Search

huggingface.co › papers › 2605.09998

Paper page - Continual Harness: Online Adaptation for Self-Improving Foundation Agents

…Seth Karten , , , , , , , Abstract A self-improving AI system for embodied agents autonomously refines its own prompts, skills, and memory through continuous learning without environment resets, achieving human-level performance in complex video…

May 13, 2026

Top stories

huggingface.co

Paper page - VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization

1w ago

huggingface.co

Paper page - ESPO: Early-Stopping Proximal Policy Optimization

1w ago

huggingface.co › papers › 2605.07637

Paper page - Learning to Communicate Locally for Large-Scale Multi-Agent Pathfinding

…Although solving MAPF optimally is NP-hard, scalable and efficient solvers are critical for real-world applications such as logistics and search-and-rescue. To this end, the research community has proposed…

May 15, 2026