Saved in:
Bibliographic Details
Main Authors: Wu, Yiran, Jia, Feiran, Zhang, Shaokun, Li, Hangyu, Zhu, Erkang, Wang, Yue, Lee, Yin Tat, Peng, Richard, Wu, Qingyun, Wang, Chi
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2306.01337
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914850725167104
author Wu, Yiran
Jia, Feiran
Zhang, Shaokun
Li, Hangyu
Zhu, Erkang
Wang, Yue
Lee, Yin Tat
Peng, Richard
Wu, Qingyun
Wang, Chi
author_facet Wu, Yiran
Jia, Feiran
Zhang, Shaokun
Li, Hangyu
Zhu, Erkang
Wang, Yue
Lee, Yin Tat
Peng, Richard
Wu, Qingyun
Wang, Chi
contents Employing Large Language Models (LLMs) to address mathematical problems is an intriguing research endeavor, considering the abundance of math problems expressed in natural language across numerous science and engineering fields. LLMs, with their generalized ability, are used as a foundation model to build AI agents for different tasks. In this paper, we study the effectiveness of utilizing LLM agents to solve math problems through conversations. We propose MathChat, a conversational problem-solving framework designed for math problems. MathChat consists of an LLM agent and a user proxy agent which is responsible for tool execution and additional guidance. This synergy facilitates a collaborative problem-solving process, where the agents engage in a dialogue to solve the problems. We perform evaluation on difficult high school competition problems from the MATH dataset. Utilizing Python, we show that MathChat can further improve previous tool-using prompting methods by 6%.
format Preprint
id arxiv_https___arxiv_org_abs_2306_01337
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle MathChat: Converse to Tackle Challenging Math Problems with LLM Agents
Wu, Yiran
Jia, Feiran
Zhang, Shaokun
Li, Hangyu
Zhu, Erkang
Wang, Yue
Lee, Yin Tat
Peng, Richard
Wu, Qingyun
Wang, Chi
Computation and Language
Machine Learning
Employing Large Language Models (LLMs) to address mathematical problems is an intriguing research endeavor, considering the abundance of math problems expressed in natural language across numerous science and engineering fields. LLMs, with their generalized ability, are used as a foundation model to build AI agents for different tasks. In this paper, we study the effectiveness of utilizing LLM agents to solve math problems through conversations. We propose MathChat, a conversational problem-solving framework designed for math problems. MathChat consists of an LLM agent and a user proxy agent which is responsible for tool execution and additional guidance. This synergy facilitates a collaborative problem-solving process, where the agents engage in a dialogue to solve the problems. We perform evaluation on difficult high school competition problems from the MATH dataset. Utilizing Python, we show that MathChat can further improve previous tool-using prompting methods by 6%.
title MathChat: Converse to Tackle Challenging Math Problems with LLM Agents
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2306.01337