arXiv cs.AI Artificial Intelligence

Shangwen Sun, Alfredo Canziani, Yann LeCun, Jiachen Zhu: The Spike, the Sparse and the Sink: Anatomy of Massive Activations and Attention Sinks https://arxiv.org/abs/2603.05498 https://arxiv.org/pdf/2603.05498 https://arxiv.org/html/2603.05498

Benjamin Feuer, Lucas Rosenblatt, Oussama Elachqar: Towards Provably Unbiased LLM Judges via Bias-Bounded Evaluation https://arxiv.org/abs/2603.05485 https://arxiv.org/pdf/2603.05485 https://arxiv.org/html/2603.05485

Zhu, Bradford, Lai, Obiso, Venkatesha, Pustejovsky, Krishnaswamy: Distributed Partial Information Puzzles: Examining Common Ground Construction Under Epistemic Asymmetry https://arxiv.org/abs/2603.05450 https://arxiv.org/pdf/2603.05450 https://arxiv.org/html/2603.05450

Harvey Lederman, Kyle Mahowald: Dissociating Direct Access from Inference in AI Introspection https://arxiv.org/abs/2603.05414 https://arxiv.org/pdf/2603.05414 https://arxiv.org/html/2603.05414

Sunishchal Dev, Andrew Sloan, Joshua Kavner, Nicholas Kong, Morgan Sandler: Judge Reliability Harness: Stress Testing the Reliability of LLM Judges https://arxiv.org/abs/2603.05399 https://arxiv.org/pdf/2603.05399 https://arxiv.org/html/2603.05399

V\'aclav Jane\v{c}ek, Giovanni Sartor: Legal interpretation and AI: from expert systems to argumentation and LLMs https://arxiv.org/abs/2603.05392 https://arxiv.org/pdf/2603.05392 https://arxiv.org/html/2603.05392

Zirong Chen, Hongchao Zhang, Meiyi Ma: PACE: A Personalized Adaptive Curriculum Engine for 9-1-1 Call-taker Training https://arxiv.org/abs/2603.05361 https://arxiv.org/pdf/2603.05361 https://arxiv.org/html/2603.05361

Diego Armando Resendez Prado: Ailed: A Psyche-Driven Chess Engine with Dynamic Emotional Modulation https://arxiv.org/abs/2603.05352 https://arxiv.org/pdf/2603.05352 https://arxiv.org/html/2603.05352

Nghi D. Q. Bui: Building AI Coding Agents for the Terminal: Scaffolding, Harness, Context Engineering, and Lessons Learned https://arxiv.org/abs/2603.05344 https://arxiv.org/pdf/2603.05344 https://arxiv.org/html/2603.05344

Lewei Xie, Haoyu Zhang, Juan Yuan, Liangjun You, Yulong Chen, Yifan Zhang: UniSTOK: Uniform Inductive Spatio-Temporal Kriging https://arxiv.org/abs/2603.05301 https://arxiv.org/pdf/2603.05301 https://arxiv.org/html/2603.05301

Sicheng Fan, Rui Wan, Yifei Leng, Gaoning Liang, Li Ling, Yanyi Shang, Dehan Kong: WebChain: A Large-Scale Human-Annotated Dataset of Real-World Web Interaction Traces https://arxiv.org/abs/2603.05295 https://arxiv.org/pdf/2603.05295 https://arxiv.org/html/2603.05295

ELita Lobo, Xu Chen, Jingjing Meng, Nan Xi, Yang Jiao, Chirag Agarwal, Yair Zick, Yan Gao: STRUCTUREDAGENT: Planning with AND/OR Trees for Long-Horizon Web Tasks https://arxiv.org/abs/2603.05294 https://arxiv.org/pdf/2603.05294 https://arxiv.org/html/2603.05294

Gao Tianxi, Cai Yufan, Yuan Yusi, Dong Jin Song: X-RAY: Mapping LLM Reasoning Capability via Formalized and Calibrated Probes https://arxiv.org/abs/2603.05290 https://arxiv.org/pdf/2603.05290 https://arxiv.org/html/2603.05290

Zijie Meng, Zheyong Xie, Zheyu Ye, Chonggang Lu, Zuozhu Liu, Zihan Niu, Yao Hu, Shaosheng Cao: GCAgent: Enhancing Group Chat Communication through Dialogue Agents System https://arxiv.org/abs/2603.05240 https://arxiv.org/pdf/2603.05240 https://arxiv.org/html/2603.05240

Zhenyu Zhang, Guangyao Chen, Yixiong Zou, Yuhua Li, Ruixuan Li: Reclaiming Lost Text Layers for Source-Free Cross-Domain Few-Shot Learning https://arxiv.org/abs/2603.05235 https://arxiv.org/pdf/2603.05235 https://arxiv.org/html/2603.05235

