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)

3,301 to 3,360 of 15,328

Reasoning over Semantic IDs Enhances Generative Recommendation
Yingzhi He, Yan Sun, Junfei Tan +6
cs.IRcs.AIarXiv:2603.23183v22026
Inference-Time Budget Control for LLM Search Agents
Zhengru Fang, Senkang Forest Hu, Zhonghao Chang +6
cs.AIarXiv:2605.05701v12026
AtomicVLA: Unlocking the Potential of Atomic Skill Learning in Robots
Likui Zhang, Tao Tang, Zhihao Zhan +9
cs.ROcs.AIcs.CVarXiv:2603.07648v12026
ActionCodec: What Makes for Good Action Tokenizers
Zibin Dong, Yicheng Liu, Shiduo Zhang +8
cs.ROcs.AIarXiv:2602.15397v12026
ALL-FEM: Agentic Large Language models Fine-tuned for Finite Element Methods
Rushikesh Deotale, Adithya Srinivasan, Yuan Tian +3
cs.CEcs.AIcs.LGarXiv:2603.21011v22026
MARLA: A Conceptual Scaffold for Regulatory Learning under the EU AI Act
Alessio Buscemi, Tom Deckenbrunnen, Imane Hmiddou +5
cs.AIarXiv:2609.04877v12026
AI Assistance Reduces Persistence and Hurts Independent Performance
Grace Liu, Brian Christian, Tsvetomira Dumbalska +2
cs.AIarXiv:2604.04721v42026
CHAMP: Cross-domain Hybrid Architecture for Matchmaking and Prediction in Online Multi-Player Games
Kai Wang, Ge Fan, Chaoyun Zhang +2
cs.AIarXiv:2609.04870v12026
From Interaction Traces to Persistent Skills: Online Evolution for Computer-Use Agents
Longtao Hu, Xiao Liang, Linchao Zhu
cs.AIarXiv:2609.04869v12026
LSSF: Safety Alignment for Large Language Models through Low-Rank Safety Subspace Fusion
Guanghao Zhou, Panjia Qiu, Cen Chen +4
cs.CYcs.AIarXiv:2602.00038v12026
TraceRouter: Robust Safety for Large Foundation Models via Path-Level Intervention
Chuancheng Shi, Shangze Li, Wenjun Lu +5
cs.CVcs.AIcs.CYarXiv:2601.21900v22026
AI Agent Systems: Architectures, Applications, and Evaluation
Bin Xu
cs.AIarXiv:2601.01743v12026
Confidence-Based Decoding is Provably Efficient for Diffusion Language Models
Changxiao Cai, Gen Li
cs.LGcs.AIcs.ITarXiv:2603.22248v12026
MM-IFEval-Pro: A Multilingual and Attack-Resistant Benchmark for Instruction-Following in Vision-Language Models
Changming Xiao, Zhenliang Ni, Jinhui He +2
cs.AIarXiv:2609.04859v12026
FoE: Forest of Errors Makes the First Solution the Best in Large Reasoning Models
Kehan Jiang, Haonan Dong, Zhaolu Kang +2
cs.AIcs.CLarXiv:2604.02967v12026
ElderBench: Benchmarking Autonomous Mobile Agents for Older Adults
Weide Zhan, Qumu Shaqu, Yuanqing Liu +6
cs.AIarXiv:2609.04850v12026
Training Question Answering Models From Synthetic Data
Raul Puri, Ryan Spring, Mostofa Patwary +2
cs.CLcs.AIarXiv:2002.09599v12020
Long Horizon Transformer Quantile Fault Prediction for Multi Site Industrial Predictive Maintenance
David J Poland, Daniele Ravi, Na Helian
cs.AIarXiv:2609.04840v12026
ProtLingo: Efficient Protein Language Modeling via Conditional Memory and Expert Routing
Mingrui Li, Sixian Shen, Minzhang Li +4
cs.AIarXiv:2609.04793v12026
Library Drift: Diagnosing and Fixing a Silent Failure Mode in Self-Evolving LLM Skill Libraries
Xing Zhang, Yanwei Cui, Guanghui Wang +4
cs.AIcs.CLcs.SEarXiv:2605.19576v32026
