Saved in:
Bibliographic Details
Main Authors: He, Chengbo, Zou, Bochao, Li, Xin, Chen, Jiansheng, Xing, Junliang, Ma, Huimin
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2501.00430
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929656915034112
author He, Chengbo
Zou, Bochao
Li, Xin
Chen, Jiansheng
Xing, Junliang
Ma, Huimin
author_facet He, Chengbo
Zou, Bochao
Li, Xin
Chen, Jiansheng
Xing, Junliang
Ma, Huimin
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2501_00430
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Enhancing LLM Reasoning with Multi-Path Collaborative Reactive and Reflection agents
He, Chengbo
Zou, Bochao
Li, Xin
Chen, Jiansheng
Xing, Junliang
Ma, Huimin
Computation and Language
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.
title Enhancing LLM Reasoning with Multi-Path Collaborative Reactive and Reflection agents
topic Computation and Language
url https://arxiv.org/abs/2501.00430