mlsanityData to 14 Oct 2026

LogiDynamics: Unraveling the Dynamics of Inductive, Abductive and Deductive Logical Inferences in LLM Reasoning

arXiv 2502.11176 ↗First posted 16 Feb 2025cs.CLcited by 12

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Modern large language models (LLMs) employ diverse logical inference mechanisms for reasoning, making the strategic optimization of these approaches critical for advancing their capabilities. This paper systematically investigate the comparative dynamics of inductive (System 1) versus abductive/deductive (System 2) inference in LLMs. We utilize a controlled analogical reasoning environment, varying modality (textual, visual, symbolic), difficulty, and task format (MCQ / free-text). Our analysis reveals System 2 pipelines generally excel, particularly in visual/symbolic modalities and harder tasks, while System 1 is competitive for textual and easier problems. Crucially, task format significantly influences their relative advantage, with System 1 sometimes outperforming System 2 in free-text rule-execution. These core findings generalize to broader in-context learning. Furthermore, we demonstrate that advanced System 2 strategies like hypothesis selection and iterative refinement can substantially scale LLM reasoning. This study offers foundational insights and actionable guidelines for strategically deploying logical inference to enhance LLM reasoning. Resources are available at https://github.com/HKUST-KnowComp/LogiDynamics.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 39 of its 80 references that are in the map. First posted on arXiv 16 Feb 2025.

Builds on

39 of 80 references.

Closest ancestors · 11

Same direction, newest first

  1. 2024DeepSeek-V3 Technical Report27 Dec
  2. 2024Can ChatGPT Make Explanatory Inferences? Benchmarks for Abductive Reasoning29 Apr
  3. 2024An Incomplete Loop: Deductive, Inductive, and Abductive Reasoning in Language Models3 Apr
  4. 2023Advancing Abductive Reasoning in Knowledge Graphs through Complex Logical Hypothesis Generation25 Dec
  5. 2023UNcommonsense Reasoning: Abductive Reasoning about Uncommon Situations14 Nov
  6. 2023ARN: Analogical Reasoning on Narratives2 Oct
  7. 2023Testing the General Deductive Reasoning Capacity of Large Language Models Using OOD Examples24 May
  8. 2023ChatABL: Abductive Learning via Natural Language Interaction with ChatGPT21 Apr
  9. 2022True Detective: A Deep Abductive Reasoning Benchmark Undoable for GPT-3 and Challenging for GPT-420 Dec
  10. 2022Emergent Analogical Reasoning in Large Language Models19 Dec
  11. 2022FOLIO: Natural Language Reasoning with First-Order Logic2 Sep

Other references · 28

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  4. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  5. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  6. 2024Qwen2.5 Technical Reportcited by 4,942
  7. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
  8. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,474
  9. 2020ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Languagecited by 324
  10. 2019Abductive Commonsense Reasoningcited by 301
  11. 2020Transformers as Soft Reasoners over Languagecited by 270
  12. 2024Pixtral 12Bcited by 179
16 more
  1. 2021Explaining Answers with Entailment Treescited by 152
  2. 2019On the Measure of Intelligencecited by 144
  3. 2023LLMs and the Abstraction and Reasoning Corpus: Successes, Failures, and the Importance of Object-based Representationscited by 82
  4. 2023A Benchmark for Learning to Translate a New Language from One Grammar Bookcited by 75
  5. 2020Stratified Rule-Aware Network for Abstract Visual Reasoningcited by 72
  6. 2020Back to the Future: Unsupervised Backprop-based Decoding for Counterfactual and Abductive Commonsense Reasoningcited by 65
  7. 2023StoryAnalogy: Deriving Story-level Analogies from Large Language Models to Unlock Analogical Understandingcited by 26
  8. 2022VASR: Visual Analogies of Situation Recognitioncited by 22
  9. 2024IDEA: Enhancing the Rule Learning Ability of Large Language Model Agent through Induction, Deduction, and Abductioncited by 22
  10. 2024AnaloBench: Benchmarking the Identification of Abstract and Long-context Analogiescited by 13
  11. 2023ANALOGICAL -- A Novel Benchmark for Long Text Analogy Evaluation in Large Language Modelscited by 12
  12. 2023Self-Consistent Narrative Prompts on Abductive Natural Language Inferencecited by 11
  13. 2024ComparisonQA: Evaluating Factuality Robustness of LLMs Through Knowledge Frequency Control and Uncertaintycited by 10
  14. 2024Can Large Language Models generalize analogy solving like children can?cited by 9
  15. 2017SCAN: Learning Hierarchical Compositional Visual Conceptscited by 6
  16. 2022Embarrassingly Simple Performance Prediction for Abductive Natural Language Inferencecited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 7; 2026: 5.

12 papers.

  1. 2025The Curse of CoT: On the Limitations of Chain-of-Thought in In-Context Learningcited by 30
  2. 2025Patterns Over Principles: The Fragility of Inductive Reasoning in LLMs under Noisy Observationscited by 12
  3. 2025Controllable Logical Hypothesis Generation for Abductive Reasoning in Knowledge Graphscited by 11
  4. 2025LLM-Hanabi: Evaluating Multi-Agent Gameplays with Theory-of-Mind and Rationale Inference in Imperfect Information Collaboration Gamecited by 8
  5. 2025Unifying Deductive and Abductive Reasoning in Knowledge Graphs with Masked Diffusion Modelcited by 8
  6. 2026Wiring the 'Why': A Unified Taxonomy and Survey of Abductive Reasoning in LLMscited by 5
  7. 2025DixitWorld: Evaluating Multimodal Abductive Reasoning in Vision-Language Models with Multi-Agent Dixit Gameplaycited by 4
  8. 2026Caesar: Deep Agentic Web Exploration for Creative Answer Synthesiscited by 1
  9. 2025Johnny: Structuring Representation Space to Enhance Machine Abstract Reasoning Abilitycited by 0
  10. 2026Towards automated data analysis: A guided framework for LLM-based risk estimationcited by 0
  11. 2026SciLens: Multi-modal Scientific Claim Verification with Agentic Entailment and Groundingcited by 0
  12. 2026PIE-APT: Abductive Planning over Temporal Dynamic Knowledge Graphs via Incremental Reasoningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024The Role of Deductive and Inductive Reasoning in Large Language Models
  2. 2024Inductive or Deductive? Rethinking the Fundamental Reasoning Abilities of LLMs
  3. 2025Logical Reasoning in Large Language Models: A Survey
  4. 2024Leveraging LLMs for Hypothetical Deduction in Logical Inference: A Neuro-Symbolic Approach
  5. 2025A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems
  6. 2025Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs
  7. 2025Reasoning on a Spectrum: Aligning LLMs to System 1 and System 2 Thinking
  8. 2023DetermLR: Augmenting LLM-based Logical Reasoning from Indeterminacy to Determinacy