Large Language Models for Generative Recommendation: A Survey and Visionary Discussions
Lei Li, Yongfeng Zhang, Dugang Liu +1
cs.IRcs.AIcs.CLarXiv:2309.01157v22023
Contrastive and Non-Contrastive Self-Supervised Learning Recover Global and Local Spectral Embedding Methods
Randall Balestriero, Yann LeCun
cs.LGcs.AIcs.CVarXiv:2205.11508v32022
Diffusion Language Models for Mobile Edge Agentic AI: Foundations, Applications, and Challenges
Chenqi Li, Minghui Min, Dusit Niyato +1
cs.AIarXiv:2609.04778v12026
DCFA: Dual-view Causal-inspired Attribution for Failure Reasoning in LLM-based Multi-agent Systems
Zehao Wang, Lanjun Wang, Shilong Jin +2
cs.AIarXiv:2609.04749v12026
Shadow Queries for Private Retrieval in Vector Databases
Xinguo Feng, Zhongkui Ma, Zihan Wang +4
cs.AIarXiv:2609.04767v12026
PERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environments
Shuochen Liu, Junyi Zhu, Long Shu +11
cs.AIarXiv:2603.23231v22026
Exploring the Reasoning Abilities of Multimodal Large Language Models (MLLMs): A Comprehensive Survey on Emerging Trends in Multimodal Reasoning
Yiqi Wang, Wentao Chen, Xiaotian Han +7
cs.CLcs.AIarXiv:2401.06805v22024
CPR-IE:A Compression-Prediction-Resource Intelligence Efficiency Metric
Xiantao Jiang
cs.AIarXiv:2609.04809v12026
MedFlow: Class-Aware Multi-Scale Generation for Medical Time-Series Synthesis
Yanhao Huang, Shibo Feng, Wanjin Feng +2
cs.AIarXiv:2609.04804v12026
Hierarchical Possession-Aware Graph Pointer Network for Pass Receiver Selection
Jingyi Wang, Da Li, Kaixin Wang +1
cs.AIcs.SIarXiv:2609.04803v12026
Whose record is this? Diagnosing and authorizing record use in personalized multimodal models
Xinyu Mao, Junsi Li, Chenyang Liu +2
cs.AIarXiv:2609.04801v12026
Sycophancy Hides Linearly in the Attention Heads
Rifo Genadi, Munachiso Nwadike, Nurdaulet Mukhituly +3
cs.CLcs.AIarXiv:2601.16644v12026
Internal Representations as Indicators of Hallucinations in Agent Tool Selection
Kait Healy, Bharathi Srinivasan, Visakh Madathil +1
cs.AIarXiv:2601.05214v12026
Memory Matters More: Event-Centric Memory as a Logic Map for Agent Searching and Reasoning
Yuyang Hu, Jiongnan Liu, Jiejun Tan +2
cs.AIcs.CLarXiv:2601.04726v12026
DODR: Deterministic Operator-Driven Reasoning in Latent Space
Weicai Huang
cs.AIarXiv:2609.04782v12026
Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs
Alexander Panfilov, Peter Romov, Igor Shilov +3
cs.LGcs.AIcs.CRarXiv:2603.24511v22026
Strategic Attentive Writer for Learning Macro-Actions
Alexander, Vezhnevets, Volodymyr Mnih +5
cs.AIcs.LGarXiv:1606.04695v12016
Visually-Guided Policy Optimization for Multimodal Reasoning
Zengbin Wang, Feng Xiong, Liang Lin +5
cs.CVcs.AIcs.CLarXiv:2604.09349v22026
A Survey on Data Pricing: from Economics to Data Science
Jian Pei
econ.THcs.AIcs.DBarXiv:2009.04462v22020
Rethinking Failure Attribution in Multi-Agent Systems: A Multi-Perspective Benchmark and Evaluation
Yeonjun In, Mehrab Tanjim, Jayakumar Subramanian +6
cs.AIarXiv:2603.25001v12026
SCRIBE: Structured Mid-Level Supervision for Tool-Using Language Models
