2 papers
cs.AI2026
EVISKILL: Grounding Skill Evolution in Replayable Evidence
Yan Zhou, Yili Wang, Yiwei Dai +2
Continual skill evolution enables LLM agents to accumulate and refine reusable procedural knowledge from interaction experience without updating model parameters. Its effectiveness…
cs.AI2026
TEPA: Revoking Stale Memories for Conflict-Robust Language Agents
Yan Zhou, Yue Ouyang, Kaiyang Zheng +1
Long-term memory enables language agents to reuse past facts, preferences, and task experience. Persistence also creates a central falsifiability problem: when the world changes, s…