mlsanityData to 14 Oct 2026

Reasoning Strategies in Large Language Models: Can They Follow, Prefer, and Optimize?

arXiv 2507.11423 ↗First posted 15 Jul 2025cs.CLcited by 1

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Human reasoning involves different strategies, each suited to specific problems. Prior work shows that large language model (LLMs) tend to favor a single reasoning strategy, potentially limiting their effectiveness in diverse reasoning challenges. In this work, we investigate whether prompting can control LLMs reasoning strategies and assess its impact on logical problem-solving. While our experiments show that no single strategy consistently improves accuracy, performance could be enhanced if models could adaptively choose the optimal strategy. We propose methods to guide LLMs in strategy selection, highlighting new ways to refine their reasoning abilities.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 14 of its 26 references that are in the map. First posted on arXiv 15 Jul 2025.

Builds on

14 of 26 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning3 Feb
  2. 2024Comparing Inferential Strategies of Humans and Large Language Models in Deductive Reasoning20 Feb

Other references · 12

  1. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  2. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  3. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  4. 2024Large Language Monkeys: Scaling Inference Compute with Repeated Samplingcited by 991
  5. 2017Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problemscited by 650
  6. 2024Generative Verifiers: Reward Modeling as Next-Token Predictioncited by 480
  7. 2024Chain-of-Thought Reasoning Without Promptingcited by 210
  8. 2023Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solvecited by 178
  9. 2024How Likely Do LLMs with CoT Mimic Human Reasoning?cited by 34
  10. 2024Do Language Models Exhibit the Same Cognitive Biases in Problem Solving as Human Learners?cited by 19
  11. 2025Bridging Internal Probability and Self-Consistency for Effective and Efficient LLM Reasoningcited by 18
  12. 2025Language Models Prefer What They Know: Relative Confidence Estimation via Confidence Preferencescited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Assessing mentalization in humans and large language modelscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025Reasoning Capabilities of Large Language Models on Dynamic Tasks
  2. 2022Towards Reasoning in Large Language Models: A Survey
  3. 2025Advancing Reasoning in Large Language Models: Promising Methods and Approaches
  4. 2023StrategyLLM: Large Language Models as Strategy Generators, Executors, Optimizers, and Evaluators for Problem Solving
  5. 2024Beyond Accuracy: Evaluating the Reasoning Behavior of Large Language Models -- A Survey
  6. 2025Probing Large Language Models in Reasoning and Translating Complex Linguistic Puzzles
  7. 2025Mapping the Minds of LLMs: A Graph-Based Analysis of Reasoning LLM
  8. 2026Opening the Black Box: A Survey on the Mechanisms of Multi-Step Reasoning in Large Language Models