# ReAgent: Reversible Multi-Agent Reasoning for Knowledge-Enhanced Multi-Hop QA

arXiv: https://arxiv.org/abs/2503.06951 · HTML: https://mlsanity.com/paper/2503.06951/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 17 of its 48 references that are in the map.
- First posted on arXiv 10 Mar 2025.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)
- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 17 of 17)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [Large Language Models Are Human-Level Prompt Engineers](https://mlsanity.com/paper/2211.01910/) (2022)
- [Gemini: A Family of Highly Capable Multimodal Models](https://mlsanity.com/paper/2312.11805/) (2023)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [Multimodal Chain-of-Thought Reasoning in Language Models](https://mlsanity.com/paper/2302.00923/) (2023)
- [HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models](https://mlsanity.com/paper/2405.14831/) (2024)
- [Debating with More Persuasive LLMs Leads to More Truthful Answers](https://mlsanity.com/paper/2402.06782/) (2024)
- [Chain of Agents: Large Language Models Collaborating on Long-Context Tasks](https://mlsanity.com/paper/2406.02818/) (2024)
- [KAG: Boosting LLMs in Professional Domains via Knowledge Augmented Generation](https://mlsanity.com/paper/2409.13731/) (2024)
- [Mirror-Consistency: Harnessing Inconsistency in Majority Voting](https://mlsanity.com/paper/2410.10857/) (2024)
- [Graphusion: A RAG Framework for Knowledge Graph Construction with a Global Perspective](https://mlsanity.com/paper/2410.17600/) (2024)
- [Multi-hop Reading Comprehension via Deep Reinforcement Learning based Document Traversal](https://mlsanity.com/paper/1905.09438/) (2019)
- [End-to-End Graph Flattening Method for Large Language Models](https://mlsanity.com/paper/2409.14880/) (2024)

## Built on by (most cited first, 13 of 13)

- [Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL](https://mlsanity.com/paper/2508.07976/) (2025)
- [End-to-End Optimization of LLM-Driven Multi-Agent Search Systems via Heterogeneous-Group-Based Reinforcement Learning](https://mlsanity.com/paper/2506.02718/) (2025)
- [CARL: Criticality-Aware Agentic Reinforcement Learning](https://mlsanity.com/paper/2512.04949/) (2025)
- [HiMPO: Hindsight-Informed Memory Policy Optimization for Less-Entangled Credit in Long-Horizon Agents](https://mlsanity.com/paper/2606.16285/) (2026)
- [Track, Rank, Crack: Epistemic Working Memory Scales Multi-Hop Reasoning in Language Agents](https://mlsanity.com/paper/2607.12267/) (2026)
- [Graph of Agents: Principled Long Context Modeling by Emergent Multi-Agent Collaboration](https://mlsanity.com/paper/2509.21848/) (2025)
- [The Horizon Gap: Planning, Memory, Execution, Training, and Evaluation for Long-Horizon LLM Agents](https://mlsanity.com/paper/2608.06663/) (2026)
- [DeALOG: Decentralized Multi-Agents Log-Mediated Reasoning Framework](https://mlsanity.com/paper/2602.00996/) (2026)
- [Diagnosis-Driven Automatic Repair for Agentic Workflow via Symbolic Inference](https://mlsanity.com/paper/2607.02882/) (2026)
- [THOR: A Theta-Gamma Hierarchical Oscillatory Reasoning Framework for Multi-hop QA](https://mlsanity.com/paper/2607.20459/) (2026)
- [DeAR: Decentralized Agentic Reasoning via Capability Grounding and Collaborative Thought Navigation](https://mlsanity.com/paper/2608.17282/) (2026)
- [GraMRAG: Orchestrating Multi-Agent Multi-Step Reasoning via Graph Memory with Reinforcement Learning](https://mlsanity.com/paper/2609.14066/) (2026)
- [SOAR: Source-Aware Reinforcement Learning with Precise Credit Assignment for Search Agents](https://mlsanity.com/paper/2610.13157/) (2026)

## Abstract (arXiv)

Recent advances in large language models (LLMs) have significantly improved multi-hop question answering (QA) through direct Chain-of-Thought (CoT) reasoning. However, the irreversible nature of CoT leads to error accumulation, making it challenging to correct mistakes in multi-hop reasoning. This paper introduces ReAgent: a Reversible multi-Agent collaborative framework augmented with explicit backtracking mechanisms, enabling reversible multi-hop reasoning. By incorporating text-based retrieval, information aggregation and validation, our system can detect and correct errors mid-reasoning, leading to more robust and interpretable QA outcomes. The framework and experiments serve as a foundation for future work on error-tolerant QA systems. Empirical evaluations across three benchmarks indicate ReAgent's efficacy, yielding average about 6% improvements against baseline models.