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)

3,661 to 3,720 of 15,308

Rethinking the Design Space of Reinforcement Learning for Diffusion Models: On the Importance of Likelihood Estimation Beyond Loss Design
Jaemoo Choi, Yuchen Zhu, Wei Guo +6
cs.LGcs.AIarXiv:2602.04663v22026
AerialVLA: A Vision-Language-Action Model for UAV Navigation via Minimalist End-to-End Control
Peng Xu, Zhengnan Deng, Jiayan Deng +2
cs.CVcs.AIcs.ROarXiv:2603.14363v12026
OS Agents: A Survey on MLLM-based Agents for General Computing Devices Use
Xueyu Hu, Tao Xiong, Biao Yi +26
cs.AIcs.CLcs.CVarXiv:2508.04482v12025
DeltaBox: Scaling Stateful AI Agents with Millisecond-Level Sandbox Checkpoint/Rollback
Yunpeng Dong, Jingkai He, Shiqi Liu +7
cs.OScs.AIarXiv:2605.22781v22026
Multimodal learning with graphs
Yasha Ektefaie, George Dasoulas, Ayush Noori +2
cs.LGcs.AIarXiv:2209.03299v62022
MELT: Improve Composed Image Retrieval via the Modification Frequentation-Rarity Balance Network
Guozhi Qiu, Zhiwei Chen, Zixu Li +4
cs.CVcs.AIarXiv:2603.29291v12026
Topological Planning with Transformers for Vision-and-Language Navigation
Kevin Chen, Junshen K. Chen, Jo Chuang +2
cs.ROcs.AIcs.CLarXiv:2012.05292v12020
ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Training
Haian Jin, Rundi Wu, Tianyuan Zhang +4
cs.CVcs.AIcs.LGarXiv:2603.04385v32026
ExploitBench: A Capability Ladder Benchmark for LLM Cybersecurity Agents
Seunghyun Lee, David Brumley
cs.CRcs.AIarXiv:2605.14153v12026
TRACER: Per-Tool Context Retention for LLM Agents via Consequence-Attributed Reinforcement Learning
Ziqi Lin, Ye Wu, Mengying Yang +4
cs.AIarXiv:2608.29363v12026
Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI
Jiangchao Yao, Shengyu Zhang, Yang Yao +15
cs.LGcs.AIarXiv:2111.06061v32021
Summaries:한국어
Relational-Core Graph Analytics Querying graphs at SQL scale, and why the node/edge model is a performance tax, not a truer picture of connected data
Gene Zhang
cs.DBcs.AIcs.PLarXiv:2609.01525v12026
Learning to Generalize Across Long-Horizon Tasks from Human Demonstrations
Ajay Mandlekar, Danfei Xu, Roberto Martín-Martín +2
cs.ROcs.AIcs.LGarXiv:2003.06085v22020
Interpretability without actionability: mechanistic methods cannot correct language model errors despite near-perfect internal representations
Sanjay Basu, Sadiq Y. Patel, Parth Sheth +5
cs.AIarXiv:2603.18353v12026
Explore More, Drift Less: Outcome-Only Reinforcement Learning Can Suffice for Long-Horizon Interactive Agents
Liming Pu, Xiaoxia Li, Yifu Liu +2
cs.LGcs.AIarXiv:2609.01245v12026
HumanEgo: Zero-Shot Robot Learning from Minutes of Human Egocentric Videos
Zhi Wang, Botao He, Kelin Yu +4
cs.ROcs.AIcs.CVarXiv:2605.24934v22026
REFACTOR-VLA: Unsupervised Library Learning of Typed Motor Programs
Riyaaz Shaik, Chandru Venkataraman
cs.LGcs.AIcs.ROarXiv:2609.01215v12026
CoopEval: Benchmarking Cooperation-Sustaining Mechanisms and LLM Agents in Social Dilemmas
Emanuel Tewolde, Xiao Zhang, David Guzman Piedrahita +2
cs.GTcs.AIcs.CLarXiv:2604.15267v22026
Inspicio: Open-Vocabulary, LLM-Based Sense Retrieval for Historical Languages
