Enhancing LLM Reasoning with Multi-Path Collaborative Reactive and Reflection agents
This work addresses accuracy and reliability issues in LLM-based agents for scientific reasoning, offering a practical solution for researchers and developers, though it appears incremental as it builds on existing agent and reflection methods.
The paper tackled the problem of insufficient accuracy and thought degeneration in LLM agents for complex scientific reasoning by proposing the RR-MP framework, which improved reasoning accuracy through multi-path collaborative agents without additional training, outperforming baselines in zero-shot and few-shot evaluations on moral, physics, and math tasks.
Agents have demonstrated their potential in scientific reasoning tasks through large language models. However, they often face challenges such as insufficient accuracy and degeneration of thought when handling complex reasoning tasks, which impede their performance. To overcome these issues, we propose the Reactive and Reflection agents with Multi-Path Reasoning (RR-MP) Framework, aimed at enhancing the reasoning capabilities of LLMs. Our approach improves scientific reasoning accuracy by employing a multi-path reasoning mechanism where each path consists of a reactive agent and a reflection agent that collaborate to prevent degeneration of thought inherent in single-agent reliance. Additionally, the RR-MP framework does not require additional training; it utilizes multiple dialogue instances for each reasoning path and a separate summarizer to consolidate insights from all paths. This design integrates diverse perspectives and strengthens reasoning across each path. We conducted zero-shot and few-shot evaluations on tasks involving moral scenarios, college-level physics, and mathematics. Experimental results demonstrate that our method outperforms baseline approaches, highlighting the effectiveness and advantages of the RR-MP framework in managing complex scientific reasoning tasks.