mlsanityData to 14 Oct 2026

Neuro-Symbolic Artificial Intelligence: Towards Improving the Reasoning Abilities of Large Language Models

arXiv 2508.13678 ↗First posted 19 Aug 2025cs.AI cs.LGcited by 20

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Large Language Models (LLMs) have shown promising results across various tasks, yet their reasoning capabilities remain a fundamental challenge. Developing AI systems with strong reasoning capabilities is regarded as a crucial milestone in the pursuit of Artificial General Intelligence (AGI) and has garnered considerable attention from both academia and industry. Various techniques have been explored to enhance the reasoning capabilities of LLMs, with neuro-symbolic approaches being a particularly promising way. This paper comprehensively reviews recent developments in neuro-symbolic approaches for enhancing LLM reasoning. We first present a formalization of reasoning tasks and give a brief introduction to the neurosymbolic learning paradigm. Then, we discuss neuro-symbolic methods for improving the reasoning capabilities of LLMs from three perspectives: Symbolic->LLM, LLM->Symbolic, and LLM+Symbolic. Finally, we discuss several key challenges and promising future directions. We have also released a GitHub repository including papers and resources related to this survey: https://github.com/LAMDASZ-ML/Awesome-LLM-Reasoning-with-NeSy.

Key facts. Cited by 20 papers in the map (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 8 of its 52 references that are in the map. First posted on arXiv 19 Aug 2025.

Builds on

8 of 52 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024DiLA: Enhancing LLM Tool Learning with Differential Logic Layer19 Feb

Other references · 7

  1. 2023LLM+P: Empowering Large Language Models with Optimal Planning Proficiencycited by 501
  2. 2020From Statistical Relational to Neuro-Symbolic Artificial Intelligencecited by 63
  3. 2022Plansformer: Generating Symbolic Plans using Transformerscited by 41
  4. 2024ChinaTravel: An Open-Ended Travel Planning Benchmark with Compositional Constraint Validation for Language Agentscited by 16
  5. 2024RLSF: Fine-tuning LLMs via Symbolic Feedbackcited by 14
  6. 2025LawGPT: Knowledge-Guided Data Generation and Its Application to Legal LLMcited by 8
  7. 2024AlphaIntegrator: Transformer Action Search for Symbolic Integration Proofscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 19.

20 papers.

Sort:

By area:

  1. 2026Adaptive Information Control for Search-Augmented LLM Reasoningcited by 11
  2. 2026SAME: Stabilized Mixture-of-Experts for Multimodal Continual Instruction Tuningcited by 8
  3. 2026Architecting Trust in Artificial Epistemic Agentscited by 3
  4. 2026The Y-Combinator for LLMs: Solving Long-Context Rot with λ-Calculuscited by 3
  5. 2026Thinking with Tables: Enhancing Multi-Modal Tabular Understanding via Neuro-Symbolic Reasoningcited by 3
  6. 2026Ontology-Constrained Neural Reasoning in Enterprise Agentic Systems: A Neurosymbolic Architecture for Domain-Grounded AI Agentscited by 3
  7. 2026NeSy-Route: A Neuro-Symbolic Benchmark for Constrained Route Planning in Remote Sensingcited by 2
  8. 2026Procedural Refinement by LLM-driven Algorithmic Debugging for ARC-AGI-2cited by 2
  9. 2026Aligning Progress and Feasibility: A Neuro-Symbolic Dual Memory Framework for Long-Horizon LLM Agentscited by 2
  10. 2026Hierarchical Alignment: Enforcing Hierarchical Instruction-Following in LLMs through Logical Consistencycited by 1
  11. 2026Towards Reliable and Robust LLM Planning: Symbolic Feedback-Driven Iterative Self-Refinement Frameworkcited by 1
  12. 2026sLTN: Structural Logic Tensor Networkscited by 1
8 more
  1. 2025Bi-CoG: Bi-Consistency-Guided Self-Training for Vision-Language Modelscited by 0
  2. 2026A Progressive Visual-Logic-Aligned Framework for Ride-Hailing Adjudicationcited by 0
  3. 2026Simulating Human Cognition: Heartbeat-Driven Autonomous Thinking Activity Scheduling for LLM-based AI systemscited by 0
  4. 2026BiNSGPS: Geometry Problem Solving via Bidirectional Neuro-Symbolic Interactioncited by 0
  5. 2026Bounding Boxes as Goals: Language-Conditioned Grasping via Neuro-Symbolic Planningcited by 0
  6. 2026SymDiag: Explainable Diagnosis for LLM Reasoning via Neuro-Symbolic Verificationcited by 0
  7. 2026SymboLLM-FE: LLM-Accelerated Symbolic Regression for Automated Feature Engineering on Tabular Datacited by 0
  8. 2026Euler: Towards Human-Centered Multi-Agent Mathematical Discoverycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Intermediate Languages Matter: Formal Languages and LLMs affect Neurosymbolic Reasoning
  2. 2025Improving Rule-based Reasoning in LLMs using Neurosymbolic Representations
  3. 2025Intermediate Languages Matter: Formal Choice Drives Neurosymbolic LLM Reasoning
  4. 2025A Comparative Study of Neurosymbolic AI Approaches to Interpretable Logical Reasoning
  5. 2022Is Neuro-Symbolic AI Meeting its Promise in Natural Language Processing? A Structured Review
  6. 2025Adaptive LLM-Symbolic Reasoning via Dynamic Logical Solver Composition
  7. 2025Current Practices for Building LLM-Powered Reasoning Tools Are Ad Hoc -- and We Can Do Better
  8. 2025Model-Grounded Symbolic Artificial Intelligence Systems Learning and Reasoning with Model-Grounded Symbolic Artificial Intelligence Systems