{"type":"ScholarlyArticle","title":"A Survey on the Feedback Mechanism of LLM-based AI Agents","authors":[{"name":"Zhipeng Liu","slug":"zhipeng-liu","given":"Zhipeng","family":"Liu","affiliation":""},{"name":"Xuefeng Bai","slug":"xuefeng-bai","given":"Xuefeng","family":"Bai","affiliation":""},{"name":"Kehai Chen","slug":"kehai-chen","given":"Kehai","family":"Chen","affiliation":""},{"name":"Xinyang Chen","slug":"xinyang-chen","given":"Xinyang","family":"Chen","affiliation":""},{"name":"Xiucheng Li","slug":"xiucheng-li","given":"Xiucheng","family":"Li","affiliation":""},{"name":"Yang Xiang","slug":"yang-xiang","given":"Yang","family":"Xiang","affiliation":""},{"name":"Jin Liu","slug":"jin-liu","given":"Jin","family":"Liu","affiliation":""},{"name":"Hong-Dong Li","slug":"hong-dong-li","given":"Hong-Dong","family":"Li","affiliation":""},{"name":"Yaowei Wang","slug":"yaowei-wang","given":"Yaowei","family":"Wang","affiliation":""},{"name":"Liqiang Nie","slug":"liqiang-nie","given":"Liqiang","family":"Nie","affiliation":""},{"name":"Min Zhang","slug":"min-zhang","given":"Min","family":"Zhang","affiliation":""}],"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.","doi":"10.24963/ijcai.2025/1175","url":"https://ijcai.org/proceedings/2025/1175","pdf":"https://ijcai.org/proceedings/2025/1175.pdf","markdown":"https://ijcai.org/proceedings/2025/1175.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/1175","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Survey Track","track":"Survey Track","number":1175,"pages":{"first":10582,"last":10592},"keywords":["Natural Language Processing: NLP: Language models","Agent-based and Multi-agent Systems: MAS: Agent theories and models"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}