AgentSWE: Can Coding Agents Build the Agent You Actually Want? Paper • 2610.13361 • Published 12 days ago • 238
From Traces to Agentic Worlds: Agentic Language World Models for Interactive Environment Simulation Paper • 2610.06100 • Published 16 days ago • 145
Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments? Paper • 2610.08215 • Published 13 days ago • 154