---
title: "MIRROR: Multi-agent Intra- and Inter-Reflection for Optimized Reasoning in Tool Learning"
authors:
  - "Zikang Guo"
  - "Benfeng Xu"
  - "Xiaorui Wang"
  - "Zhendong Mao"
doi: "10.24963/ijcai.2025/14"
url: "https://ijcai.org/proceedings/2025/14"
pdf: "https://ijcai.org/proceedings/2025/0014.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "117-125"
track: "Main Track"
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"
---

# MIRROR: Multi-agent Intra- and Inter-Reflection for Optimized Reasoning in Tool Learning

Zikang Guo, Benfeng Xu, Xiaorui Wang, Zhendong Mao

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 117-125. DOI: [10.24963/ijcai.2025/14](https://doi.org/10.24963/ijcai.2025/14)

## 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.