CAFE: Closed-Loop Autonomous Task Formulation and Execution without Instance-Specific Instructions
Overview
This research introduces CAFE, a system for scene-driven robot autonomy that selects and executes tasks within predefined categories like cleaning and storage without instance-specific goals. The architecture maintains online memory of objects and zones, using a rule-guided Trigger-LLM to admit formulation from evidence while Draft, Complete, and Audit modules propose goals, resolve details, and check dependencies. Evaluation on 12 AI2-THOR scenes compares three backbones and task-complexity tiers using coverage, constraint, and execution metrics, with results showing Tri-LLM achieving higher GCR scores than baselines. The paper includes controls on completion, auditing, zones, feedback, triggering, and prompt examples, alongside LimoCobot traces illustrating storage, cleanup, and recovery from failed grasps.
Generated from attributed reports · Updated 1 days ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Control: reported autonomous
“CAFE: Closed-Loop Autonomous Task Formulation and Execution without Instance-Specific Instructions”
Exact source · revision 1Source owner not reported
Reported quantity · scenes evaluated: 12 other · reported trials
“rigger-LLM admits formulation from accumulated evidence; Draft, Complete, and Audit propose goals, resolve execution details, and check dependencies. Outcomes update memory for correction and subsequent discovery. Evaluation in 12 AI2-THOR scenes compares three backbones and task-complexity tiers using coverage, constraint, and execution metrics. Tri-LLM records higher GCR scores than the evaluated baselines across t”
Exact source · revision 1Source owner not reported
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalCAFE: Closed-Loop Autonomous Task Formulation and Execution without Instance-Specific Instructions
This research introduces CAFE, a system for scene-driven robot autonomy that selects and executes tasks within predefined categories like cleaning and storage without instance-specific goals. The architecture maintains online memory of objects and zones, using a rule-guided Trigger-LLM to admit formulation from evidence while Draft, Complete, and Audit modules propose goals, resolve details, and check dependencies. Evaluation on 12 AI2-THOR scenes compares three backbones and task-complexity tiers using coverage, constraint, and execution metrics, with results showing Tri-LLM achieving higher GCR scores than baselines. The paper includes controls on completion, auditing, zones, feedback, triggering, and prompt examples, alongside LimoCobot traces illustrating storage, cleanup, and recovery from failed grasps.
Event coverage history
Current attention 9·Peak within the comparable range 10（2026-11-11 06:00 UTC）·Change within the comparable range over 24 hours –
The trend compares participants observed continuously; its scope may be narrower than current attention totals. Hover or click to explore hourly observations, or use the left and right arrow keys.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).