{"type":"ScholarlyArticle","title":"MIRROR: Multi-agent Intra- and Inter-Reflection for Optimized Reasoning in Tool Learning","authors":[{"name":"Zikang Guo","slug":"zikang-guo","given":"Zikang","family":"Guo","affiliation":""},{"name":"Benfeng Xu","slug":"benfeng-xu","given":"Benfeng","family":"Xu","affiliation":""},{"name":"Xiaorui Wang","slug":"xiaorui-wang","given":"Xiaorui","family":"Wang","affiliation":""},{"name":"Zhendong Mao","slug":"zhendong-mao","given":"Zhendong","family":"Mao","affiliation":""}],"abstract":"Complex tasks involving tool integration pose significant challenges for Large Language Models (LLMs), leading to the emergence of multi-agent workflows as a promising solution. Reflection has emerged as an effective strategy for correcting erroneous trajectories in agentic workflows. However, existing approaches only exploit such capability in the post-action stage, where the agent observes the execution outcomes. We argue that, like humans, LLMs can also engage in reflection before action execution: the agent can anticipate undesirable outcomes from its own decisions, which not only provides a necessarily complementary perspective to evaluate the decision but also prevents the propagation of errors throughout the trajectory. In this paper, we propose MIRROR, a framework that consists of both intra-reflection, which critically assesses intended actions before execution, and inter-reflection, which further adjusts the trajectory based on observations. This design systematically leverages LLM reflection capabilities to eliminate and rectify erroneous actions on a more comprehensive scope. Evaluations on both the StableToolBench and TravelPlanner benchmarks demonstrate MIRROR's superior performance, achieving state-of-the-art results compared to existing approaches.","doi":"10.24963/ijcai.2025/14","url":"https://ijcai.org/proceedings/2025/14","pdf":"https://ijcai.org/proceedings/2025/0014.pdf","markdown":"https://ijcai.org/proceedings/2025/14.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/14","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":"Agent-based and Multi-agent Systems","track":"Main Track","number":14,"pages":{"first":117,"last":125},"keywords":["Agent-based and Multi-agent Systems: MAS: Multi-agent planning","Agent-based and Multi-agent Systems: MAS: Applications","Agent-based and Multi-agent Systems: MAS: Coordination and cooperation"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}