mlsanityData to 14 Oct 2026

Recursion of Thought: A Divide-and-Conquer Approach to Multi-Context Reasoning with Language Models

arXiv 2306.06891 ↗First posted 12 Jun 2023cs.CL cs.AIcited by 24

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

Abstract (arXiv)

Generating intermediate steps, or Chain of Thought (CoT), is an effective way to significantly improve language models' (LM) multi-step reasoning capability. However, the CoT lengths can grow rapidly with the problem complexity, easily exceeding the maximum context size. Instead of increasing the context limit, which has already been heavily investigated, we explore an orthogonal direction: making LMs divide a problem into multiple contexts. We propose a new inference framework, called Recursion of Thought (RoT), which introduces several special tokens that the models can output to trigger context-related operations. Extensive experiments with multiple architectures including GPT-3 show that RoT dramatically improves LMs' inference capability to solve problems, whose solution consists of hundreds of thousands of tokens.

Key facts. Cited by 24 papers in the map (data through 14 Oct 2026). Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning. Builds on 17 of its 22 references that are in the map. First posted on arXiv 12 Jun 2023.

Builds on

17 of 22 references.

References · 17

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  5. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  6. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  7. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,407
  8. 2022Solving Quantitative Reasoning Problems with Language Modelscited by 1,392
  9. 2021Show Your Work: Scratchpads for Intermediate Computation with Language Modelscited by 886
  10. 2020Efficient Transformers: A Surveycited by 790
  11. 2020Long Range Arena: A Benchmark for Efficient Transformerscited by 700
  12. 2022Decomposed Prompting: A Modular Approach for Solving Complex Taskscited by 558
5 more
  1. 2019Theoretical Limitations of Self-Attention in Neural Sequence Modelscited by 288
  2. 2015Neural Programmer-Interpreterscited by 101
  3. 2022Successive Prompting for Decomposing Complex Questionscited by 94
  4. 2017Making Neural Programming Architectures Generalize via Recursioncited by 35
  5. 2019Learning Compositional Neural Programs with Recursive Tree Search and Planningcited by 17

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 16; 2025: 2; 2026: 3.

24 papers.

Sort:

By area:

  1. 2023Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Futurecited by 184
  2. 2023Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agentscited by 72
  3. 2024MAPO: Advancing Multilingual Reasoning through Multilingual Alignment-as-Preference Optimizationcited by 69
  4. 2024Follow the Rules: Reasoning for Video Anomaly Detection with Large Language Modelscited by 57
  5. 2024LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraintscited by 35
  6. 2024Dynamic Planning for LLM-based Graphical User Interface Automationcited by 19
  7. 2024Structure Guided Prompt: Instructing Large Language Model in Multi-Step Reasoning by Exploring Graph Structure of the Textcited by 14
  8. 2025Pie: A Programmable Serving System for Emerging LLM Applicationscited by 14
  9. 2024Regress, Don't Guess -- A Regression-like Loss on Number Tokens for Language Modelscited by 13
  10. 2024A Theory for Length Generalization in Learning to Reasoncited by 11
  11. 2024Beyond Graphs: Can Large Language Models Comprehend Hypergraphs?cited by 11
  12. 2024Reversal of Thought: Enhancing Large Language Models with Preference-Guided Reverse Reasoning Warm-upcited by 10
12 more
  1. 2024Reverse That Number! Decoding Order Matters in Arithmetic Learningcited by 9
  2. 2026Recursive Models for Long-Horizon Reasoningcited by 9
  3. 2024ReDel: A Toolkit for LLM-Powered Recursive Multi-Agent Systemscited by 8
  4. 2023Conditions for Length Generalization in Learning Reasoning Skillscited by 7
  5. 2024Let's Be Self-generated via Step by Step: A Curriculum Learning Approach to Automated Reasoning with Large Language Modelscited by 4
  6. 2024Towards Goal-oriented Prompt Engineering for Large Language Models: A Surveycited by 3
  7. 2024Large Language Models as Realistic Microservice Trace Generatorscited by 2
  8. 2024AutoReason: Automatic Few-Shot Reasoning Decompositioncited by 1
  9. 2024MetaRuleGPT: Recursive Numerical Reasoning of Language Models Trained with Simple Rulescited by 1
  10. 2025Serve Programs, Not Promptscited by 0
  11. 2026Understanding Tone-Dependent Inference Cost in Large Language Modelscited by 0
  12. 2026Recursive Language Models Generalize Out of Domaincited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Chained Recursive Language Models for Multi-Iteration Reasoning
  2. 2024Fine-Tuning on Diverse Reasoning Chains Drives Within-Inference CoT Refinement in LLMs
  3. 2023Chain-of-Thought Hub: A Continuous Effort to Measure Large Language Models' Reasoning Performance
  4. 2025Reasoning Beyond Language: A Comprehensive Survey on Latent Chain-of-Thought Reasoning
  5. 2025Recursive Decomposition of Logical Thoughts: Framework for Superior Reasoning and Knowledge Propagation in Large Language Models
  6. 2023Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Models
  7. 2026ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning
  8. 2025SCOUT: Teaching Pre-trained Language Models to Enhance Reasoning via Flow Chain-of-Thought