robotics
One Policy Takes On a Hundred Household Tasks
An independent BEHAVIOR Challenge team trained one checkpoint across 211 million demonstration frames, then routed fourteen hard tasks to a coding agent.
Summary
An independent BEHAVIOR Challenge team trained one checkpoint across 211 million demonstration frames, then routed fourteen hard tasks to a coding agent.
An independent team reports a single vision-language-action checkpoint for all 100 long-horizon tasks in the 2026 BEHAVIOR Challenge. Its learned policy scored 0.392 Q across the full set after a roughly one-pass, 200,000-step run over 211 million demonstration frames. Fourteen tasks were separately routed to a coding agent with observation and motion tools; on those tasks the authors report mean Q of 0.639 versus 0.108 for the learned policy. The public submission included only part of those agent results and finished with 0.446 Q and 27.3% full-task success.
Why it matters
An independent BEHAVIOR Challenge team trained one checkpoint across 211 million demonstration frames, then routed fourteen hard tasks to a coding agent.
Limits and context
- The public submission included only part of those agent results and finished with 0.446 Q and 27.3% full-task success.
Key claims
An independent BEHAVIOR Challenge team trained one checkpoint across 211 million demonstration frames, then routed fourteen hard tasks to a coding agent.
Qualification: The public submission included only part of those agent results and finished with 0.446 Q and 27.3% full-task success.
Evidence: source-2026-11-11-009
Sources
- arXiv:2611.14432v1arXiv / Cornell University · primary research
Corrections
No corrections have been recorded for this story.