mlsanityData to 14 Oct 2026

Dynamic Chain-of-Thought: Towards Adaptive Deep Reasoning

arXiv 2502.10428 ↗First posted 7 Feb 2025cs.AI cs.LGcited by 5

On the map: LLM reasoning → Prompting and chain-of-thought reasoning

Abstract (arXiv)

To reduce the cost and consumption of computing resources caused by computational redundancy and delayed reward assignment in long CoT, this research proposes the dynamic chain-of-thought (D-CoT) with adaptive reasoning time and steps. The researcher used simulation experiment to simulate the integration of D-CoT through Python 3.13 IDLE combined with a Python simulator based on GPTs. At the same time, the researcher used DeepSeek R1 as a control group to test and compare the performance of the D-CoT simulator in processing MIT OpenCourseWare's linear algebra exam questions. Experimental results show that D-CoT is better than DeepSeek R1 based on long CoT in three indicators: reasoning time, CoT length (reasoning steps) and token count, which achieves a significant reduction in computing resource consumption. In addition, this research has potential value in deep reasoning optimization that is used as a reference for future dynamic deep reasoning frameworks.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning. Builds on 16 of its 22 references that are in the map. First posted on arXiv 7 Feb 2025.

Builds on

16 of 22 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024The Impact of Reasoning Step Length on Large Language Models10 Jan
  2. 2023Towards Revealing the Mystery behind Chain of Thought: A Theoretical Perspective24 May
  3. 2023Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting7 May
  4. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Models28 Jan

Other references · 12

  1. 2017Attention Is All You Needcited by 60,361
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  4. 2024DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Modelscited by 867
  5. 2024Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMscited by 570
  6. 2024O1 Replication Journey: A Strategic Progress Report -- Part 1cited by 143
  7. 2024Evaluation of OpenAI o1: Opportunities and Challenges of AGIcited by 127
  8. 2024O1 Replication Journey -- Part 2: Surpassing O1-preview through Simple Distillation, Big Progress or Bitter Lesson?cited by 92
  9. 2025o3-mini vs DeepSeek-R1: Which One is Safer?cited by 24
  10. 2024From GPT-4 to Gemini and Beyond: Assessing the Landscape of MLLMs on Generalizability, Trustworthiness and Causality through Four Modalitiescited by 19
  11. 2024From Text to Transformation: A Comprehensive Review of Large Language Models' Versatilitycited by 19
  12. 2024OpenRFT: Adapting Reasoning Foundation Model for Domain-specific Tasks with Reinforcement Fine-Tuningcited by 13

Built on by

Cited by year

Citing papers per year: 2025: 5.

5 papers.

  1. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 384
  2. 2025Co-Evolving LLM Coder and Unit Tester via Reinforcement Learningcited by 56
  3. 2025To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Modelscited by 22
  4. 2025BadThink: Triggered Overthinking Attacks on Chain-of-Thought Reasoning in Large Language Modelscited by 8
  5. 2025Evaluation of LLMs for mathematical problem solvingcited by 7

Similar, not cited

Close in wording, no citation either way

  1. 2025Adaptive Deep Reasoning: Triggering Deep Thinking When Needed
  2. 2024To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning
  3. 2024Rethinking Chain-of-Thought from the Perspective of Self-Training
  4. 2025Long or short CoT? Investigating Instance-level Switch of Large Reasoning Models
  5. 2026Divide-and-Conquer CoT: RL for Reducing Latency via Parallel Reasoning
  6. 2024Markov Chain of Thought for Efficient Mathematical Reasoning
  7. 2026D-COT: Disciplined Chain-of-Thought Learning for Efficient Reasoning in Small Language Models
  8. 2023Stress Testing Chain-of-Thought Prompting for Large Language Models