Book
Open access
Jul 2026
Exploration-and-Thinking: Agentic Reasoning over Knowledge Graphs via an LLM-RL Synergized Framework
EAT (Exploration-and-Thinking), a novel agentic framework that synergizes LLMs with Reinforcement Learning (RL) for efficient and faithful reasoning on KGs, which surpasses the reasoning capability of GPT-4o while utilizing a significantly smaller 8B-parameter LLM.
Yi Xia, Gang Zhou, Jing Chen et al.
· Annual International ACM SIG... · 0 citations