01. Librarian Agents: Training LLMs to Curate Long-Context Workspaces that Anticipate Future Queries

86% worth reading · novelty 2.0/3 · new method · cs.CL

02. KnowGPO: Knowledge-Grouped Policy Optimization for Search Agents

85% worth reading · novelty 1.9/3 · new method · cs.AI

03. FDE-Gym: The Last Mile of AI Delivery

83% worth reading · novelty 2.0/3 · benchmark/eval · cs.AI

04. 3DCodeVerse: Exploring 3D Worlds as Code

84% worth reading · novelty 1.9/3 · benchmark/eval · cs.AI

05. Diviner: Agentic RCA with Human-Governed Adaptation for Large-Scale Infrastructure

85% worth reading · novelty 1.6/3 · applied system · cs.MA

06. MLExpert: Towards a Generalist Agentic Model for Autonomous Machine Learning Engineering

85% worth reading · novelty 1.6/3 · new method · cs.AI

07. Learning to Steer LLM Agents and Multi-Agent Systems

85% worth reading · novelty 1.6/3 · new method · cs.LG

08. Bias Control and Injection for Multi-Agent Aggregation

81% worth reading · novelty 1.9/3 · new method · cs.MA

09. Believed but Not Said: Measuring Hidden Belief Collapse in Multi-Agent LLM Discussions

79% worth reading · novelty 1.9/3 · benchmark/eval · cs.MA

10. MetaShare: Failure-Aware Collective Self-Improvement for Open-Ended Agents

81% worth reading · novelty 1.7/3 · new method · cs.MA

11. AI Consilium: a Benchmark of LLM Clinical Multidisciplinary Second Opinions

82% worth reading · novelty 1.6/3 · benchmark/eval · cs.CL

12. Agentic-Priors: Using Large Language Models to Address the Cold Start Problem in Preference Elicitation

77% worth reading · novelty 1.8/3 · new method · cs.MA

13. A Responsibility-Centered Coordination Mechanism for Decentralized Multi-Agent Systems

79% worth reading · novelty 1.6/3 · new method · cs.MA

14. Discovering state-of-the-art quantum circuits with large language models

72% worth reading · novelty 2.0/3 · new method · cs.AI

15. Training Reasoning Models to Generate Diverse Scientific Ideas

77% worth reading · novelty 1.6/3 · new method · cs.CL

16. Lean Graph Search for Formal Theorem Proving

79% worth reading · novelty 1.4/3 · new method · cs.LG

17. CoDA: Co-Evolution of Data Engines and Action Policies

69% worth reading · novelty 2.0/3 · new method · cs.AI

18. Decentralized LLM Workflows via Sequential Auctions

72% worth reading · novelty 1.7/3 · new method · cs.MA

19. OmniVerifier-C1: Decomposed Graded Verifier for Rule-Governed Generative World Modeling

69% worth reading · novelty 1.7/3 · new method · cs.CL

20. MindEval2: Clinically Grounded Patients and Rubrics for Evaluating Language Models in Mental Health Support

73% worth reading · novelty 1.3/3 · benchmark/eval · cs.CL