HomeArtificial Intelligence

Artificial Intelligence

Reasoning, planning, agents, knowledge representation and general AI methods.

Showing the latest 40 / 40 papers(All fields:Computation & LanguageMachine LearningComputer VisionSoundAudio & Speech Processing

Physics Is All You Need? A Case Study in Physicist-Supervised AI Development of Scientific Software
Artificial Intelligence · 2026-05 · arXiv:2605.30353
Nhat-Minh Nguyen
SchGen: PCB Schematic Generation with Semantic-Grounded Code Representations
Artificial Intelligence · 2026-05 · arXiv:2605.30345
Qinpei Luo, Ruichun Ma, Xinyu Zhang, Lili Qiu
Tiny but Trusted: Efficient Vision-Language Reasoning for Time-Series Anomaly Detection
Artificial Intelligence · 2026-05 · arXiv:2605.30344
Xiaona Zhou, Muntasir Wahed, Tianjiao Yu, Constantin Brif +1
Locally Coherent, Globally Incoherent: Bounding Compositional Incoherence in Multi-Component LLM Agents
Artificial Intelligence · 2026-05 · arXiv:2605.30335
Anany Kotawala
Demystifying Data Organization for Enhanced LLM Training
Artificial Intelligence · 2026-05 · arXiv:2605.30334
Yalun Dai, Yangyu Huang, Tongshen Yang, Yonghan Wang +7
MIRA: Mid-training Rubric Anchoring for Source-Aware Data Selection
Artificial Intelligence · 2026-05 · arXiv:2605.30288
Haowen Wang, Yaxin Du, Jian Yang, Jiajun Wu +7
ProjectionBench: Evaluating Scientific Hypothesis Generation in LLMs Under Progressive Information Disclosure
Artificial Intelligence · 2026-05 · arXiv:2605.30284
A. J. Lew, Y. Cao, M. J. Buehler
mcp-proto-okn: Natural-language access to open scientific knowledge graphs through the Model Context Protocol
Artificial Intelligence · 2026-05 · arXiv:2605.30283
Peter W. Rose, Benjamin M. Good, Amanda M. Saravia-Butler, Charlotte A. Nelson +6
When Should Models Change Their Minds? Contextual Belief Management in Large Language Models
Artificial Intelligence · 2026-05 · arXiv:2605.30219
Haoming Xu, Weihong Xu, Zongrui Li, Mengru Wang +5
Persona Conditioning of Brand Recommendations in Retrieval-Augmented Commercial Chat: A Prominence-Stratified Cross-Provider Audit
Artificial Intelligence · 2026-05 · arXiv:2605.30207
Will Jack, Noah Lehman, Keller Maloney, Sarah Xu
Double-Edged Sword or Sharp Tool? Designing and Evaluating Triadic LLM-Teacher Collaboration for K-12 Writing at Scale
Artificial Intelligence · 2026-05 · arXiv:2605.30200
Canran Wang, Yuwen Yang, Zhen Wang, Ming Ma +4
Modularizing Educational LLM-Agency for Fostering Responsible Learning Assistance
Artificial Intelligence · 2026-05 · arXiv:2605.30187
Julius Gabelmann, Felix Jahn, Kevin Baum, Sophie van Rossum +3
BioRefusalAudit: Auditing Biosecurity Refusal Depth Using General and Domain-Fine-Tuned Sparse Autoencoders
Artificial Intelligence · 2026-05 · arXiv:2605.30162
Caleb DeLeeuw
Meta-Cognitive Memory Policy Optimization for Long-Horizon LLM Agents
Artificial Intelligence · 2026-05 · arXiv:2605.30159
Ziyan Liu, Zhezheng Hao, Yeqiu Chen, Hong Wang +6
Temporal Stability and Few-Shot Prompting in Math Task Assessment
Artificial Intelligence · 2026-05 · arXiv:2605.30151
Danielle S. Fox, Brenda L. Robles, Elizabeth DiPietro Brovey, Christian D. Schunn
Anchorless Diversification for Parallel LLM Ideation
Artificial Intelligence · 2026-05 · arXiv:2605.30150
Fares Nabil Ibrahim, Nafis Saami Azad, Raiyan Abdul Baten
AgentSchool: An LLM-Powered Multi-Agent Simulation for Education
Artificial Intelligence · 2026-05 · arXiv:2605.30144
Yulei Ye, Wenhao Li, Zhong Wen, Yunshu Huang +22
Enhancing Multi-Agent Communication through Attention Steering with Context Relevance
Artificial Intelligence · 2026-05 · arXiv:2605.30136
Hongxiang Zhang, Yuan Tian, Tianyi Zhang
VLA-Trace: Diagnosing Vision-Language-Action Models through Representation and Behavior Tracing
Artificial Intelligence · 2026-05 · arXiv:2605.30117