Michele Ciletti
cs.CLcs.AIarXiv:2609.00998v12026
HarnessEvolve: Learning from Reference Trajectories for Reliable Agent Self-Evolution
Wen Jiang, Mingmin Chu, Yimeng Tian +6
cs.LGcs.AIarXiv:2609.00829v12026
Discrete Audio Tokens: More Than a Survey!
Pooneh Mousavi, Gallil Maimon, Adel Moumen +18
cs.SDcs.AIcs.CLarXiv:2506.10274v32025
Experience Compression Spectrum: Unifying Memory, Skills, and Rules in LLM Agents
Xing Zhang, Guanghui Wang, Yanwei Cui +4
cs.AIcs.CLcs.MAarXiv:2604.15877v22026
The Second Challenge on Cross-Domain Few-Shot Object Detection at NTIRE 2026: Methods and Results
Xingyu Qiu, Yuqian Fu, Jiawei Geng +71
cs.CVcs.AIarXiv:2604.11998v12026
Algorithmic Fairness in Education
René F. Kizilcec, Hansol Lee
cs.CYcs.AIcs.LGarXiv:2007.05443v32020
Multiagent Bidirectionally-Coordinated Nets: Emergence of Human-level Coordination in Learning to Play StarCraft Combat Games
Peng Peng, Ying Wen, Yaodong Yang +4
cs.AIcs.LGarXiv:1703.10069v42017
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
FlashVID: Efficient Video Large Language Models via Training-free Tree-based Spatiotemporal Token Merging
Ziyang Fan, Keyu Chen, Ruilong Xing +3
cs.CVcs.AIcs.CLarXiv:2602.08024v12026
GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM
Hao Kang, Qingru Zhang, Souvik Kundu +4
cs.LGcs.AIcs.CLarXiv:2403.05527v42024
GUI Agents for Continual Game Generation
Yixu Huang, Bo Li, Na Li +8
cs.SEcs.AIcs.CVarXiv:2605.28258v12026
Poison Once, Exploit Forever: Environment-Injected Memory Poisoning Attacks on Web Agents
Wei Zou, Mingwen Dong, Miguel Romero Calvo +7
cs.CRcs.AIarXiv:2604.02623v22026
Exponential quantum advantage in processing massive classical data
Haimeng Zhao, Alexander Zlokapa, Hartmut Neven +4
quant-phcs.AIcs.CCarXiv:2604.07639v12026
Discriminative Predicate Path Mining for Fact Checking in Knowledge Graphs
Baoxu Shi, Tim Weninger
cs.DBcs.AIcs.IRarXiv:1510.05911v22015
Subtraction-Based Tumor Segmentation and Lesion-Centered pCR Prediction for the MAMA-MIA Challenge
Kai Geissler, Raphael Schäfer
cs.CVcs.AIcs.LGarXiv:2608.29162v12026
Combining Reinforcement Learning and Constraint Programming for Combinatorial Optimization
Quentin Cappart, Thierry Moisan, Louis-Martin Rousseau +2
cs.AIcs.LGarXiv:2006.01610v12020
Understanding State Preferences With Text As Data: Introducing the UN General Debate Corpus
Alexander Baturo, Niheer Dasandi, Slava J. Mikhaylov
cs.CLcs.AIstat.MLarXiv:1707.02774v12017
CF-VLM:CounterFactual Vision-Language Fine-tuning
Jusheng Zhang, Kaitong Cai, Yijia Fan +2
cs.LGcs.AIarXiv:2506.17267v12025
Benchmark Contamination: A Taxonomy Organized by Defeated Mitigation
Johanna Angulo, Víctor Yeste, Hector Espinos-Morato
cs.CRcs.AIcs.CLarXiv:2608.29463v12026
TurboTransformers: An Efficient GPU Serving System For Transformer Models
Jiarui Fang, Yang Yu, Chengduo Zhao +1
cs.DCcs.AIcs.LGarXiv:2010.05680v42020
EvoLM: Self-Evolving Language Models through Co-Evolved Discriminative Rubrics
Shuyue Stella Li, Rui Xin, Teng Xiao +8
cs.AIarXiv:2605.03871v12026
