K-Level Reasoning: Establishing Higher Order Beliefs in Large Language Models for Strategic Reasoning
This work addresses the challenge of strategic reasoning in LLMs for multi-agent environments, establishing a foundational framework for future research, though it is incremental as it adapts existing game theory concepts to LLMs.
The paper tackled the problem of enabling Large Language Models (LLMs) to perform strategic reasoning by proposing the K-Level Reasoning (K-R) framework, which uses recursive mechanisms to form higher-order beliefs, and demonstrated its advantages on four testbeds including game theory and social intelligence tasks.
Strategic reasoning is a complex yet essential capability for intelligent agents. It requires Large Language Model (LLM) agents to adapt their strategies dynamically in multi-agent environments. Unlike static reasoning tasks, success in these contexts depends on anticipating other agents' beliefs and actions while continuously adjusting strategies to achieve individual goals. LLMs and LLM agents often struggle with strategic reasoning due to the absence of a reasoning framework that enables them to dynamically infer others' perspectives and adapt to changing environments. Inspired by the Level-K framework from game theory and behavioral economics, which extends reasoning from simple reactions to structured strategic depth, we propose a novel framework: "K-Level Reasoning with Large Language Models (K-R)." This framework employs recursive mechanisms to enable LLMs to achieve varying levels of strategic depth, allowing agents to form higher order beliefs - beliefs about others' beliefs. We validate this framework through rigorous testing on four testbeds: two classical game theory problems and two social intelligence tasks. The results demonstrate the advantages of K-R in strategic reasoning. Our work presents the first recursive implementation of strategic depth in large language models (LLMs). It establishes a foundation for future research into theory of mind and strategic reasoning in LLMs.