mlsanityData to 14 Oct 2026

Multi-LLM Collaborative Search for Complex Problem Solving

arXiv 2502.18873 ↗First posted 26 Feb 2025cs.AI cs.CLcited by 10

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

Abstract (arXiv)

Large language models (LLMs) often struggle with complex reasoning tasks due to their limitations in addressing the vast reasoning space and inherent ambiguities of natural language. We propose the Mixture-of-Search-Agents (MoSA) paradigm, a novel approach leveraging the collective expertise of multiple LLMs to enhance search-based reasoning. MoSA integrates diverse reasoning pathways by combining independent exploration with iterative refinement among LLMs, mitigating the limitations of single-model approaches. Using Monte Carlo Tree Search (MCTS) as a backbone, MoSA enables multiple agents to propose and aggregate reasoning steps, resulting in improved accuracy. Our comprehensive evaluation across four reasoning benchmarks demonstrates MoSA's consistent performance improvements over single-agent and other multi-agent baselines, particularly in complex mathematical and commonsense reasoning tasks.

Key facts. Cited by 10 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 35 of its 47 references that are in the map. First posted on arXiv 26 Feb 2025.

Builds on

35 of 47 references.

Closest ancestors · 6

Same direction, newest first

  1. 2024Mixture-of-Agents Enhances Large Language Model Capabilities7 Jun
  2. 2023Towards Reasoning in Large Language Models via Multi-Agent Peer Review Collaboration14 Nov
  3. 2023Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models6 Oct
  4. 2023ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs22 Sep
  5. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate30 May
  6. 2023Reasoning with Language Model is Planning with World Model24 May

Other references · 29

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  3. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  4. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  5. 2023Let's Verify Step by Stepcited by 3,789
  6. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  7. 2019The Curious Case of Neural Text Degenerationcited by 2,916
  8. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
  9. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,407
  10. 2024ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Toolscited by 1,121
  11. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,076
  12. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 886
17 more
  1. 2021Are NLP Models really able to Solve Simple Math Word Problems?cited by 878
  2. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 743
  3. 2023LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusioncited by 564
  4. 2024ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Searchcited by 344
  5. 2022The Vendi Score: A Diversity Evaluation Metric for Machine Learningcited by 311
  6. 2023A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaborationcited by 290
  7. 2023Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology Viewcited by 222
  8. 2023Large Language Model Routing with Benchmark Datasetscited by 172
  9. 2024AlphaMath Almost Zero: Process Supervision without Processcited by 162
  10. 2024Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8Bcited by 158
  11. 2023Routing to the Expert: Efficient Reward-guided Ensemble of Large Language Modelscited by 145
  12. 2024Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solverscited by 138
  13. 2020Trading Off Diversity and Quality in Natural Language Generationcited by 96
  14. 2023Everything of Thoughts: Defying the Law of Penrose Triangle for Thought Generationcited by 74
  15. 2024Ensemble Learning for Heterogeneous Large Language Models with Deep Parallel Collaborationcited by 67
  16. 2023Fusing Models with Complementary Expertisecited by 46
  17. 2024Understanding When Tree of Thoughts Succeeds: Larger Models Excel in Generation, Not Discriminationcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 5.

10 papers.

  1. 2025Collaborative Memory: Multi-User Memory Sharing in LLM Agents with Dynamic Access Controlcited by 61
  2. 2025Fine-Grained Preference Optimization Improves Spatial Reasoning in VLMscited by 32
  3. 2025How to Train a Leader: Hierarchical Reasoning in Multi-Agent LLMscited by 12
  4. 2026Attention-MoA: Enhancing Mixture-of-Agents via Inter-Agent Semantic Attention and Deep Residual Synthesiscited by 3
  5. 2026Reasoning Consensus: Structural Ensembling of LLM Reasoning via Weighted DAG Aggregationcited by 2
  6. 2025Ctrl-Z Sampling: Scaling Diffusion Sampling with Controlled Random Zigzag Explorationscited by 1
  7. 2025MCCE: A Framework for Multi-LLM Collaborative Search in Discrete Spaces with Similarity-Filtered Preference Learningcited by 1
  8. 2026SpatiO: Adaptive Test-Time Orchestration of Vision-Language Agents for Spatial Reasoningcited by 0
  9. 2026When LLM Meets Tree Search: A Systematic View of Inference as Search in Large Language Modelscited by 0
  10. 2026Towards Better Exploration in Sequential Test-Time Scalingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Fleet of Agents: Coordinated Problem Solving with Large Language Models
  2. 2025Reinforcement Fine-Tuning for Reasoning towards Multi-Step Multi-Source Search in Large Language Models
  3. 2025Unleashing Diverse Thinking Modes in LLMs through Multi-Agent Collaboration
  4. 2025An Empirical Study on Reinforcement Learning for Reasoning-Search Interleaved LLM Agents
  5. 2025Adaptive Reasoning Executor: A Collaborative Agent System for Efficient Reasoning
  6. 2025MARS: toward more efficient multi-agent collaboration for LLM reasoning
  7. 2023Corex: Pushing the Boundaries of Complex Reasoning through Multi-Model Collaboration
  8. 2024Navigating Complexity: Orchestrated Problem Solving with Multi-Agent LLMs