Enhancing the General Agent Capabilities of Low-Paramter LLMs through Tuning and Multi-Branch Reasoning

Qinhao Zhou, Zihan Zhang, Xiang Xiang, Ke Wang, Yuchuan Wu, Yongbin Li


Abstract
Open-source pre-trained Large Language Models (LLMs) exhibit strong language understanding and generation capabilities, making them highly successful in a variety of tasks. However, when used as agents for dealing with complex problems in the real world, their performance is far inferior to large commercial models such as ChatGPT and GPT-4. As intelligent agents, LLMs need to have the capabilities of task planning, long-term memory, and the ability to leverage external tools to achieve satisfactory performance. Various methods have been proposed to enhance the agent capabilities of LLMs. On the one hand, methods involve constructing agent-specific data and fine-tuning the models. On the other hand, some methods focus on designing prompts that effectively activate the reasoning abilities of the LLMs. We explore both strategies on the 7B and 13B models. We propose a comprehensive method for constructing agent-specific data using GPT-4. Through supervised fine-tuning with constructed data, we find that for these models with a relatively small number of parameters, supervised fine-tuning can significantly reduce hallucination outputs and formatting errors in agent tasks. Furthermore, techniques such as multi-path reasoning and task decomposition can effectively decrease problem complexity and enhance the performance of LLMs as agents. We evaluate our method on five agent tasks of AgentBench and achieve satisfactory results.
Anthology ID:
2024.findings-naacl.184
Volume:
Findings of the Association for Computational Linguistics: NAACL 2024
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2922–2931
Language:
URL:
https://aclanthology.org/2024.findings-naacl.184
DOI:
10.18653/v1/2024.findings-naacl.184
Bibkey:
Cite (ACL):
Qinhao Zhou, Zihan Zhang, Xiang Xiang, Ke Wang, Yuchuan Wu, and Yongbin Li. 2024. Enhancing the General Agent Capabilities of Low-Paramter LLMs through Tuning and Multi-Branch Reasoning. In Findings of the Association for Computational Linguistics: NAACL 2024, pages 2922–2931, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
Enhancing the General Agent Capabilities of Low-Paramter LLMs through Tuning and Multi-Branch Reasoning (Zhou et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-naacl.184.pdf