mlsanityData to 7 Oct 2026

Evolving Deeper LLM Thinking

arXiv 2501.09891 ↗First posted 17 Jan 2025cs.AIcited by 58

On the map: LLM reasoning → Test-time compute and efficient thinking

Abstract (arXiv)

We explore an evolutionary search strategy for scaling inference time compute in Large Language Models. The proposed approach, Mind Evolution, uses a language model to generate, recombine and refine candidate responses. The proposed approach avoids the need to formalize the underlying inference problem whenever a solution evaluator is available. Controlling for inference cost, we find that Mind Evolution significantly outperforms other inference strategies such as Best-of-N and Sequential Revision in natural language planning tasks. In the TravelPlanner and Natural Plan benchmarks, Mind Evolution solves more than 98% of the problem instances using Gemini 1.5 Pro without the use of a formal solver.

Key facts. Cited by 58 papers in the map (data through 7 Oct 2026). Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning. Builds on 19 of its 47 references that are in the map. First posted on arXiv 17 Jan 2025.

Builds on

19 of 47 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024Improving LLM Reasoning through Scaling Inference Computation with Collaborative Verification5 Oct
  2. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters6 Aug
  3. 2024Large Language Model-Based Evolutionary Optimizer: Reasoning with elitism4 Mar

Other references · 16

  1. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  2. 2023Let's Verify Step by Stepcited by 3,598
  3. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
  4. 2024Large Language Monkeys: Scaling Inference Compute with Repeated Samplingcited by 946
  5. 2023Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolutioncited by 521
  6. 2024TravelPlanner: A Benchmark for Real-World Planning with Language Agentscited by 385
  7. 2023Language Models can Solve Computer Taskscited by 371
  8. 2024Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoningcited by 267
  9. 2024ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolutioncited by 266
  10. 2023EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizerscited by 189
  11. 2024NATURAL PLAN: Benchmarking LLMs on Natural Language Planningcited by 125
  12. 2024EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithmscited by 109
4 more
  1. 2024Prover-Verifier Games improve legibility of LLM outputscited by 79
  2. 2024Multi-step Problem Solving Through a Verifier: An Empirical Analysis on Model-induced Process Supervisioncited by 51
  3. 2024Large Language Models Can Solve Real-World Planning Rigorously with Formal Verification Toolscited by 47
  4. 2023Large Language Model for Multi-objective Evolutionary Optimizationcited by 29

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 38; 2026: 20.

58 papers.

Sort:

By area:

