---
title: "A Survey on the Feedback Mechanism of LLM-based AI Agents"
authors:
  - "Zhipeng Liu"
  - "Xuefeng Bai"
  - "Kehai Chen"
  - "Xinyang Chen"
  - "Xiucheng Li"
  - "Yang Xiang"
  - "Jin Liu"
  - "Hong-Dong Li"
  - "Yaowei Wang"
  - "Liqiang Nie"
  - "Min Zhang"
doi: "10.24963/ijcai.2025/1175"
url: "https://ijcai.org/proceedings/2025/1175"
pdf: "https://ijcai.org/proceedings/2025/1175.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "10582-10592"
track: "Survey Track"
keywords:
  - "Natural Language Processing: NLP: Language models"
  - "Agent-based and Multi-agent Systems: MAS: Agent theories and models"
---

# 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

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 10582-10592. DOI: [10.24963/ijcai.2025/1175](https://doi.org/10.24963/ijcai.2025/1175)

## 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.