AgentSWE: Can Coding Agents Build the Agent You Actually Want? Paper • 2610.13361 • Published 6 days ago • 208
From Traces to Agentic Worlds: Agentic Language World Models for Interactive Environment Simulation Paper • 2610.06100 • Published 10 days ago • 141
Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments? Paper • 2610.08215 • Published 7 days ago • 154