mlsanityData to 14 Oct 2026

Enhancing Large Language Models through Structured Reasoning

arXiv 2506.20241 ↗First posted 25 Jun 2025cs.CL cs.AIcited by 5

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Recent Large Language Models (LLMs) have significantly advanced natural language processing and automated decision-making. However, these models still encounter difficulties when performing complex reasoning tasks involving logical deduction and systematic planning, primarily due to their reliance on implicit statistical relationships without structured knowledge representation.Inspired by cognitive science and neurosymbolic AI, we introduce a novel approach to enhance LLMs through explicit structured reasoning. First, we convert unstructured data into structured formats by explicitly annotating reasoning steps. We then employ this structured dataset to train LLMs through Supervised Fine-Tuning (SFT). Additionally, we enhance the structured reasoning capabilities of LLMs using Group Relative Policy Optimization (GRPO), incorporating two innovative algorithms--MAX-Flow and Longest Common Subsequence (LCS)--which notably improve reasoning effectiveness and reduce computational complexity. Experimental results from fine-tuning a DeepSeek-R1-Distill-Qwen-1.5B model demonstrate concise reasoning, robust performance across various scenarios, and improved compatibility with optimization techniques, validating the efficacy of structured reasoning integration in LLMs.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 23 of its 56 references that are in the map. First posted on arXiv 25 Jun 2025.

Builds on

23 of 56 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond13 Mar

Other references · 22

  1. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  2. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,810
  3. 2024OpenAI o1 System Cardcited by 1,244
  4. 2025Kimi k1.5: Scaling Reinforcement Learning with LLMscited by 1,210
  5. 2023Eureka: Human-Level Reward Design via Coding Large Language Modelscited by 571
  6. 2025Process Reinforcement through Implicit Rewardscited by 504
  7. 2025L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learningcited by 384
  8. 2025VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Taskscited by 285
  9. 2025O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruningcited by 279
  10. 2025Training Language Models to Reason Efficientlycited by 247
  11. 2025REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalizationcited by 241
  12. 2025ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learningcited by 192
10 more
  1. 2024VinePPO: Refining Credit Assignment in RL Training of LLMscited by 183
  2. 2025DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Modelscited by 158
  3. 2025CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Modelscited by 96
  4. 2024On Designing Effective RL Reward at Training Time for LLM Reasoningcited by 87
  5. 2025Tapered Off-Policy REINFORCE: Stable and efficient reinforcement learning for LLMscited by 61
  6. 2025Think When You Need: Self-Adaptive Chain-of-Thought Learningcited by 38
  7. 2025Enhancing LLM Reasoning with Iterative DPO: A Comprehensive Empirical Investigationcited by 37
  8. 2025Exploring Data Scaling Trends and Effects in Reinforcement Learning from Human Feedbackcited by 26
  9. 2025Adaptive Group Policy Optimization: Towards Stable Training and Token-Efficient Reasoningcited by 21
  10. 2025One Framework to Rule Them All: Unifying RL-Based and RL-Free Methods in RLHFcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 3.

5 papers.

  1. 2025Dropping Experts, Recombining Neurons: Retraining-Free Pruning for Sparse Mixture-of-Experts LLMscited by 25
  2. 2026From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AIcited by 6
  3. 2026SPEAR: Distilling Domain-Adaptive Reasoning Skeletons via Sequential Symbolic Alignment in Reinforcement Learningcited by 1
  4. 2025ReFIne: A Framework for Trustworthy Large Reasoning Models with Reliability, Faithfulness, and Interpretabilitycited by 0
  5. 2026RecBundle: A Next-Generation Geometric Paradigm for Explainable Recommender Systemscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Structured Reasoning for Large Language Models
  2. 2025Advancing Reasoning in Large Language Models: Promising Methods and Approaches
  3. 2025From Implicit Exploration to Structured Reasoning: Leveraging Guideline and Refinement for LLMs
  4. 2025Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models
  5. 2025Reasoning Beyond Limits: Advances and Open Problems for LLMs
  6. 2026Maistros: A Greek Large Language Model Adapted Through Knowledge Distillation From Large Reasoning Models
  7. 2025Implicit Reasoning in Large Language Models: A Comprehensive Survey
  8. 2024Struct-X: Enhancing Large Language Models Reasoning with Structured Data