Haoyuan Shi, Xiancong Ren, Yingji Zhang, Qinfan Zhang +8
PokerSkill: LLMs Can Play Expert-Level Poker without Training or Solvers
Artificial Intelligence · 2026-05 · arXiv:2605.30094
Boning Li, Baoxiang Wang, Longbo Huang
Selective QA over Conflicting Multi-Source Personal Memory: A Diagnostic Testbed and Method Comparison
Artificial Intelligence · 2026-05 · arXiv:2605.30087
Tiancheng Yang, Matthias Schonlau, Ilia Sucholutsky
Conformal Certification of Reasoning Trace Prefixes
Artificial Intelligence · 2026-05 · arXiv:2605.30085
Matt Y. Cheung, Ashok Veeraraghavan, Hanjie Chen, Guha Balakrishnan
Robust and Generalizable Safety Steering for Text-to-Image Diffusion Transformers
Artificial Intelligence · 2026-05 · arXiv:2605.30049
Zihao Xue, Yan Wang, Zhen Bi, Long Ma +6
Learning to Choose: An Empowerment-Guided Multi-Agent System with semantic communication for Adaptive Method Selection
Artificial Intelligence · 2026-05 · arXiv:2605.30042
Geremy Loachamín-Suntaxi, Robert Lazar, Dimitrios G. Giovanis, Ioannis G. Kevrekidis +1
Domain-Specific Data Synthesis for LLMs via Minimal Sufficient Representation Learning
Artificial Intelligence · 2026-05 · arXiv:2605.30039
Tong Ye, Hang Yu, Tengfei Ma, Xuhong Zhang +5
Teaching Values to Machines: Simulating Human-Like Behavior in LLMs
Artificial Intelligence · 2026-05 · arXiv:2605.30036
Asaf Yehudai, Naama Rozen, Ariel Gera
RAISE: RAG Design as an Architecture Search Problem
Artificial Intelligence · 2026-05 · arXiv:2605.30029
Zhen Chen, Yibing Liu, Weihao Xie, Yu Liang +2
From GPS Points to Travel Patterns: Flexible and Semantic Trajectory Generation with LLMs
Artificial Intelligence · 2026-05 · arXiv:2605.30014
Silin Zhou, Chenhao Wang, Yuntao Wen, Shuo Shang +2
KairosAgent: Agentic Time Series Forecasting with Fused Semantic Reasoning
Artificial Intelligence · 2026-05 · arXiv:2605.30002
Kun Feng, Ziwei Shan, Yuchen Fang, Yiyang Tan +5
Cookie-Bench: Continuous On-screen Key Interaction Evaluation for Web Generation
Artificial Intelligence · 2026-05 · arXiv:2605.30000
Haoyue Yang, Zhangxiao Shen, Fan Ding, Hangting Lou +7
Accelerating Constrained Decoding with Token Space Compression
Artificial Intelligence · 2026-05 · arXiv:2605.29986
Michael Sullivan, Alexander Koller
Compass: Navigating Global Marine Lead Data Integration through Expert-Guided LLM Agent
Artificial Intelligence · 2026-05 · arXiv:2605.29966
Yiming Liu, Bin Lu, Meng Jin, Ziyuan Sang +5
Meta-Programming for Linear-time Temporal Answer Set Programming
Artificial Intelligence · 2026-05 · arXiv:2605.29965
Susana Hahn, Amade Nems, Javier Romero, Torsten Schaub
Formalizing Mathematics at Scale
Artificial Intelligence · 2026-05 · arXiv:2605.29955
Ahmad Rammal, Niket Patel, Fabian Gloeckle, Amaury Hayat +4
MuPHI: Learning Implicit Multimodal Harm Reasoning via Semantically Grounded Reward Optimization
Artificial Intelligence · 2026-05 · arXiv:2605.29951
Anisha Saha, Varsha Suresh, Teodora Kamova, Sophia Wiedmann +2
Make LLM Learn to Synthesize from Streaming Experiences through Feedback
Artificial Intelligence · 2026-05 · arXiv:2605.29940
Zhenlin Hu, Yan Wang, Zhen Bi, Zihao Xue +6
It`s All About Speed: AI`s Impact on Workflow in Music Production
Artificial Intelligence · 2026-05 · arXiv:2605.29931
Finn McClellan, Fabio Morreale
Toward AI Systems That Understand Self and Others: A Multi-Phase Inference Framework for Human Cognitive Diversity and World-Model Alignment
Artificial Intelligence · 2026-05 · arXiv:2605.29930
Toru Takahashi
On the Geometry of Games and their Solvers
Artificial Intelligence · 2026-05 · arXiv:2605.29919
Yaqi Sun, Julian Ma, David Mguni
Redundant or Necessary? A Benchmark for Detecting Redundant Steps in Agent Trajectories
Artificial Intelligence · 2026-05 · arXiv:2605.29893
Minyang Hu, Bo Yang, Zhinuo Zhou, Jiachen Liang +3