Clearing the Fog: Towards Installing and Refining Proactive Exploration Capabilities in LLM Agents
This work proposes \the authors', a novel method designed to instill and refine proactive exploration in LLM agents, which consists of two components: Exploratory Data Construction, which synthesizes exploration-rich trajectories to mitigate the hindsight bias of standard demonstrations; and RL Optimization with Contra...
Zhizhao Guan, Chen Huang, Zi-Ming Liu et al.
· 1 citation