3 papers
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…
cs.IR2026
Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligence
Yuyuan Feng, Zhishang Xiang, Chaobin Yang +32
LLMs have evolved from language generators to autonomous agents capable of complex, long-horizon tasks. This evolution has produced paradigms including Prompt Engineering to elicit…