Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
Memadapter: Counterfactual Adaptation Against Memory-induced Sycophancy
Ruqing Ning, Haibo Meng, Zhishang Xiang +4
Long-term memory enables LLM-based agents to retain and reuse information across tasks and sessions, supporting personalization and long-horizon interactions. However, persistent m…
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…