Caching for Accelerating Diffusion-Based Visual Generation

TIPS: Turn-Level Information-Potential Reward Shaping for Search-Augmented LLMs

Augmenting Human Performance with an XR Agent Learning from Online Behavior and BCI Evidence

Incompressible Knowledge Probes: Estimating Black-Box LLM Parameter Counts via Factual Capacity

School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs

Thinking with Generated Images

Astra: A Multi-Agent System for GPU Kernel Performance Optimization

General In-Hand Object Rotation with Vision and Touch

Adapting the Interface, Not the Model: Runtime Harness Adaptation for Deterministic LLM Agents

Position: Graph Learning Will Lose Relevance Due To Poor Benchmarks

Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization

A Generative Deep Learning Approach to Stochastic Downscaling of Precipitation Forecasts

More Perspectives, Stronger Signals: Multi-Perspective Enhancement and Progressive Fusion for Multimodal Entity Representation Learning

Agent Behavioral Contracts: Formal Specification and Runtime Enforcement for Reliable Autonomous AI Agents