MAC-Reasoner: A Multi-Agent Collaborative Framework for Enhancing Logical Reasoning in Large Language Models

摘要

Large language models (LLMs) face challenges in logical reasoning where correctness requires strict deductive procedures. Purely model-based approaches often suffer from hallucinations, while neuro-symbolic methods typically delegate deduction to external solvers, reducing the LLM to a mere translator. To address this, we propose MAC-Reasoner, a multi-agent framework that constructs a Logic-Augmented Context to enhance LLMs’ reasoning. In this framework, a translator agent converts problems into executable symbolic programs. Symbolic information from solver execution is transformed into the Logic-Augmented Context, serving as a verification reference where logical conflicts trigger heightened attention to violated constraints. We evaluate MAC-Reasoner with three backbone LLMs on four challenging benchmarks. Results show consistent and robust improvements over baselines. Furthermore, reasoning traces from MAC-Reasoner can be used for supervised fine-tuning of LLMs to achieve more accurate and efficient logical reasoning.