Deming Chen, et al.: AI+HW 2035: Shaping the Next Decade https://arxiv.org/abs/2603.05225 https://arxiv.org/pdf/2603.05225 https://arxiv.org/html/2603.05225

Jonathan D. Chang, et al.: KARL: Knowledge Agents via Reinforcement Learning https://arxiv.org/abs/2603.05218 https://arxiv.org/pdf/2603.05218 https://arxiv.org/html/2603.05218

Zheng Li, Jiayi Xu, Zhikai Hu, Hechang Chen, Lele Cong, Yunyun Wang, Shuchao Pang: MedCoRAG: Interpretable Hepatology Diagnosis via Hybrid Evidence Retrieval and Multispecialty Consensus https://arxiv.org/abs/2603.05129 https://arxiv.org/pdf/2603.05129 https://arxiv.org/html/2603.05129

Boren Hu, Xiao Liu, Boci Peng, Xinping Zhao, Xiaoran Shang, Yun Zhu, Lijun Wu: Bidirectional Curriculum Generation: A Multi-Agent Framework for Data-Efficient Mathematical Reasoning https://arxiv.org/abs/2603.05120 https://arxiv.org/pdf/2603.05120 https://arxiv.org/html/2603.05120

Ravi Kiran Kadaboina: Jagarin: A Three-Layer Architecture for Hibernating Personal Duty Agents on Mobile https://arxiv.org/abs/2603.05069 https://arxiv.org/pdf/2603.05069 https://arxiv.org/html/2603.05069

Fan, Shi, Xu, Cai, Zeng, Ling, Shang, Kong: WebFactory: Automated Compression of Foundational Language Intelligence into Grounded Web Agents https://arxiv.org/abs/2603.05044 https://arxiv.org/pdf/2603.05044 https://arxiv.org/html/2603.05044

Hyuntae Park, Yeachan Kim, SangKeun Lee: Enhancing Zero-shot Commonsense Reasoning by Integrating Visual Knowledge via Machine Imagination https://arxiv.org/abs/2603.05040 https://arxiv.org/pdf/2603.05040 https://arxiv.org/html/2603.05040

Qian Huang, King Wang Poon: The Trilingual Triad Framework: Integrating Design, AI, and Domain Knowledge in No-code AI Smart City Course https://arxiv.org/abs/2603.05036 https://arxiv.org/pdf/2603.05036 https://arxiv.org/html/2603.05036

Mohd Safwan Uddin, Saba Hajira: AegisUI: Behavioral Anomaly Detection for Structured User Interface Protocols in AI Agent Systems https://arxiv.org/abs/2603.05031 https://arxiv.org/pdf/2603.05031 https://arxiv.org/html/2603.05031

Lu, Fang, Shao, Chen, Cui, Bian, Su, Ke, Qiu, Huang: Survive at All Costs: Exploring LLM's Risky Behaviors under Survival Pressure https://arxiv.org/abs/2603.05028 https://arxiv.org/pdf/2603.05028 https://arxiv.org/html/2603.05028

Janani Rangila, Akila Siriweera, Incheon Paik, Keitaro Naruse, Isuru Jayanada, Vishmika Devindi: S5-SHB Agent: Society 5.0 enabled Multi-model Agentic Blockchain Framework for Smart Home https://arxiv.org/abs/2603.05027 https://arxiv.org/pdf/2603.05027 https://arxiv.org/html/2603.05027

Alin-Gabriel Vaduva, Simona-Vasilica Oprea, Adela Bara: Measuring the Fragility of Trust: Devising Credibility Index via Explanation Stability (CIES) for Business Decision Support Systems https://arxiv.org/abs/2603.05024 https://arxiv.org/pdf/2603.05024 https://arxiv.org/html/2603.05024

Zuo Fei, Kezhi Wang, Xiaomin Chen, Yizhou Huang: BioLLMAgent: A Hybrid Framework with Enhanced Structural Interpretability for Simulating Human Decision-Making in Computational Psychiatry https://arxiv.org/abs/2603.05016 https://arxiv.org/pdf/2603.05016 https://arxiv.org/html/2603.05016

Yuzhe Zhou, Zhenglin Hua, Haiyun Guo, Yuheng Jia: Rethinking Representativeness and Diversity in Dynamic Data Selection https://arxiv.org/abs/2603.04981 https://arxiv.org/pdf/2603.04981 https://arxiv.org/html/2603.04981

Kenny Ye Liang, Zhongyi Pei, Huan Zhang, Yuhui Liu, Shaoxu Song, Jianmin Wang: Retrieval-Augmented Generation with Covariate Time Series https://arxiv.org/abs/2603.04951 https://arxiv.org/pdf/2603.04951 https://arxiv.org/html/2603.04951