Self-Improvement with Auxiliary Rewards: Learning from Verified Traces and Evaluating Transfer Paper • 2610.41296 • Published 6 days ago • 7
Lies We Can See: Joint Verbal and Non-Verbal Deception by VLM Agents in Embodied Social Interactions Paper • 2608.30428 • Published Aug 31 • 13
FlashAdventure: A Benchmark for GUI Agents Solving Full Story Arcs in Diverse Adventure Games Paper • 2509.01052 • Published Sep 1, 2025 • 22