mlsanityData to 14 Oct 2026

From Language to Logic: A Bi-Level Framework for Structured Reasoning

arXiv 2507.08501 ↗First posted 11 Jul 2025cs.AIcited by 0

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Structured reasoning over natural language inputs remains a core challenge in artificial intelligence, as it requires bridging the gap between unstructured linguistic expressions and formal logical representations. In this paper, we propose a novel bi-level framework that maps language to logic through a two-stage process: high-level task abstraction and low-level logic generation. At the upper level, a large language model (LLM) parses natural language queries into intermediate structured representations specifying the problem type, objectives, decision variables, and symbolic constraints. At the lower level, the LLM uses these representations to generate symbolic workflows or executable reasoning programs for accurate and interpretable decision making. The framework supports modular reasoning, enforces explicit constraints, and generalizes across domains such as mathematical problem solving, question answering, and logical inference. We further optimize the framework with an end-to-end bi-level optimization approach that jointly refines both the high-level abstraction and low-level logic generation stages. Experiments on multiple realistic reasoning benchmarks demonstrate that our approach significantly outperforms existing baselines in accuracy, with accuracy gains reaching as high as 40%. Moreover, the bi-level design enhances transparency and error traceability, offering a promising step toward trustworthy and systematic reasoning with LLMs.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 30 of its 69 references that are in the map. First posted on arXiv 11 Jul 2025.

Builds on

30 of 69 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025AutoLogi: Automated Generation of Logic Puzzles for Evaluating Reasoning Abilities of Large Language Models24 Feb
  2. 2024On Memorization of Large Language Models in Logical Reasoning30 Oct
  3. 2023Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning20 May

Other references · 27

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  3. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  4. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  5. 2024Qwen2.5 Technical Reportcited by 4,942
  6. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameterscited by 1,986
  7. 2024OpenAI o1 System Cardcited by 1,244
  8. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,076
  9. 2021Are NLP Models really able to Solve Simple Math Word Problems?cited by 878
  10. 2017Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problemscited by 650
  11. 2024Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMscited by 570
  12. 2023Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Modelscited by 560
15 more
  1. 2022Decomposed Prompting: A Modular Approach for Solving Complex Taskscited by 558
  2. 2025rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinkingcited by 313
  3. 2025REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalizationcited by 241
  4. 2021A Dataset for Answering Time-Sensitive Questionscited by 154
  5. 2025Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Thoughtcited by 109
  6. 2023GPT-4 Doesn't Know It's Wrong: An Analysis of Iterative Prompting for Reasoning Problemscited by 89
  7. 2024Test of Time: A Benchmark for Evaluating LLMs on Temporal Reasoningcited by 88
  8. 2025ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learningcited by 79
  9. 2025ReasonFlux: Hierarchical LLM Reasoning via Scaling Thought Templatescited by 63
  10. 2024MathCoder2: Better Math Reasoning from Continued Pretraining on Model-translated Mathematical Codecited by 39
  11. 2025PR-Attack: Coordinated Prompt-RAG Attacks on Retrieval-Augmented Generation in Large Language Models via Bilevel Optimizationcited by 32
  12. 2025CounterBench: Evaluating and Improving Counterfactual Reasoning in Large Language Modelscited by 21
  13. 2024Code Prompting Elicits Conditional Reasoning Abilities in Text+Code LLMscited by 20
  14. 2024Abstraction-of-Thought Makes Language Models Better Reasonerscited by 11
  15. 2025Argus: Federated Non-convex Bilevel Learning over 6G Space-Air-Ground Integrated Networkcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2022Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning
  2. 2025Reasoning Beyond Language: A Comprehensive Survey on Latent Chain-of-Thought Reasoning
  3. 2025Enhancing Large Language Models through Structured Reasoning
  4. 2024Reliable Reasoning Beyond Natural Language
  5. 2024Leveraging LLMs for Hypothetical Deduction in Logical Inference: A Neuro-Symbolic Approach
  6. 2026Pushing the Boundaries of Natural Reasoning: Interleaved Bonus from Formal-Logic Verification
  7. 2025Reasoning Systems as Structured Processes: Foundations, Failures, and Formal Criteria
  8. 2026SymbolLKG: Towards Verifiable Logical Reasoning via Logical Knowledge Graph and Symbolic Solvers