Ask Only When Needed: Proactive Retrieval from Memory and Skills for Experience-Driven Lifelong Agents

ArXi:2604.20572v1 Announce Type: new Online lifelong learning enables agents to accumulate experience across interactions and continually improve on long-horizon tasks. However, existing methods typically treat retrieval from past experience as a passive operation, triggering it only at task initialization or after completing a step. Consequently, agents often fail to identify knowledge gaps during interaction and proactively retrieve the most useful experience for the current decision.