ProtGNN: Towards Self-Explaining Graph Neural Networks
Zaixi Zhang, Qi Liu, Hao Wang +2
cs.LGcs.AIarXiv:2112.00911v12021
Pretrained Vision-Language-Action Models are Surprisingly Resistant to Forgetting in Continual Learning
Huihan Liu, Changyeon Kim, Bo Liu +2
cs.LGcs.AIcs.ROarXiv:2603.03818v22026
Advancing Reasoning in Large Language Models: Promising Methods and Approaches
Avinash Patil, Aryan Jadon
cs.CLcs.AIarXiv:2502.03671v22025
Adaptive Multi-Branching for Shallow Decision Tree Induction
Hanul Park, Jeonghoon Choi, Juseong Kim +2
cs.LGcs.AIarXiv:2608.29262v12026
LAP: Language-Action Pre-Training Enables Zero-shot Cross-Embodiment Transfer
Lihan Zha, Asher J. Hancock, Mingtong Zhang +5
cs.ROcs.AIarXiv:2602.10556v22026
User Experience Design Professionals' Perceptions of Generative Artificial Intelligence
Jie Li, Hancheng Cao, Laura Lin +3
cs.CYcs.AIcs.ETarXiv:2309.15237v22023
Emergent Misalignment Is Not Magical
Mingxuan Li, Qirun Dai, Heran Wang +1
cs.AIcs.CLcs.LGarXiv:2608.29118v12026
STRIDE: Strategic Trajectory Reasoning via Discriminative Estimation for Verifiable Reinforcement Learning
Qinjian Zhao, Zhihao Dou, Dinggen Zhang +10
cs.AIcs.LGarXiv:2606.15866v12026
Humans are Missing from AI Coding Agent Research
Zora Z. Wang, John Yang, Kilian Lieret +10
cs.HCcs.AIcs.SEarXiv:2608.12355v12026
DexWild: Dexterous Human Interactions for In-the-Wild Robot Policies
Tony Tao, Mohan Kumar Srirama, Jason Jingzhou Liu +2
cs.ROcs.AIcs.CVarXiv:2505.07813v22025
Reasoning with Very Expressive Fuzzy Description Logics
I. Horrocks, J. Z. Pan, G. Stamou +2
cs.AIarXiv:1111.0039v12011
Stop Automating Peer Review Without Rigorous Evaluation
Joachim Baumann, Jiaxin Pei, Sanmi Koyejo +1
cs.AIarXiv:2605.03202v22026
Evaluating and Inducing Personality in Pre-trained Language Models
Guangyuan Jiang, Manjie Xu, Song-Chun Zhu +3
cs.CLcs.AIcs.LGarXiv:2206.07550v32022
Transforming Science with Large Language Models: A Survey on AI-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluation
Steffen Eger, Yong Cao, Jennifer D'Souza +11
cs.CLcs.AIcs.CVarXiv:2502.05151v32025
Efficient Geothermal Well-Control Optimization via Diffusion-Surrogate Reinforcement Learning
Ruimin Dai, Guodong Chen, Randy Harsuko +2
cs.AIarXiv:2608.28791v12026
Polite Dialogue Generation Without Parallel Data
Tong Niu, Mohit Bansal
cs.CLcs.AIcs.LGarXiv:1805.03162v12018
The Long-Horizon Task Mirage? Diagnosing Where and Why Agentic Systems Break
Xinyu Jessica Wang, Haoyue Bai, Yiyou Sun +7
cs.AIarXiv:2604.11978v12026
Reinforcing Chain-of-Thought Reasoning with Self-Evolving Rubrics
Leheng Sheng, Wenchang Ma, Ruixin Hong +3
cs.AIcs.LGarXiv:2602.10885v12026
Inside the Scaffold: A Source-Code Taxonomy of Coding Agent Architectures
Benjamin Rombaut
cs.SEcs.AIcs.ETarXiv:2604.03515v22026
Data Mixing Laws: Optimizing Data Mixtures by Predicting Language Modeling Performance
Jiasheng Ye, Peiju Liu, Tianxiang Sun +3
cs.CLcs.AIcs.LGarXiv:2403.16952v22024
ReCreate: Reasoning and Creating Domain Agents Driven by Experience
Zhezheng Hao, Hong Wang, Jian Luo +6
cs.AIarXiv:2601.11100v22026

