A Survey on the Feedback Mechanism of LLM-based AI Agents

Liu, Zhipeng; Bai, Xuefeng; Chen, Kehai; Chen, Xinyang; Li, Xiucheng; Xiang, Yang; Liu, Jin; Li, Hong-Dong; Wang, Yaowei; Nie, Liqiang; Zhang, Min

doi:10.24963/ijcai.2025/1175

A Survey on the Feedback Mechanism of LLM-based AI Agents

Zhipeng Liu, Xuefeng Bai, Kehai Chen, Xinyang Chen, Xiucheng Li, Yang Xiang, Jin Liu, Hong-Dong Li, Yaowei Wang, Liqiang Nie, Min Zhang

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Survey Track. Pages 10582-10592.

https://doi.org/10.24963/ijcai.2025/1175

Keywords

Natural Language Processing: NLP: Language models
Agent-based and Multi-agent Systems: MAS: Agent theories and models

Abstract

Large language models (LLMs) are increasingly being adopted to develop general-purpose AI agents. However, it remains challenging for these LLM-based AI agents to efficiently learn from feedback and iteratively optimize their strategies. To address this challenge, tremendous efforts have been dedicated to designing diverse feedback mechanisms for LLM-based AI agents. To provide a comprehensive overview of this rapidly evolving field, this paper presents a systematic review of these studies, offering a holistic perspective on the feedback mechanisms in LLM-based AI agents. We begin by discussing the construction of LLM-based AI agents, introducing a generalized framework that encapsulates much of the existing work. Next, we delve into the exploration of feedback mechanisms, categorizing them into four distinct types: internal feedback, external feedback, multi-agent feedback, and human feedback. Additionally, we provide an overview of evaluation protocols and benchmarks specifically tailored for LLM-based AI agents. Finally, we highlight the significant challenges and identify potential directions for future studies. The relevant papers are summarized and will be consistently updated at https://github.com/kevinson7515/Agents-Feedback-Mechanisms.

Zhipeng Liu, Xuefeng Bai, Kehai Chen, Xinyang Chen, Xiucheng Li, Yang Xiang, Jin Liu, Hong-Dong Li, Yaowei Wang, Liqiang Nie, and Min Zhang. 2025. A Survey on the Feedback Mechanism of LLM-based AI Agents. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 10582–10592. https://doi.org/10.24963/ijcai.2025/1175

@inproceedings{ijcai2025p1175,
  title     = {A Survey on the Feedback Mechanism of LLM-based AI Agents},
  author    = {Liu, Zhipeng and Bai, Xuefeng and Chen, Kehai and Chen, Xinyang and Li, Xiucheng and Xiang, Yang and Liu, Jin and Li, Hong-Dong and Wang, Yaowei and Nie, Liqiang and Zhang, Min},
  booktitle = {Proceedings of the Thirty-Fourth International Joint Conference on
               Artificial Intelligence, {IJCAI-25}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {James Kwok},
  pages     = {10582--10592},
  year      = {2025},
  month     = {8},
  note      = {Survey Track},
  doi       = {10.24963/ijcai.2025/1175},
  url       = {https://doi.org/10.24963/ijcai.2025/1175},
}

TY  - CPAPER
TI  - A Survey on the Feedback Mechanism of LLM-based AI Agents
AU  - Liu, Zhipeng
AU  - Bai, Xuefeng
AU  - Chen, Kehai
AU  - Chen, Xinyang
AU  - Li, Xiucheng
AU  - Xiang, Yang
AU  - Liu, Jin
AU  - Li, Hong-Dong
AU  - Wang, Yaowei
AU  - Nie, Liqiang
AU  - Zhang, Min
T2  - Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2025
SP  - 10582
EP  - 10592
DO  - 10.24963/ijcai.2025/1175
UR  - https://doi.org/10.24963/ijcai.2025/1175
ER  -