FLARE: Verifying MILP Reformulations with LLM-Based Theorem Proving

arXiv:2608.25220 · cs.AI, cs.LO, math.OC · Submitted 2026-08-25 · Read on arXiv

cs.AI, cs.LO, math.OC

Submitted: 2026-08-25

Updated: 2026-08-25

Code: https://github.com/henryrobbins/flare

Terminology

• Accuracy — 23× in this paper · explained in 1 episode
• Verification — 19× in this paper · explained in 2 episodes
• Agent Harness — 8× in this paper · explained in 2 episodes
• Ablation — 7× in this paper · explained in 1 episode
• Axioms — 6× in this paper · explained in 2 episodes
• Ablation study — 5× in this paper · explained in 1 episode
• Agent Skills — 5× in this paper · explained in 1 episode
• Mixed-Integer Linear Programming — 5× in this paper
• Traveling Salesman Problem — 5× in this paper
• Benchmark — 4× in this paper · explained in 2 episodes
• Objective Function — 4× in this paper · explained in 2 episodes
• World Food Program — 4× in this paper
• Formal Verification — 3× in this paper · explained in 2 episodes
• Adam — 2× in this paper · explained in 2 episodes
• Agentic Framework — 2× in this paper · explained in 6 episodes
• Air Traffic Management — 2× in this paper
• Combinatorial Optimization — 2× in this paper · explained in 2 episodes
• Core — 2× in this paper · explained in 2 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Agentic Reasoning — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Few-Shot Learning — 1× in this paper · explained in 4 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Hallucination — 1× in this paper · explained in 3 episodes
• LLM judge — 1× in this paper · explained in 2 episodes
• LLM-as-a-Judge — 1× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Lean Language Server Protocol — 1× in this paper
• Model Context Protocol — 1× in this paper
• Model Context Protocol (MCP) — 1× in this paper · explained in 8 episodes
• Multi-Agent System — 1× in this paper · explained in 6 episodes
• Progressive Disclosure — 1× in this paper · explained in 2 episodes
• Quantum Physics — 1× in this paper · explained in 10 episodes

Sources

• OptiMUS-0.3: Using Large Language Models to Model and Solve Optimization Problems at Scale
• Ax-Prover: A Deep Reasoning Agentic Framework for Theorem Proving in Mathematics and Quantum Physics
• Seed-Prover 1.5: Mastering Undergraduate-Level Theorem Proving via Learning from Experience
• Let's Have a Conversation: Designing and Evaluating LLM Agents for Interactive Optimization
• Mathematical exploration and discovery at scale
• Glia: A Human-Inspired AI for Automated Systems Design and Optimization
• VRPAgent: LLM-Driven Discovery of Heuristic Operators for Vehicle Routing Problems
• Automated Conjecture Resolution with Formal Verification
• Large Language Models for Supply Chain Optimization
• Large-Scale Optimization Model Auto-Formulation: Harnessing LLM Flexibility via Structured Workflow
• Numina-Lean-Agent: An Open and General Agentic Reasoning System for Formal Mathematics
• AlphaEvolve: A coding agent for scientific and algorithmic discovery
• DeepSeek-Prover-V2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal Decomposition
• A Minimal Agent for Automated Theorem Proving
• Kimina-Prover Preview: Towards Large Formal Reasoning Models with Reinforcement Learning
• ORGEval: Graph-Theoretic Evaluation of LLMs in Optimization Modeling
• Enhancing CVRP Solver through LLM-driven Automatic Heuristic Design
• EvoCut: Strengthening Integer Programs via Evolution-Guided Language Models

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
• 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
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection