mlsanityData to 14 Oct 2026

REL: Working out is all you need

arXiv 2412.04645 ↗First posted 5 Dec 2024cs.AIcited by 0

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Recent developments, particularly OpenAI's O1 model, have demonstrated the remarkable potential of Large Language Models (LLMs) for complex reasoning tasks. Through analysis of O1's outputs and provided sample Chain-of-Thought (CoT) demonstrations, we observe that it approaches problem-solving in a distinctly human-like manner, systematically brainstorming ideas, testing hypotheses, verifying results, and planning comprehensive solutions. These sophisticated reasoning capabilities remain notably absent in other state-of-the-art language models. In this paper, we hypothesize that this performance gap stems from the limited availability of high-quality reasoning process data in current training sets. We demonstrate that by constructing a specialized dataset focused on explicit problem-solving workflows ("worked solutions"), we can elicit substantially improved planning capabilities from existing models. Additionally, we propose the Reasoning Enhancement Loop (REL), a method for generating synthetic worked solutions.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 18 of its 19 references that are in the map. First posted on arXiv 5 Dec 2024.

Builds on

18 of 19 references.

References · 18

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  4. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  5. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  6. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameterscited by 1,986
  7. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,407
  8. 2023Instruction-Following Evaluation for Large Language Modelscited by 1,228
  9. 2021A General Language Assistant as a Laboratory for Alignmentcited by 1,055
  10. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 1,017
  11. 2022STaR: Bootstrapping Reasoning With Reasoningcited by 940
  12. 2023Instruction Tuning for Large Language Models: A Surveycited by 623
6 more
  1. 2023The Curse of Recursion: Training on Generated Data Makes Models Forgetcited by 356
  2. 2024Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learningcited by 241
  3. 2022Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matterscited by 222
  4. 2024LLMs Can't Plan, But Can Help Planning in LLM-Modulo Frameworkscited by 179
  5. 2024LLMs Still Can't Plan; Can LRMs? A Preliminary Evaluation of OpenAI's o1 on PlanBenchcited by 94
  6. 2018Estimate and Replace: A Novel Approach to Integrating Deep Neural Networks with Existing Applicationscited by 21

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models
  2. 2024A Comparative Study on Reasoning Patterns of OpenAI's o1 Model
  3. 2024OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models
  4. 2024Inference Scaling vs Reasoning: An Empirical Analysis of Compute-Optimal LLM Problem-Solving
  5. 2025Knowledge Augmented Complex Problem Solving with Large Language Models: A Survey
  6. 2025Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models
  7. 2025Bridging the Reasoning Gap: Small LLMs Can Plan with Generalised Strategies
  8. 2025From System 1 to System 2: A Survey of Reasoning Large Language Models