AI Papers arXiv

Generative AI-assisted Participatory Modeling in Socio-Environmental Planning under Deep Uncertainty Zhihao Pei, Nir Lipovetzky, Angela M. Rojas-Arevalo, Fjalar J. de Haan, Enayat A. Moallemi arxiv.org/abs/2603.17021 [𝚌𝚜.𝙰𝙸]

Transformers are Bayesian Networks Gregory Coppola arxiv.org/abs/2603.17063 [𝚌𝚜.𝙰𝙸]

Cascade-Aware Multi-Agent Routing: Spatio-Temporal Sidecars and Geometry-Switching Davide Di Gioia arxiv.org/abs/2603.17112 [𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙻𝙶]

How Clued up are LLMs? Evaluating Multi-Step Deductive Reasoning in a Text-Based Game Environment Rebecca Ansell, Autumn Toney-Wails arxiv.org/abs/2603.17169 [𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙲𝙻]

AI Scientist via Synthetic Task Scaling Ziyang Cai, Harkirat Behl arxiv.org/abs/2603.17216 [𝚌𝚜.𝙰𝙸]

Draft-and-Prune: Improving the Reliability of Auto-formalization for Logical Reasoning Zhiyu Ni, Zheng Liang, Liangcheng Song, Chenrui Cao, Xian Zhang, Alberto Sangiovanni-Vincentelli, Pierluigi Nuzzo arxiv.org/abs/2603.17233 [𝚌𝚜.𝙰𝙸]

Graph-Native Cognitive Memory for AI Agents: Formal Belief Revision Semantics for Versioned Memory Architectures Young Bin Park arxiv.org/abs/2603.17244 [𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙸𝚁 𝚌𝚜.𝙻𝙾]

Contrastive Reasoning Alignment: Reinforcement Learning from Hidden Representations Haozheng Luo, Yimin Wang, Jiahao Yu, Binghui Wang, Yan Chen arxiv.org/abs/2603.17305 [𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙲𝙻 𝚌𝚜.𝙻𝙶]

InfoDensity: Rewarding Information-Dense Traces for Efficient Reasoning Chengwei Wei, Jung-jae Kim, Longyin Zhang, Shengkai Chen, Nancy F. Chen arxiv.org/abs/2603.17310 [𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙲𝙻]

Physics-informed offline reinforcement learning eliminates catastrophic fuel waste in maritime routing Aniruddha Bora, Julie Chalfant, Chryssostomos Chryssostomidis arxiv.org/abs/2603.17319 [𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙻𝙶 𝚌𝚜.𝚁𝙾]

ShuttleEnv: An Interactive Data-Driven RL Environment for Badminton Strategy Modeling Ang Li, Xinyang Gong, Bozhou Chen, Yunlong Lu, Jiaming Ji, Yongyi Wang, Yaodong Yang, Wenxin Li arxiv.org/abs/2603.17324 [𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙻𝙶]

A Progressive Visual-Logic-Aligned Framework for Ride-Hailing Adjudication Weiming Wu, Zi-Jian Cheng, Jie Meng, Peng Zhen, Shan Huang, Qun Li, Guobin Wu, Lan-Zhe Guo arxiv.org/abs/2603.17328 [𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙻𝙶]

Towards Safer Large Reasoning Models by Promoting Safety Decision-Making before Chain-of-Thought Generation Jianan Chen, Zhifang Zhang, Shuo He, Linan Yue, Lei Feng, Minling Zhang arxiv.org/abs/2603.17368 [𝚌𝚜.𝙰𝙸]

From Digital Twins to World Models:Opportunities, Challenges, and Applications for Mobile Edge General Intelligence Jie Zheng, Dusit Niyato, Changyuan Zhao, Jiawen Kang, Jiacheng Wang arxiv.org/abs/2603.17420 [𝚌𝚜.𝙰𝙸]

Proactive Knowledge Inquiry in Doctor-Patient Dialogue: Stateful Extraction, Belief Updating, and Path-Aware Action Planning Zhenhai Pan, Yan Liu, Jia You arxiv.org/abs/2603.17425 [𝚌𝚜.𝙰𝙸]

Informative Semi-Factuals for XAI: The Elaborated Explanations that People Prefer Saugat Aryal, Mark T. Keane arxiv.org/abs/2603.17534 [𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙻𝙶]

Per-Domain Generalizing Policies: On Learning Efficient and Robust Q-Value Functions (Extended Version with Technical Appendix) Nicola J. Müller, Moritz Oster, Isabel Valera, Jörg Hoffmann, Timo P. Gros arxiv.org/abs/2603.17544 [𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙻𝙶]

DEAF: A Benchmark for Diagnostic Evaluation of Acoustic Faithfulness in Audio Language Models Jiaqi Xiong, Yunjia Qi, Qi Cao, Yu Zheng, Weisheng Xu, Ziteng Wang, Ruofan Liao, Yutong Zhang, Sichen Liu arxiv.org/abs/2603.18048 [𝚌𝚜.𝙰𝙸 𝚌𝚜.𝚂𝙳 𝚎𝚎𝚜𝚜.𝙰𝚂]

Continually self-improving AI Zitong Yang arxiv.org/abs/2603.18073 [𝚌𝚜.𝙰𝙸]

Multi-Trait Subspace Steering to Reveal the Dark Side of Human-AI Interaction Xin Wei Chia, Swee Liang Wong, Jonathan Pan arxiv.org/abs/2603.18085 [𝚌𝚜.𝙰𝙸]