01. AdvSim2Real : Training Web Agents Against Adaptive Prompt Injection in a Web World Model

83% worth reading · novelty 1.9/3 · new method · cs.AI

02. EIO-Agents: The Missing Semantic Layer for AI Agent Evaluation

81% worth reading · novelty 2.1/3 · new method · cs.MA

03. SquidAgent: Parallelize Wisely, Coordinate Efficiently

84% worth reading · novelty 1.8/3 · new method · cs.CL

04. Token-Efficient Multi-Agent Collaboration via System One-Guided Computational Division of Labor

86% worth reading · novelty 1.7/3 · new method · cs.MA

05. Harness Engineering for Software Engineering via Modular Executable Dev-Primitives

82% worth reading · novelty 1.9/3 · new method · cs.MA

06. Agent in a Bottle: Can LLM Agents Turn Their Capabilities Into Cheap, Scalable Artifacts?

82% worth reading · novelty 1.9/3 · benchmark/eval · cs.AI

07. Visual Orchestration Tax in Agentic VLM Pipelines: Auditing and Certifying Visual Evidence Reuse

80% worth reading · novelty 1.9/3 · new method · cs.MA

08. ScienceClaw: Benchmarking Continual Self-Evolution of AI-for-Science Agents Across the Natural and Social Sciences

80% worth reading · novelty 1.9/3 · benchmark/eval · cs.AI

09. Joint Workflow and Prompt Optimization for User Behavior Simulation

78% worth reading · novelty 2.0/3 · new method · cs.MA

10. Do I Need the Cloud? Uncertainty-Aware Step-Level Handoff for Small Language Model Agents

84% worth reading · novelty 1.4/3 · new method · cs.MA

11. nanoMuse: An Open-Source Personal Agent for Every Device You Own

78% worth reading · novelty 1.8/3 · applied system · cs.AI

12. Recursive Game Creator: An Agentic Product-Level Experience-Oriented Game Harness

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

13. WorldSolver: Can LLM Agents Simulate the Physical Dynamics via Solver Generation?

77% worth reading · novelty 1.8/3 · benchmark/eval · cs.AI

14. Where Rules End and Judges Begin: Measuring the Judgment Boundary in Multi-Agent Systems Security

78% worth reading · novelty 1.7/3 · new method · cs.MA

15. Principled Under Pressure: Post-Training Decides Whether LLMs Act on Their Own Moral Judgment

75% worth reading · novelty 1.9/3 · benchmark/eval · cs.CL

16. Evidence-Bound Reasoning: Neuro-Semantic Verification of Biomedical AI in Glioblastoma Radiogenomics

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

17. EgoLAP: Learning from Egocentric Human Data through Language-Action Reasoning

73% worth reading · novelty 1.9/3 · new method · cs.AI

18. A Case Study in Assuring AI-Written Software

78% worth reading · novelty 1.5/3 · applied system · cs.MA

19. VeriFine: Scaling Verification for Self-Improvement in Embodied Reasoning

74% worth reading · novelty 1.7/3 · new method · cs.AI

20. IdeaAnchor: Teaching LLMs to Turn Literature into Research Ideas

72% worth reading · novelty 1.8/3 · new method · cs.AI