Conference paper · 2024 · Open access

AgentBank: Towards Generalized LLM Agents via Fine-Tuning on 50000+ Interaction Trajectories

Yifan Song, Weimin Xiong, Xiutian Zhao, Dawei Zhu, Wenhao Wu, Ke Wang, Cheng Li, Wei Peng, Sujian Li

Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP), 2124–2141 · Published 1 January 2024 · DOI 10.18653/v1/2024.findings-emnlp.116

Free PDFView at the publisherCite this paper

In brief

“AgentBank: Towards Generalized LLM Agents via Fine-Tuning on 50000+ Interaction Trajectories” is a 2024 conference paper by Yifan Song and 8 co-authors, published in Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP). OpenAlex counts 40 citations as of 16 November 2026, which puts it in the top 7% 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: EMNLP (Findings of EMNLP).

Citations
40
Most cited in
2026 (20)
Field-weighted impact
6.08
References
43
Authors
9

Abstract

Fine-tuning on agent-environment interaction trajectory data holds significant promise for surfacing generalized agent capabilities in opensource large language models (LLMs).In this work, we introduce AGENTBANK, by far the largest trajectory tuning data collection featuring more than 50k diverse high-quality interaction trajectories which comprises 16 tasks covering five distinct agent skill dimensions.Leveraging a novel annotation pipeline, we are able to scale the annotated trajectories and generate a trajectory dataset with minimized difficulty bias.Furthermore, we fine-tune LLMs on AGENTBANK to get a series of agent models, SAMOYED.Our comparative experiments demonstrate the effectiveness of scaling the interaction trajectory data to acquire generalized agent capabilities.Additional studies also reveal some key observations regarding trajectory tuning and agent skill generalization.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Song, Y., Xiong, W., Zhao, X., Zhu, D., Wu, W., Wang, K., Li, C., Peng, W., & Li, S. (2024). AgentBank: Towards Generalized LLM Agents via Fine-Tuning on 50000+ Interaction Trajectories. Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP), 2124–2141. https://doi.org/10.18653/v1/2024.findings-emnlp.116

MLA 9

Song, Yifan, et al. “AgentBank: Towards Generalized LLM Agents via Fine-Tuning on 50000+ Interaction Trajectories.” Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP), 2024, pp. 2124–2141. https://doi.org/10.18653/v1/2024.findings-emnlp.116.

Chicago

Song, Yifan, Weimin Xiong, Xiutian Zhao, Dawei Zhu, Wenhao Wu, Ke Wang, Cheng Li, Wei Peng, and Sujian Li. 2024. “AgentBank: Towards Generalized LLM Agents via Fine-Tuning on 50000+ Interaction Trajectories.” Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP): 2124–2141. https://doi.org/10.18653/v1/2024.findings-emnlp.116.

Harvard

Song, Y. et al. (2024) ‘AgentBank: Towards Generalized LLM Agents via Fine-Tuning on 50000+ Interaction Trajectories’, Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP), pp. 2124–2141. doi:10.18653/v1/2024.findings-emnlp.116.

IEEE

Y. Song et al., “AgentBank: Towards Generalized LLM Agents via Fine-Tuning on 50000+ Interaction Trajectories,” Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP), pp. 2124–2141, 2024, doi: 10.18653/v1/2024.findings-emnlp.116.

BibTeX

@inproceedings{song2024agentbank,
  title     = {{AgentBank: Towards Generalized LLM Agents via Fine-Tuning on 50000+ Interaction Trajectories}},
  author    = {Song, Yifan and Xiong, Weimin and Zhao, Xiutian and Zhu, Dawei and Wu, Wenhao and Wang, Ke and Li, Cheng and Peng, Wei and Li, Sujian},
  booktitle = {Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)},
  year      = {2024},
  pages     = {2124--2141},
  doi       = {10.18653/v1/2024.findings-emnlp.116},
  url       = {https://doi.org/10.18653/v1/2024.findings-emnlp.116}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
202422
20251818
20262020

Its field-weighted citation impact is 6.08: it has been cited 6.08 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 › AI-based Problem Solving and Planning

  • LLM agents
  • Samoyeds
  • open-source large language models
  • agent-environment interaction

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Song, Y., Xiong, W., Zhao, X., Zhu, D., Wu, W., Wang, K., Li, C., Peng, W., & Li, S. (2024). AgentBank: Towards Generalized LLM Agents via Fine-Tuning on 50000+ Interaction Trajectories. Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP), 2124–2141. https://doi.org/10.18653/v1/2024.findings-emnlp.116

How many times has this paper been cited?

40 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: EMNLP (Findings of EMNLP).

Who wrote this paper?

Yifan Song, Weimin Xiong, Xiutian Zhao, Dawei Zhu, Wenhao Wu, Ke Wang, Cheng Li, Wei Peng, Sujian Li.

What is the DOI of this paper?

10.18653/v1/2024.findings-emnlp.116. The permanent link is https://doi.org/10.18653/v1/2024.findings-emnlp.116.

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.