01. Agent World Model in the Wild: Computer-Use Agent Environment Synthesis

88% worth reading · novelty 1.9/3 · new method · cs.AI

02. Same Simulation, Different Evidence: Where Retrieved Tool Output Costs LLM Agents Accuracy

88% worth reading · novelty 1.9/3 · benchmark/eval · cs.AI

03. WeAct: Dynamic Weight Switching as Agent Actions

86% worth reading · novelty 1.9/3 · new method · cs.AI

04. ASTOR: Benchmarking and Improving Autoformulation for Soft-Constraint Optimization with a Formal Grammar

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

05. OpenVLHarness: Real World Visual Agentic Tool-Use with Multimodal Memory

87% worth reading · novelty 1.4/3 · applied system · cs.AI

06. Learning Who Talks to Whom: Role-Aware Communication Topology Scheduling for Efficient LLM Multi-Agent Collaboration

84% worth reading · novelty 1.6/3 · new method · cs.MA

07. The One-Pixel of Reasoning: One Truthful Relation Is Enough to Mislead LLM Agents

79% worth reading · novelty 1.9/3 · new method · cs.MA

08. Autonomous intelligence for mining productivity: a multi-agent AI approach to operational value creation

79% worth reading · novelty 1.9/3 · new method · cs.MA

09. RefCraft: Benchmarking Visual-Reference-Conditioned Agentic Generation through Web Development

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

10. Can It Actually Work? Synthesizing Functional CAD Mechanisms

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

11. Same Data, Different Bytes: Serialization-Invariant Integrity Checks for Agent-Published Datasets

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

12. MAPS: A Multi-Agent Personalized Script-Driven Video Advertising System Enhanced by Reinforcement Learning

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

13. Train An Imaginative Agent

76% worth reading · novelty 1.8/3 · new method · cs.AI

14. RESIN: Multi-Chain Reasoning with Entity-Structured Indexing

81% worth reading · novelty 1.4/3 · new method · cs.CL

15. Discovery-Probability Graph Planning for Embodied Agents in Tasks with Hidden Cooperation Requirements

72% worth reading · novelty 1.9/3 · new method · cs.MA

16. Where is Physical RSI capability from? An Observational Scaling Law of LLM-as-policy

73% worth reading · novelty 1.8/3 · benchmark/eval · cs.AI

17. Behavioral Probes for Information Flow in LLM Swarms

75% worth reading · novelty 1.5/3 · new method · cs.MA

18. ProteinGeoBench: Frontier Structural-Biology Agents Are Fluent at Lookup but Lost in Geometry

78% worth reading · novelty 1.2/3 · benchmark/eval · cs.AI

19. MemT-1.0: Towards Memory-Native Evolution

73% worth reading · novelty 1.5/3 · new method · cs.CL

20. How Far Can an Agent Push? Trust-Safety Margins in Live Language-Based Economic Games

67% worth reading · novelty 1.8/3 · benchmark/eval · cs.MA