mlsanityData to 14 Oct 2026

ReasoningFlow: Semantic Structure of Complex Reasoning Traces

arXiv 2506.02532 ↗First posted 3 Jun 2025cs.CLcited by 12

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

Abstract (arXiv)

Large reasoning models (LRMs) generate complex reasoning traces with planning, reflection, verification, and backtracking. In this work, we introduce ReasoningFlow, a unified schema for analyzing the semantic structures of these complex traces. ReasoningFlow parses traces into directed acyclic graphs, enabling the characterization of distinct reasoning patterns as subgraph structures. This human-interpretable representation offers promising applications in understanding, evaluating, and enhancing the reasoning processes of LRMs.

Key facts. Cited by 12 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 12 of its 23 references that are in the map. First posted on arXiv 3 Jun 2025.

Builds on

12 of 23 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond27 Mar
  2. 2025Scaling Evaluation-time Compute with Reasoning Models as Evaluators25 Mar
  3. 2025Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models20 Mar
  4. 2025Demystifying Long Chain-of-Thought Reasoning in LLMs5 Feb
  5. 2025Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs30 Jan

Other references · 7

  1. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  2. 2024A Survey on LLM-as-a-Judgecited by 1,423
  3. 2025Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRscited by 377
  4. 2025DeepSeek-R1 Thoughtology: Let's think about LLM Reasoningcited by 92
  5. 2025Evaluating Step-by-step Reasoning Traces: A Surveycited by 63
  6. 2014Clingo = ASP + Control: Preliminary Reportcited by 56
  7. 2025Premise-Augmented Reasoning Chains Improve Error Identification in Math reasoning with LLMscited by 22

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 9.

12 papers.

  1. 2025Where Did This Sentence Come From? Tracing Provenance in LLM Reasoning Distillationcited by 6
  2. 2026Characterizing, Evaluating, and Optimizing Complex Reasoningcited by 5
  3. 2026ReasonOps: Operator Segmentation for LLM Reasoning Tracescited by 5
  4. 2026ReasoningFlow: Discourse Structures for Understanding LLM Reasoning Tracescited by 5
  5. 2026FaithformBench: Benchmarking Faithfulness of Mathematical Chain-of-Thought Autoformalisationcited by 5
  6. 2025Modeling Hierarchical Thinking in Large Reasoning Modelscited by 3
  7. 2025KisMATH: Do LLMs Have Knowledge of Implicit Structures in Mathematical Reasoning?cited by 2
  8. 2026Reasoning Consensus: Structural Ensembling of LLM Reasoning via Weighted DAG Aggregationcited by 2
  9. 2026Beyond Input Understanding: Diagnosing Multilingual Mathematical Reasoning with Directed Acyclic Trace Graphscited by 0
  10. 2026ThinkProbe: Beyond Accuracy -- Structural Profiling of Open-Ended LLM Reasoning Traces via Non-Generative Thought Graphscited by 0
  11. 2026LCoT-GV: Graph Attention Networks for Verifying Long Reasoning Chains in Large Language Modelscited by 0
  12. 2026SearchAtlas: Analyzing Agentic Search Strategies via Evidential Query Graphscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Reasoning Structure of Large Language Models
  2. 2025Graph-Memoized Reasoning: Foundations Structured Workflow Reuse in Intelligent Systems
  3. 2023Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning
  4. 2026Exposing Weaknesses of Large Reasoning Models through Graph Algorithm Problems
  5. 2025Topology of Reasoning: Understanding Large Reasoning Models through Reasoning Graph Properties
  6. 2025Grounding LLM Reasoning with Knowledge Graphs
  7. 2025Reasoning Models Reason Well, Until They Don't
  8. 2025PathMind: A Retrieve-Prioritize-Reason Framework for Knowledge Graph Reasoning with Large Language Models