Solving Formal Math Problems by Decomposition and Iterative Reflection
read the original abstract
General-purpose Large Language Models (LLMs) have achieved remarkable success in intelligence, performing comparably to human experts on complex reasoning tasks such as coding and mathematical reasoning. However, generating formal proofs in specialized languages like Lean 4 remains a significant challenge for these models, limiting their application in complex theorem proving and automated verification. Current approaches typically require specializing models through fine-tuning on dedicated formal corpora, incurring high costs for data collection and training. In this work, we introduce \textbf{Delta Prover}, an agent-based framework that orchestrates the interaction between a general-purpose LLM and the Lean 4 proof environment. Delta Prover leverages the reflection and reasoning capabilities of general-purpose LLMs to interactively construct formal proofs in Lean 4, circumventing the need for model specialization. At its core, the agent integrates two novel, interdependent components: an algorithmic framework for reflective decomposition and iterative proof repair, and a custom Domain-Specific Language (DSL) built upon Lean 4 for streamlined subproblem management. \textbf{Delta Prover achieves a state-of-the-art 95.9\% success rate on the miniF2F-test benchmark, surpassing all existing approaches, including those requiring model specialization.} Furthermore, Delta Prover exhibits a significantly stronger test-time scaling law compared to standard Best-of-N proof strategies. Crucially, our findings demonstrate that general-purpose LLMs, when guided by an effective agentic structure, possess substantial untapped theorem-proving capabilities. This presents a computationally efficient alternative to specialized models for robust automated reasoning in formal environments.
This paper has not been read by Pith yet.
Forward citations
Cited by 8 Pith papers
-
Beyond the Library: An Agentic Framework for Autoformalizing Research Mathematics
An orchestrator-driven agentic pipeline using general coding LLMs autoformalizes 32 PutnamBench problems and the main theorems plus proofs from five STOC papers into Lean 4, with two proofs using only the kernel.
-
Beyond the Library: An Agentic Framework for Autoformalizing Research Mathematics
Agentic LLM framework autoformalizes 32 Putnam problems and main theorems plus proofs from five STOC papers into Lean 4, with two proofs using only kernel axioms.
-
Automating Formal Verification with Agent-Guided Tree Search
Agent-directed tree search improves LLM performance on Lean formal verification tasks, with context-based orchestration solving more intermediate specs at lower token cost than baseline agents.
-
Aristotle: IMO-level Automated Theorem Proving
Aristotle reaches gold-medal-equivalent performance on 2025 IMO problems via integrated Lean proof search, informal lemma formalization, and a dedicated geometry solver.
-
Optimizing the Cost-Quality Tradeoff of Agentic Theorem Provers in Lean
An agentic theorem prover in Lean uses a control plane to route actions based on cost and success estimates, achieving 28.9% lower average cost than a fixed-step baseline on a PutnamBench subset while preserving performance.
-
A Theoretical Framework for Self-Play Theorem Proving Algorithms
Provides a graph model of theorems and proves exponential growth of proved theorems via random-walk conjecturing under connectivity, plus a diversity-maximizing conjecturer using diffusion similarity from contrastive ...
-
AI for Mathematics: Progress, Challenges, and Prospects
AI for math combines task-specific architectures and general foundation models to support research and advance AI reasoning capabilities.
-
Shaping Schema via Language Representation as the Next Frontier for LLM Intelligence Expanding
Advanced language representations shape LLMs' schemas to improve knowledge activation and problem-solving.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.