ASH: Agents that Self-Hone in Long-Horizon Worlds
Quick summary
arXiv:2605.14211v4 Announce Type: replace Abstract: Long-horizon visuomotor tasks remain a fundamental challenge in AI, as current methods rely on hand-engineered rewards or action-labeled demonstrations, neither of which scales. We introduce ASH, an agentic system that learns a long-horizon policy from unlabeled, noisy internet video, without reward shaping or expert annotation. ASH follows a self-improvement loop; when it gets stuck, ASH learns an Inverse Dynamics Model (IDM) from its own trajectories, and uses its IDM to extract supervision from relevant internet video. ASH uses unsupervise
Key takeaways
- arXiv:2605.14211v4 Announce Type: replace Abstract: Long-horizon visuomotor tasks remain a fundamental challenge in AI, as current methods rely on hand-engineered rewards or action-labeled demonstrations, neither of which scales.
- We introduce ASH, an agentic system that learns a long-horizon policy from unlabeled, noisy internet video, without reward shaping or expert annotation.
- ASH follows a self-improvement loop; when it gets stuck, ASH learns an Inverse Dynamics Model (IDM) from its own trajectories, and uses its IDM to extract supervision from relevant internet video.
Why it matters
“ASH: Agents that Self-Hone in Long-Horizon Worlds” may affect what data AI products can use and where accountability sits. Product teams should watch compliance duties, rights holders should watch enforcement, and users should watch transparency and appeal mechanisms.
Member comments