Yuxuan Jiang, Francis Ferraro
cs.AIarXiv:2601.03555v32026
Agentic Proposing: Enhancing Large Language Model Reasoning via Compositional Skill Synthesis
Zhengbo Jiao, Shaobo Wang, Zifan Zhang +5
cs.AIcs.LGarXiv:2602.03279v12026
RubricEval: A Rubric-Level Meta-Evaluation Benchmark for LLM Judges in Instruction Following
Tianjun Pan, Xuan Lin, Wenyan Yang +7
cs.AIarXiv:2603.25133v12026
Self-Evolving Recommendation System: End-To-End Autonomous Model Optimization With LLM Agents
Haochen Wang, Yi Wu, Daryl Chang +2
cs.LGcs.AIarXiv:2602.10226v32026
Aplaud: Adaptive Personalized Low-Rank Decomposition for User-Specific LLM
Xinyu Li, Ruoming Jin, Jianfeng Zhu +2
cs.AIarXiv:2609.04738v12026
AgentCgroup: Understanding and Controlling OS Resources of AI Agents
Yusheng Zheng, Jiakun Fan, Quanzhi Fu +3
cs.OScs.AIarXiv:2602.09345v32026
FinalityBench: An Effect-Level Benchmark for Agent Decisions Under Delayed and Conflicting Financial Finality
Abhishek Sharma
cs.AIarXiv:2609.04706v12026
AgenTRIM: Tool Risk Mitigation for Agentic AI
Roy Betser, Amit Giloni, Shamik Bose +4
cs.CRcs.AIarXiv:2601.12449v22026
Model Retirement Creates Reproducibility Risk in Biomedical AI Publications
Nathan Wolfrath, Meghan Conroy, Thomas Kosten +7
cs.AIarXiv:2609.04699v12026
Train What You Deploy:Token-Faithful Post-Training of a Production Coding
Cheng Li, Jiexiong Liu, Yixuan Chen +1
cs.AIarXiv:2609.04678v12026
E-GRPO: High Entropy Steps Drive Effective Reinforcement Learning for Flow Models
Shengjun Zhang, Zhang Zhang, Chensheng Dai +1
cs.LGcs.AIcs.CVarXiv:2601.00423v12026
ERPBench: Evaluating LLM Agents for Enterprise Decision-Making Across Competitive Market Ecologies
Xinran Zhang, Pengrui Lu, Lyumanshan Ye +1
cs.AIarXiv:2609.04667v12026
Harness-agnostic detection and immunization of reward hacking in self-evolving language models
Rongxin Yang, Yang Liu, Shang Luo +10
cs.AIarXiv:2609.04665v12026
Avatar Forcing: Real-Time Interactive Head Avatar Generation for Natural Conversation
Taekyung Ki, Sangwon Jang, Jaehyeong Jo +2
cs.LGcs.AIcs.CVarXiv:2601.00664v22026
Relational Collaborative Filtering:Modeling Multiple Item Relations for Recommendation
Xin Xin, Xiangnan He, Yongfeng Zhang +2
cs.IRcs.AIarXiv:1904.12796v32019
SkillEvolver: Skill Learning as a Meta-Skill
Genrui Zhang, Erle Zhu, Jinfeng Zhou +2
cs.AIarXiv:2605.10500v12026
Overcoming the Retrieval Barrier: Indirect Prompt Injection in the Wild for LLM Systems
Hongyan Chang, Ergute Bao, Xinjian Luo +1
cs.CRcs.AIarXiv:2601.07072v12026
PLUME: Parameter-Efficient Personalization of Large Language Models via Low-Rank User Modulation in Shared Subspaces
Xinyu Li, Hao Zhou, Jianfeng Zhu +4
cs.AIarXiv:2609.04715v12026
How to Allocate, How to Learn? Dynamic Rollout Allocation and Advantage Modulation for Policy Optimization
Yangyi Fang, Jiaye Lin, Xiaoliang Fu +6
cs.LGcs.AIarXiv:2602.19208v22026
LLM Reasoning as Trajectories: Step-Specific Representation Geometry and Correctness Signals
Lihao Sun, Hang Dong, Bo Qiao +3
cs.CLcs.AIcs.LGarXiv:2604.05655v12026

