ProactAgent learns a proactive retrieval policy via reinforcement learning on paired task continuations, improving lifelong agent performance and cutting retrieval overhead on SciWorld, AlfWorld, and StuLife.
Self-refine: Iterative refinement with self-feedback
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Ask Only When Needed: Proactive Retrieval from Memory and Skills for Experience-Driven Lifelong Agents
ProactAgent learns a proactive retrieval policy via reinforcement learning on paired task continuations, improving lifelong agent performance and cutting retrieval overhead on SciWorld, AlfWorld, and StuLife.