Conference
Open access
2026
Generative Gamer: Learning Equilibrium Strategy by LLM-driven Dynamic Deduction
GenGamer is introduced, a framework that trains LLMs to reason like an expert player, and proposes the Deduction Tree Reward (DTR), a process-oriented mechanism that provides step-by-step feedback on the quality of the reasoning process, rather than relying solely on the final game outcome.
Yadong Zhang, Xinshu Shen, Yupei Ren et al.
· Annual Meeting of the Associ... · 0 citations