Synthetic Proofs with Tool-Integrated Reasoning: Contrastive Alignment for LLM Mathematics with Lean

Mark Obozov, Michael Diskin, Aleksandr Beznosikov, Alexander Gasnikov, Serguei Barannikov

Abstract: Modern mathematical reasoning benchmarks primarily focus on answer finding rather than proof verification, creating a gap in evaluating the proving capabilities of large language models (LLMs). We present a methodology for generating diverse mathematical proof tasks using formal tools. Our approach combines Lean-based synthetic problem generation with a novel Tool-Integrated Reasoning (TiR) framework for partial proof validation, and it uses contrastive preference optimization to align the model's proof outputs. Experiments on the Qwen-2.5 family of models demonstrate meaningful improvements in mathematical reasoning, particularly for smaller models. Our aligned models achieve up to a 57% higher success rate than baselines on the MiniF2F benchmark (across 0.5B, 1.5B, and 7B parameter models). These results highlight the potential of synthetic data and integrated validation for advancing LLM-based mathematical reasoning.