Embodied agents maintain persistent identity while evolving modular capabilities through a closed-loop process, raising simulated task success from 32.4% to 91.3% with zero policy drift.
DEPS: Describe, explain, plan and select: Interactive planning with large language models enables open-world multi-task agents,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Learning Without Losing Identity: Capability Evolution for Embodied Agents
Embodied agents maintain persistent identity while evolving modular capabilities through a closed-loop process, raising simulated task success from 32.4% to 91.3% with zero policy drift.