01. RFChipAgent: Multi-Agentic AI Flow for Analog/RF Chip Design

83% worth reading · novelty 2.2/3 · applied system · cs.MA

02. Accurate but Not Humble: Evaluating Epistemic Humility in LLM Agents under Knowledge Conflict

82% worth reading · novelty 1.8/3 · benchmark/eval · cs.CL

03. BrickBench: Evaluating Agentic Brick Design

82% worth reading · novelty 1.7/3 · benchmark/eval · cs.AI

04. RoboRSI: Stable, efficient, and reusable robot self-evolution in complex real-world environments

80% worth reading · novelty 1.8/3 · new method · cs.AI

05. Long Text to Predictive Features: LLM-Guided Blockwise Feature Engineering via Executable Program Search

79% worth reading · novelty 1.8/3 · new method · cs.CL

06. SWE-Journey: Towards More Realistic Evaluation of Coding Assistants through Long-Horizon, Multi-Turn Interaction

81% worth reading · novelty 1.7/3 · benchmark/eval · cs.MA

07. OA-MAP: Evidence-Grounded Multi-Agent Multimodal Framework for Interpretable Knee Osteoarthritis Progression

80% worth reading · novelty 1.7/3 · applied system · cs.MA

08. OnTrack: Real-Time Monitoring and Intervention in LLM Agent Trajectories via Streaming Structure-Aware Optimal Transport

81% worth reading · novelty 1.6/3 · new method · cs.CL

09. GeoReform: Reflective Formalization Evolution for Multimodal Geometry Problem Solving

81% worth reading · novelty 1.6/3 · new method · cs.AI

10. From Reactive Containment to Proactive Assurance: Lessons from OpenAI, Anthropic, and Google Agent Security Incidents

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

11. MindFlow: Mind Supernet Powered Thinking Flows for Research Idea Innovation

75% worth reading · novelty 1.9/3 · new method · cs.MA

12. Ecology of AI Agents: Collaboration Creates a Population Threshold for Takeoff

72% worth reading · novelty 2.0/3 · survey/position · cs.AI

13. ARC: A Reasoning Recipe for Robot Foundation Models

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

14. Can AI Agents Learn Their Way to the Top? Evaluating Heuristic Learning in a Long-Running Game Agent Competition

77% worth reading · novelty 1.6/3 · benchmark/eval · cs.CL

15. Mental-Models for Multi-Agent Systems

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

16. ViSkill: Reinforcing VLM Agents with Evolving Visual-Native Skills

70% worth reading · novelty 1.7/3 · new method · cs.CL

17. Reading the Room: Foundations, Design, and Challenges of Normative Competence in LLMs

64% worth reading · novelty 2.0/3 · benchmark/eval · cs.MA

18. Personalization Matters: Long-Horizon Conversation Agent with User-Centric Information in Online Shopping Interactions

77% worth reading · novelty 1.0/3 · new method · cs.MA

19. Caught in the Act: Probes Effectively Detect Sabotage and Catch Unverbalized Deception

74% worth reading · novelty 1.2/3 · new method · cs.AI

20. Cited but Not Consulted: A Counterfactual Audit of Legal Chain-of-Thought Faithfulness

56% worth reading · novelty 1.9/3 · benchmark/eval · cs.CL