Learning to Prove, Not Just to Answer: Reinforcement Learning from Formal Verification for Natural-Language Logical Reasoning
cs.AI
Submitted: 2026-09-29
Updated: 2026-09-29
Code: https://github.com/AI4SS/Logic-Agent5https:
Project page: https://cvc5.github.io/papers/2022/BarbosaBBKLMMMN-TACAS22.pdf
Terminology
Sources
- Learning to Generate Formally Verifiable Step-by-Step Logic Reasoning via Structured Formal Intermediaries
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- The Llama 3 Herd of Models
- VeriCoT: Neuro-symbolic Chain-of-Thought Validation via Logical Consistency Checks
- Large Language Models Meet Symbolic Provers for Logical Reasoning Evaluation
- Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- HybridFlow: A Flexible and Efficient RLHF Framework
- Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
- Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning
- LogicReward: Incentivizing LLM Reasoning via Step-Wise Logical Supervision
- Qwen2.5 Technical Report
- Qwen3 Technical Report
- Semantic-Aware Logical Reasoning via a Semiotic Framework
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems