# Enhancing LLM Reasoning with Multi-Path Collaborative Reactive and Reflection agents

arXiv: https://arxiv.org/abs/2501.00430 · HTML: https://mlsanity.com/paper/2501.00430/

## Key facts

- Cited by 15 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 24 of its 38 references that are in the map.
- First posted on arXiv 31 Dec 2024.

## 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 / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 24 of 24)

- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [Reasoning with Language Model is Planning with World Model](https://mlsanity.com/paper/2305.14992/) (2023)
- [Large Language Model based Multi-Agents: A Survey of Progress and Challenges](https://mlsanity.com/paper/2402.01680/) (2024)
- [Self-critiquing models for assisting human evaluators](https://mlsanity.com/paper/2206.05802/) (2022)
- [Risks from Learned Optimization in Advanced Machine Learning Systems](https://mlsanity.com/paper/1906.01820/) (2019)
- [RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models](https://mlsanity.com/paper/2310.00746/) (2023)
- [ExpertPrompting: Instructing Large Language Models to be Distinguished Experts](https://mlsanity.com/paper/2305.14688/) (2023)
- [Solving Math Word Problems by Combining Language Models With Symbolic Solvers](https://mlsanity.com/paper/2304.09102/) (2023)
- [Text Modular Networks: Learning to Decompose Tasks in the Language of Existing Models](https://mlsanity.com/paper/2009.00751/) (2020)
- [Large Language Model-based Human-Agent Collaboration for Complex Task Solving](https://mlsanity.com/paper/2402.12914/) (2024)
- [Agents Thinking Fast and Slow: A Talker-Reasoner Architecture](https://mlsanity.com/paper/2410.08328/) (2024)
- [LLM Harmony: Multi-Agent Communication for Problem Solving](https://mlsanity.com/paper/2401.01312/) (2024)
- [Aligning Large Language Models with Human: A Survey](https://mlsanity.com/paper/2307.12966/) (2023)
- [CoMM: Collaborative Multi-Agent, Multi-Reasoning-Path Prompting for Complex Problem Solving](https://mlsanity.com/paper/2404.17729/) (2024)
- [LLMs can Find Mathematical Reasoning Mistakes by Pedagogical Chain-of-Thought](https://mlsanity.com/paper/2405.06705/) (2024)
- [Iterative Translation Refinement with Large Language Models](https://mlsanity.com/paper/2306.03856/) (2023)
- [SELF: Self-Evolution with Language Feedback](https://mlsanity.com/paper/2310.00533/) (2023)
- [Let's Do a Thought Experiment: Using Counterfactuals to Improve Moral Reasoning](https://mlsanity.com/paper/2306.14308/) (2023)
- [Skin-in-the-Game: Decision Making via Multi-Stakeholder Alignment in LLMs](https://mlsanity.com/paper/2405.12933/) (2024)
- [A Human-Computer Collaborative Tool for Training a Single Large Language Model Agent into a Network through Few Examples](https://mlsanity.com/paper/2404.15974/) (2024)

## Built on by (most cited first, 15 of 15)

- [RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning](https://mlsanity.com/paper/2504.20073/) (2025)
- [Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models](https://mlsanity.com/paper/2503.09567/) (2025)
- [A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?](https://mlsanity.com/paper/2503.24235/) (2025)
- [Talk Isn't Always Cheap: Understanding Failure Modes in Multi-Agent Debate](https://mlsanity.com/paper/2509.05396/) (2025)
- [A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents](https://mlsanity.com/paper/2601.12538/) (2026)
- [Talk Structurally, Act Hierarchically: A Collaborative Framework for LLM Multi-Agent Systems](https://mlsanity.com/paper/2502.11098/) (2025)
- [Enhancing Long Chain-of-Thought Reasoning through Multi-Path Plan Aggregation](https://mlsanity.com/paper/2510.11620/) (2025)
- [A Survey on Parallel Reasoning](https://mlsanity.com/paper/2510.12164/) (2025)
- [Meta-Policy Reflexion: Reusable Reflective Memory and Rule Admissibility for Resource-Efficient LLM Agent](https://mlsanity.com/paper/2509.03990/) (2025)
- [MUPA: Towards Multi-Path Agentic Reasoning for Grounded Video Question Answering](https://mlsanity.com/paper/2506.18071/) (2025)
- [Test-time Scaling of LLMs: A Survey from A Subproblem Structure Perspective](https://mlsanity.com/paper/2511.14772/) (2025)
- [DeCoDe: Defer-and-Complement Decision-Making via Decoupled Concept Bottleneck Models](https://mlsanity.com/paper/2505.19220/) (2025)
- [Distilling Long-CoT Reasoning through Collaborative Step-wise Multi-Teacher Decoding](https://mlsanity.com/paper/2605.02290/) (2026)
- [Bridging Inference-Time Scaling and Episodic Memory with Action-Centric Graphs](https://mlsanity.com/paper/2607.27415/) (2026)
- [Multi-Agent Forensic Reasoning for Generalizable Deepfake Video Detection](https://mlsanity.com/paper/2608.06865/) (2026)

## Abstract (arXiv)

Agents have demonstrated their potential in scientific reasoning tasks through large language models. However, they often face challenges such as insufficient accuracy and degeneration of thought when handling complex reasoning tasks, which impede their performance. To overcome these issues, we propose the Reactive and Reflection agents with Multi-Path Reasoning (RR-MP) Framework, aimed at enhancing the reasoning capabilities of LLMs. Our approach improves scientific reasoning accuracy by employing a multi-path reasoning mechanism where each path consists of a reactive agent and a reflection agent that collaborate to prevent degeneration of thought inherent in single-agent reliance. Additionally, the RR-MP framework does not require additional training; it utilizes multiple dialogue instances for each reasoning path and a separate summarizer to consolidate insights from all paths. This design integrates diverse perspectives and strengthens reasoning across each path. We conducted zero-shot and few-shot evaluations on tasks involving moral scenarios, college-level physics, and mathematics. Experimental results demonstrate that our method outperforms baseline approaches, highlighting the effectiveness and advantages of the RR-MP framework in managing complex scientific reasoning tasks.