mlsanityData to 14 Oct 2026

MAR:Multi-Agent Reflexion Improves Reasoning Abilities in LLMs

arXiv 2512.20845 ↗First posted 23 Dec 2025cs.AI cs.MAcited by 4

On the map: LLM reasoning → Reasoning for agents, planning and code

also in 1 more
Abstract (arXiv)

LLMs have shown the capacity to improve their performance on reasoning tasks through reflecting on their mistakes, and acting with these reflections in mind. However, continual reflections of the same LLM onto itself exhibit degeneration of thought, where the LLM continues to repeat the same errors again and again even with the knowledge that its wrong. To address this problem, we instead introduce multi-agent with multi-persona debators as the method to generate reflections. Through out extensive experimentation, we've found that the leads to better diversity of in the reflections generated by the llm agent. We demonstrate an accuracy of 47% EM HotPot QA (question answering) and 82.7% on HumanEval (programming), both performances surpassing reflection with a single llm.

Key facts. Cited by 4 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 12 of its 19 references that are in the map. First posted on arXiv 23 Dec 2025.

Builds on

12 of 19 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025Self-signals Driven Multi-LLM Debate for Efficient and Accurate Reasoning8 Oct
  2. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate30 May

Other references · 10

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  3. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  4. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  5. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  6. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  7. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
  8. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,395
  9. 2023Language Models can Solve Computer Taskscited by 372
  10. 2025Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversitycited by 105

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanismscited by 21
  2. 2026ParamMem: Augmenting Language Agents with Parametric Reflective Memorycited by 5
  3. 2026Courtroom-Style Multi-Agent Debate with Progressive RAG and Role-Switching for Controversial Claim Verificationcited by 4
  4. 2026TEC: A Collection of Human Trial-and-error Trajectories for Problem Solvingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Rethinking the Bounds of LLM Reasoning: Are Multi-Agent Discussions the Key?
  2. 2024Enhancing LLM Reasoning with Multi-Path Collaborative Reactive and Reflection agents
  3. 2024Self-Reflection in LLM Agents: Effects on Problem-Solving Performance
  4. 2025Can LLM Agents Really Debate? A Controlled Study of Multi-Agent Debate in Logical Reasoning
  5. 2023Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMs
  6. 2026Multi-Agent Debate with Memory Masking
  7. 2025Reinforce LLM Reasoning through Multi-Agent Reflection
  8. 2025A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems