作者位次 #4/7ACL 2026Findings· Findings of ACL
G raph M ind: LLM s as Dynamic Knowledge Builders for Sequential Decision-Making
Sunguk Shin · Hayeong Lee · Jun Ho Seo · Jinho Lee · Myunsoo Kim · Minsuk Chang · Byung-Jun Lee
摘要
While the reasoning capabilities of large language models (LLMs) have advanced considerably, efficiently internalizing and leveraging new information in dynamically interactive environments remains a significant challenge. This limitation is particularly pronounced in partially observable environ...