一作ACL 2026Findings· Findings of ACL
SAM em: State-Aware Memory as a Fine-Grained Memory for LLM Agents in Decision-Making
Tong Wang · Pei Xu · Shiyue Cao · Likun Yang · Daipeng Li · Jianbin Jiao · Kaiqi Huang
摘要
Existing LLM-based agents primarily utilize coarse-grained experiential memory, where experiences are retrieved based on global task or scene context. While effective in simple settings, such coarse-grained memory lacks the situational alignment required for complex multi-step decision-making. As...