Conference paper · 2024 · Open access
Enhancing the General Agent Capabilities of Low-Paramter LLMs through Tuning and Multi-Branch Reasoning
Findings of the Association for Computational Linguistics: NAACL, 2922–2931 · Published 1 January 2024 · DOI 10.18653/v1/2024.findings-naacl.184
In brief
“Enhancing the General Agent Capabilities of Low-Paramter LLMs through Tuning and Multi-Branch Reasoning” is a 2024 conference paper by Qinhao Zhou and 5 co-authors, published in Findings of the Association for Computational Linguistics: NAACL. OpenAlex counts 14 citations as of 16 November 2026, which puts it in the top 5% of works published in 2024 by citations. It is open access under a CC BY licence: the full text is free to read at Findings of the Association for Computational Linguistics: NAACL.
- Citations
- 14
- Most cited in
- 2026 (8)
- Field-weighted impact
- 2.14
- References
- 29
- Authors
- 6
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 finetuning 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.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Zhou, Q., Zhang, Z., Xiang, X., Wang, K., Wu, Y., & Li, Y. (2024). Enhancing the General Agent Capabilities of Low-Paramter LLMs through Tuning and Multi-Branch Reasoning. Findings of the Association for Computational Linguistics: NAACL, 2922–2931. https://doi.org/10.18653/v1/2024.findings-naacl.184
MLA 9
Zhou, Qinhao, et al. “Enhancing the General Agent Capabilities of Low-Paramter LLMs through Tuning and Multi-Branch Reasoning.” Findings of the Association for Computational Linguistics: NAACL, 2024, pp. 2922–2931. https://doi.org/10.18653/v1/2024.findings-naacl.184.
Chicago
Zhou, Qinhao, 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.” Findings of the Association for Computational Linguistics: NAACL: 2922–2931. https://doi.org/10.18653/v1/2024.findings-naacl.184.
Harvard
Zhou, Q. et al. (2024) ‘Enhancing the General Agent Capabilities of Low-Paramter LLMs through Tuning and Multi-Branch Reasoning’, Findings of the Association for Computational Linguistics: NAACL, pp. 2922–2931. doi:10.18653/v1/2024.findings-naacl.184.
IEEE
Q. Zhou, Z. Zhang, X. Xiang, K. Wang, Y. Wu, and Y. Li, “Enhancing the General Agent Capabilities of Low-Paramter LLMs through Tuning and Multi-Branch Reasoning,” Findings of the Association for Computational Linguistics: NAACL, pp. 2922–2931, 2024, doi: 10.18653/v1/2024.findings-naacl.184.
BibTeX
@inproceedings{zhou2024enhancing,
title = {{Enhancing the General Agent Capabilities of Low-Paramter LLMs through Tuning and Multi-Branch Reasoning}},
author = {Zhou, Qinhao and Zhang, Zihan and Xiang, Xiang and Wang, Ke and Wu, Yuchuan and Li, Yongbin},
booktitle = {Findings of the Association for Computational Linguistics: NAACL},
year = {2024},
pages = {2922--2931},
doi = {10.18653/v1/2024.findings-naacl.184},
url = {https://doi.org/10.18653/v1/2024.findings-naacl.184}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2024 | 3 | |
| 2025 | 3 | |
| 2026 | 8 |
Its field-weighted citation impact is 2.14: it has been cited 2.14 times as often as the average work of the same field, type and year (1.00 is the world average).
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- LLM agents
- supervised fine-tuning
- task decomposition
- hallucination mitigation
- prompt engineering
- task planning
- long-term memory
- GPT-4
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Zhou, Q., Zhang, Z., Xiang, X., Wang, K., Wu, Y., & Li, Y. (2024). Enhancing the General Agent Capabilities of Low-Paramter LLMs through Tuning and Multi-Branch Reasoning. Findings of the Association for Computational Linguistics: NAACL, 2922–2931. https://doi.org/10.18653/v1/2024.findings-naacl.184
How many times has this paper been cited?
14 times, according to OpenAlex on 16 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access: read the free full text at Findings of the Association for Computational Linguistics: NAACL.
Who wrote this paper?
Qinhao Zhou, Zihan Zhang, Xiang Xiang, Ke Wang, Yuchuan Wu, Yongbin Li.
What is the DOI of this paper?
10.18653/v1/2024.findings-naacl.184. The permanent link is https://doi.org/10.18653/v1/2024.findings-naacl.184.
Bibliographic data from OpenAlex (CC0), last checked 16 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.