Artificial Intelligence

Reasoning over Semantic IDs Enhances Generative Recommendation

Inference-Time Budget Control for LLM Search Agents

AtomicVLA: Unlocking the Potential of Atomic Skill Learning in Robots

ActionCodec: What Makes for Good Action Tokenizers

ALL-FEM: Agentic Large Language models Fine-tuned for Finite Element Methods

MARLA: A Conceptual Scaffold for Regulatory Learning under the EU AI Act

AI Assistance Reduces Persistence and Hurts Independent Performance

CHAMP: Cross-domain Hybrid Architecture for Matchmaking and Prediction in Online Multi-Player Games

From Interaction Traces to Persistent Skills: Online Evolution for Computer-Use Agents

LSSF: Safety Alignment for Large Language Models through Low-Rank Safety Subspace Fusion

TraceRouter: Robust Safety for Large Foundation Models via Path-Level Intervention

AI Agent Systems: Architectures, Applications, and Evaluation

Confidence-Based Decoding is Provably Efficient for Diffusion Language Models

MM-IFEval-Pro: A Multilingual and Attack-Resistant Benchmark for Instruction-Following in Vision-Language Models

FoE: Forest of Errors Makes the First Solution the Best in Large Reasoning Models

ElderBench: Benchmarking Autonomous Mobile Agents for Older Adults

Training Question Answering Models From Synthetic Data

Long Horizon Transformer Quantile Fault Prediction for Multi Site Industrial Predictive Maintenance

ProtLingo: Efficient Protein Language Modeling via Conditional Memory and Expert Routing

Library Drift: Diagnosing and Fixing a Silent Failure Mode in Self-Evolving LLM Skill Libraries

Large Language Models for Generative Recommendation: A Survey and Visionary Discussions

Contrastive and Non-Contrastive Self-Supervised Learning Recover Global and Local Spectral Embedding Methods

Diffusion Language Models for Mobile Edge Agentic AI: Foundations, Applications, and Challenges

DCFA: Dual-view Causal-inspired Attribution for Failure Reasoning in LLM-based Multi-agent Systems

Shadow Queries for Private Retrieval in Vector Databases

PERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environments

Exploring the Reasoning Abilities of Multimodal Large Language Models (MLLMs): A Comprehensive Survey on Emerging Trends in Multimodal Reasoning

CPR-IE:A Compression-Prediction-Resource Intelligence Efficiency Metric

MedFlow: Class-Aware Multi-Scale Generation for Medical Time-Series Synthesis

Hierarchical Possession-Aware Graph Pointer Network for Pass Receiver Selection

Whose record is this? Diagnosing and authorizing record use in personalized multimodal models

Sycophancy Hides Linearly in the Attention Heads

Internal Representations as Indicators of Hallucinations in Agent Tool Selection

Memory Matters More: Event-Centric Memory as a Logic Map for Agent Searching and Reasoning

DODR: Deterministic Operator-Driven Reasoning in Latent Space

Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs

Strategic Attentive Writer for Learning Macro-Actions

Visually-Guided Policy Optimization for Multimodal Reasoning

A Survey on Data Pricing: from Economics to Data Science

Rethinking Failure Attribution in Multi-Agent Systems: A Multi-Perspective Benchmark and Evaluation

SCRIBE: Structured Mid-Level Supervision for Tool-Using Language Models

Agentic Proposing: Enhancing Large Language Model Reasoning via Compositional Skill Synthesis

RubricEval: A Rubric-Level Meta-Evaluation Benchmark for LLM Judges in Instruction Following

Self-Evolving Recommendation System: End-To-End Autonomous Model Optimization With LLM Agents

Aplaud: Adaptive Personalized Low-Rank Decomposition for User-Specific LLM

AgentCgroup: Understanding and Controlling OS Resources of AI Agents

FinalityBench: An Effect-Level Benchmark for Agent Decisions Under Delayed and Conflicting Financial Finality

AgenTRIM: Tool Risk Mitigation for Agentic AI

Model Retirement Creates Reproducibility Risk in Biomedical AI Publications

Train What You Deploy:Token-Faithful Post-Training of a Production Coding

E-GRPO: High Entropy Steps Drive Effective Reinforcement Learning for Flow Models

ERPBench: Evaluating LLM Agents for Enterprise Decision-Making Across Competitive Market Ecologies

Harness-agnostic detection and immunization of reward hacking in self-evolving language models

Avatar Forcing: Real-Time Interactive Head Avatar Generation for Natural Conversation

Relational Collaborative Filtering:Modeling Multiple Item Relations for Recommendation

SkillEvolver: Skill Learning as a Meta-Skill

Overcoming the Retrieval Barrier: Indirect Prompt Injection in the Wild for LLM Systems

PLUME: Parameter-Efficient Personalization of Large Language Models via Low-Rank User Modulation in Shared Subspaces

How to Allocate, How to Learn? Dynamic Rollout Allocation and Advantage Modulation for Policy Optimization

LLM Reasoning as Trajectories: Step-Specific Representation Geometry and Correctness Signals