CheckerBench: Can Long-Horizon Agents Synthesize Static-Analysis Checkers? Paper • 2610.07557 • Published 5 days ago • 64
From Traces to Agentic Worlds: Agentic Language World Models for Interactive Environment Simulation Paper • 2610.06100 • Published 6 days ago • 130
Realtime-Venus: A full-duplex interaction system with asynchronous delegation Paper • 2609.13814 • Published 29 days ago • 199