  1. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 381
  2. 2025CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learningcited by 59
  3. 2025SETS: Leveraging Self-Verification and Self-Correction for Improved Test-Time Scalingcited by 54
  4. 2025EvoFlow: Evolving Diverse Agentic Workflows On The Flycited by 49
  5. 2025Wider or Deeper? Scaling LLM Inference-Time Compute with Adaptive Branching Tree Searchcited by 48
  6. 2025Crosslingual Reasoning through Test-Time Scalingcited by 46
  7. 2026AdaEvolve: Adaptive LLM Driven Zeroth-Order Optimizationcited by 46
  8. 2026EvoX: Meta-Evolution for Automated Discoverycited by 45
  9. 2025PonderLM: Pretraining Language Models to Ponder in Continuous Spacecited by 44
  10. 2026Meta Context Engineering via Agentic Skill Evolutioncited by 42
  11. 2025When To Solve, When To Verify: Compute-Optimal Problem Solving and Generative Verification for LLM Reasoningcited by 41
  12. 2025Recursive Self-Aggregation Unlocks Deep Thinking in Large Language Modelscited by 30
38 more
  1. 2025Two Heads are Better Than One: Test-time Scaling of Multi-agent Collaborative Reasoningcited by 29
  2. 2025To Backtrack or Not to Backtrack: When Sequential Search Limits Model Reasoningcited by 24
  3. 2025Reasoning Beyond Limits: Advances and Open Problems for LLMscited by 16
  4. 2025An Empirical Study of LLM Reasoning Ability Under Strict Output Length Constraintcited by 16
  5. 2025PlanGEN: A Multi-Agent Framework for Generating Planning and Reasoning Trajectories for Complex Problem Solvingcited by 15
  6. 2025SAMULE: Self-Learning Agents Enhanced by Multi-level Reflectioncited by 15
  7. 2025HyperTree Planning: Enhancing LLM Reasoning via Hierarchical Thinkingcited by 14
  8. 2025Parallel Test-Time Scaling for Latent Reasoning Modelscited by 12
  9. 2025Cognitive Alpha Mining via LLM-Driven Code-Based Evolutioncited by 12
  10. 2025Temporal Consistency for LLM Reasoning Process Error Identificationcited by 10
  11. 2025DISC: Dynamic Decomposition Improves LLM Inference Scalingcited by 9
  12. 2025Faster and Better LLMs via Latency-Aware Test-Time Scalingcited by 9
  13. 2025First Finish Search: Efficient Test-Time Scaling in Large Language Modelscited by 8
  14. 2025LatentEvolve: Self-Evolving Test-Time Scaling in Latent Spacecited by 8
  15. 2026UniT: Unified Multimodal Chain-of-Thought Test-time Scalingcited by 8
  16. 2025Position: Scaling LLM Agents Requires Asymptotic Analysis with LLM Primitivescited by 7
  17. 2026Prism: Efficient Test-Time Scaling via Hierarchical Search and Self-Verification for Discrete Diffusion Language Modelscited by 7
  18. 2026Procedural Knowledge at Scale Improves Reasoningcited by 7
  19. 2025EvoMem: Improving Multi-Agent Planning with Dual-Evolving Memorycited by 6
  20. 2025On the Limits of Test-Time Compute: Sequential Reward Filtering for Better Inferencecited by 6
  21. 2026SeLaR: Selective Latent Reasoning in Large Language Modelscited by 6
  22. 2025Teaching LLMs According to Their Aptitude: Adaptive Reasoning for Mathematical Problem Solvingcited by 4
  23. 2025Position: Ensuring mutual privacy is necessary for effective external evaluation of proprietary AI systemscited by 4
  24. 2025LLM-Guided Search for Deletion-Correcting Codescited by 4
  25. 2025A Short Survey on Small Reasoning Models: Training, Inference, Applications and Research Directionscited by 4
  26. 2026Reasoning over Precedents Alongside Statutes: Case-Augmented Deliberative Alignment for LLM Safetycited by 3
  27. 2026TIDE: Tuning-Integrated Dynamic Evolution for LLM-Based Automated Heuristic Designcited by 3
  28. 2025Rethinking the Unsolvable: When In-Context Search Meets Test-Time Scalingcited by 2
  29. 2026FlowPIE: Test-Time Scientific Idea Evolution with Flow-Guided Literature Explorationcited by 2
  30. 2026Distributional Energy-Based Models for Uncertainty-Aware Structured LLM Reasoningcited by 2
  31. 2025Sample-Efficient Optimization over Generative Priors via Coarse Learnabilitycited by 1
  32. 2025Follow the Path: Reasoning over Knowledge Graph Paths to Improve Large Language Model Factualitycited by 1
  33. 2025Evolutionary System 2 Reasoning: An Empirical Proofcited by 1
  34. 2025FutureWeaver: Planning Test-Time Compute for Multi-Agent Systems with Modularized Collaborationcited by 1
  35. 2026Programming over Thinking: Efficient and Robust Multi-Constraint Planningcited by 1
  36. 2026See it to Place it: Evolving Macro Placements with Vision-Language Modelscited by 1
  37. 2025Dual-Process Scaffold Reasoning for Enhancing LLM Code Debuggingcited by 0
  38. 2025MultiGA: Leveraging Multi-Source Seeding in Genetic Algorithmscited by 0

50 most cited of 58 All 58 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Evolutionary thoughts: integration of large language models and evolutionary algorithms
  2. 2026Policy of Thoughts: Scaling Test-Time Training for LLM Reasoning via Online Policy Evolution
  3. 2025Population-Evolve: a Parallel Sampling and Evolutionary Method for LLM Math Reasoning
  4. 2023Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Models
  5. 2026Position: Agentic Evolution is the Path to Evolving LLMs
  6. 2026What Makes an LLM a Good Optimizer? A Trajectory Analysis of LLM-Guided Evolutionary Search
  7. 2025MetaScale: Test-Time Scaling with Evolving Meta-Thoughts
  8. 2025Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs