research
The Agent Split the World From the Job
Mimir stores environmental knowledge separately from task history, then grounds both memories when an embodied agent must act over long horizons.
Summary
Mimir stores environmental knowledge separately from task history, then grounds both memories when an embodied agent must act over long horizons.
Mimir separates an embodied agent's memory into world and task stores and dynamically grounds retrieved records against the current scene. The authors report a maximum success rate of 42.5 percent, a 23 percent average and an 8.5-point overall improvement over their best same-backbone comparison; they also report 86 percent on long-horizon EB-Habitat tasks. These are preprint benchmark results, and the authors say code is forthcoming rather than presently documenting a deployed robot system.
Why it matters
Mimir stores environmental knowledge separately from task history, then grounds both memories when an embodied agent must act over long horizons.
Limits and context
No additional limitation was separately recorded.
Key claims
Mimir stores environmental knowledge separately from task history, then grounds both memories when an embodied agent must act over long horizons.
Evidence: source-2026-08-06-008
Sources
- arXiv preprint 2608.04933arXiv · primary research
Corrections
No corrections have been recorded for this story.