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

arXiv: https://arxiv.org/abs/2505.20670 · HTML: https://mlsanity.com/paper/2505.20670/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 19 of its 34 references that are in the map.
- First posted on arXiv 27 May 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [Tool learning and function calling](https://mlsanity.com/agents/tool-learning-and-function-calling/)

## Builds on (most cited first, 19 of 19)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks](https://mlsanity.com/paper/2211.12588/) (2022)
- [Gemini: A Family of Highly Capable Multimodal Models](https://mlsanity.com/paper/2312.11805/) (2023)
- [CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing](https://mlsanity.com/paper/2305.11738/) (2023)
- [KILT: a Benchmark for Knowledge Intensive Language Tasks](https://mlsanity.com/paper/2009.02252/) (2020)
- [Understanding the planning of LLM agents: A survey](https://mlsanity.com/paper/2402.02716/) (2024)
- [TravelPlanner: A Benchmark for Real-World Planning with Language Agents](https://mlsanity.com/paper/2402.01622/) (2024)
- [Internet-Augmented Dialogue Generation](https://mlsanity.com/paper/2107.07566/) (2021)
- [Foundation Models for Decision Making: Problems, Methods, and Opportunities](https://mlsanity.com/paper/2303.04129/) (2023)
- [Mindstorms in Natural Language-Based Societies of Mind](https://mlsanity.com/paper/2305.17066/) (2023)
- [ToolGen: Unified Tool Retrieval and Calling via Generation](https://mlsanity.com/paper/2410.03439/) (2024)
- [A Survey of Reasoning with Foundation Models](https://mlsanity.com/paper/2312.11562/) (2023)
- [Smurfs: Multi-Agent System using Context-Efficient DFSDT for Tool Planning](https://mlsanity.com/paper/2405.05955/) (2024)

## Built on by (most cited first, 7 of 7)

- [AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User Constraints](https://mlsanity.com/paper/2606.05622/) (2026)
- [PreFlect: From Retrospective to Prospective Reflection in Large Language Model Agents](https://mlsanity.com/paper/2602.07187/) (2026)
- [Red-MIRROR: Agentic LLM-based Autonomous Penetration Testing with Reflective Verification and Knowledge-augmented Interaction](https://mlsanity.com/paper/2603.27127/) (2026)
- [Decoupled Travel Planning with Behavior Forest](https://mlsanity.com/paper/2604.21354/) (2026)
- [State-Centric Decision Process](https://mlsanity.com/paper/2605.12755/) (2026)
- [IMAGINE: Integrating Multi-Agent System into One Model for Complex Reasoning and Planning](https://mlsanity.com/paper/2510.14406/) (2025)
- [HyEvo: Self-Evolving Hybrid Agentic Workflows for Efficient Reasoning](https://mlsanity.com/paper/2603.19639/) (2026)

## Abstract (arXiv)

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.