Artificial Intelligence

Rethinking the Design Space of Reinforcement Learning for Diffusion Models: On the Importance of Likelihood Estimation Beyond Loss Design

AerialVLA: A Vision-Language-Action Model for UAV Navigation via Minimalist End-to-End Control

OS Agents: A Survey on MLLM-based Agents for General Computing Devices Use

DeltaBox: Scaling Stateful AI Agents with Millisecond-Level Sandbox Checkpoint/Rollback

Multimodal learning with graphs

MELT: Improve Composed Image Retrieval via the Modification Frequentation-Rarity Balance Network

Topological Planning with Transformers for Vision-and-Language Navigation

ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Training

ExploitBench: A Capability Ladder Benchmark for LLM Cybersecurity Agents

TRACER: Per-Tool Context Retention for LLM Agents via Consequence-Attributed Reinforcement Learning

Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI

Relational-Core Graph Analytics Querying graphs at SQL scale, and why the node/edge model is a performance tax, not a truer picture of connected data

Learning to Generalize Across Long-Horizon Tasks from Human Demonstrations

Interpretability without actionability: mechanistic methods cannot correct language model errors despite near-perfect internal representations

Explore More, Drift Less: Outcome-Only Reinforcement Learning Can Suffice for Long-Horizon Interactive Agents

HumanEgo: Zero-Shot Robot Learning from Minutes of Human Egocentric Videos

REFACTOR-VLA: Unsupervised Library Learning of Typed Motor Programs

CoopEval: Benchmarking Cooperation-Sustaining Mechanisms and LLM Agents in Social Dilemmas

Inspicio: Open-Vocabulary, LLM-Based Sense Retrieval for Historical Languages

HarnessEvolve: Learning from Reference Trajectories for Reliable Agent Self-Evolution

Discrete Audio Tokens: More Than a Survey!

Experience Compression Spectrum: Unifying Memory, Skills, and Rules in LLM Agents

The Second Challenge on Cross-Domain Few-Shot Object Detection at NTIRE 2026: Methods and Results

Algorithmic Fairness in Education

Multiagent Bidirectionally-Coordinated Nets: Emergence of Human-level Coordination in Learning to Play StarCraft Combat Games

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

FlashVID: Efficient Video Large Language Models via Training-free Tree-based Spatiotemporal Token Merging

GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

GUI Agents for Continual Game Generation

Poison Once, Exploit Forever: Environment-Injected Memory Poisoning Attacks on Web Agents

Exponential quantum advantage in processing massive classical data

Discriminative Predicate Path Mining for Fact Checking in Knowledge Graphs

Subtraction-Based Tumor Segmentation and Lesion-Centered pCR Prediction for the MAMA-MIA Challenge

Combining Reinforcement Learning and Constraint Programming for Combinatorial Optimization

Understanding State Preferences With Text As Data: Introducing the UN General Debate Corpus

CF-VLM:CounterFactual Vision-Language Fine-tuning

Benchmark Contamination: A Taxonomy Organized by Defeated Mitigation

TurboTransformers: An Efficient GPU Serving System For Transformer Models

EvoLM: Self-Evolving Language Models through Co-Evolved Discriminative Rubrics

ProtGNN: Towards Self-Explaining Graph Neural Networks

Pretrained Vision-Language-Action Models are Surprisingly Resistant to Forgetting in Continual Learning

Advancing Reasoning in Large Language Models: Promising Methods and Approaches

Adaptive Multi-Branching for Shallow Decision Tree Induction

LAP: Language-Action Pre-Training Enables Zero-shot Cross-Embodiment Transfer

User Experience Design Professionals' Perceptions of Generative Artificial Intelligence

Emergent Misalignment Is Not Magical

STRIDE: Strategic Trajectory Reasoning via Discriminative Estimation for Verifiable Reinforcement Learning

Humans are Missing from AI Coding Agent Research

DexWild: Dexterous Human Interactions for In-the-Wild Robot Policies

Reasoning with Very Expressive Fuzzy Description Logics

Stop Automating Peer Review Without Rigorous Evaluation

Evaluating and Inducing Personality in Pre-trained Language Models

Transforming Science with Large Language Models: A Survey on AI-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluation

Efficient Geothermal Well-Control Optimization via Diffusion-Surrogate Reinforcement Learning

Polite Dialogue Generation Without Parallel Data

The Long-Horizon Task Mirage? Diagnosing Where and Why Agentic Systems Break

Reinforcing Chain-of-Thought Reasoning with Self-Evolving Rubrics

Inside the Scaffold: A Source-Code Taxonomy of Coding Agent Architectures

Data Mixing Laws: Optimizing Data Mixtures by Predicting Language Modeling Performance

ReCreate: Reasoning and Creating Domain Agents Driven by Experience