mlsanityData to 7 Oct 2026

Self-Consistency from Only Two Samples: CoT-PoT Ensembling for Efficient LLM Reasoning

arXiv 2604.17433 ↗First posted 19 Apr 2026cs.CL cs.AI cs.LGcited by 0

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

Abstract (arXiv)

Self-consistency (SC) is a popular technique for improving the reasoning accuracy of large language models by aggregating multiple sampled outputs, but it comes at a high computational cost due to extensive sampling. We introduce a hybrid ensembling approach that leverages the complementary strengths of two distinct modes of reasoning: Chain-of-Thought (CoT) and Program-of-Thought (PoT). We describe a general framework for combining these two forms of reasoning in self-consistency, as well as particular strategies for both full sampling and early-stopping. We show that CoT-PoT ensembling not only improves overall accuracy, but also drastically reduces the number of samples required for SC by a factor of 9.3x. In particular, the majority of tasks (78.6%) can be addressed with only two samples, which has not been possible with any prior SC methods.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning. Builds on 21 of its 22 references that are in the map. First posted on arXiv 19 Apr 2026.

Builds on

21 of 22 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024Make Every Penny Count: Difficulty-Adaptive Self-Consistency for Cost-Efficient Reasoning24 Aug
  2. 2024Escape Sky-high Cost: Early-stopping Self-Consistency for Multi-step Reasoning19 Jan
  3. 2023Let's Sample Step by Step: Adaptive-Consistency for Efficient Reasoning and Coding with LLMs19 May
  4. 2022Large Language Models Can Self-Improve20 Oct

Other references · 17

  1. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  2. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  3. 2017Deep reinforcement learning from human preferencescited by 3,846
  4. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  5. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 1,906
  6. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,057
  7. 2024Large Language Monkeys: Scaling Inference Compute with Repeated Samplingcited by 946
  8. 2023Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotationscited by 895
  9. 2021Are NLP Models really able to Solve Simple Math Word Problems?cited by 861
  10. 2021FinQA: A Dataset of Numerical Reasoning over Financial Datacited by 552
  11. 2023MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuningcited by 483
  12. 2022Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoningcited by 347
5 more
  1. 2023Large Language Model Cascades with Mixture of Thoughts Representations for Cost-efficient Reasoningcited by 140
  2. 2023Rewarding Chatbots for Real-World Engagement with Millions of Userscited by 58
  3. 2024The Larger the Better? Improved LLM Code-Generation via Budget Reallocationcited by 41
  4. 2023Automatic Model Selection with Large Language Models for Reasoningcited by 35
  5. 2023Plan, Verify and Switch: Integrated Reasoning with Diverse X-of-Thoughtscited by 27

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Optimal Self-Consistency for Efficient Reasoning with Large Language Models
  2. 2024Reasoning Aware Self-Consistency: Leveraging Reasoning Paths for Efficient LLM Sampling
  3. 2023Two Failures of Self-Consistency in the Multi-Step Reasoning of LLMs
  4. 2024Semantic Self-Consistency: Enhancing Language Model Reasoning via Semantic Weighting
  5. 2025Self-Consistency Is Losing Its Edge: Diminishing Returns and Rising Costs in Modern LLMs
  6. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Models
  7. 2025A Theoretical Study on Bridging Internal Probability and Self-Consistency for LLM Reasoning
  8. 2024Integrate the Essence and Eliminate the Dross: Fine-Grained Self-Consistency for Free-Form Language Generation