A Minimal Agent for Automated Theorem Proving
This provides a systematic comparison tool for researchers in automated theorem proving, though it is incremental as it builds on existing state-of-the-art systems.
The authors tackled the problem of comparing AI-based theorem prover architectures by proposing a minimal agentic baseline that implements core features like iterative proof refinement, achieving competitive performance with simpler architecture and demonstrating advantages in sample efficiency and cost-effectiveness.
We propose a minimal agentic baseline that enables systematic comparison across different AI-based theorem prover architectures. This design implements the core features shared among state-of-the-art systems: iterative proof refinement, library search and context management. We evaluate our baseline using qualitatively different benchmarks and compare various popular models and design choices, and demonstrate competitive performance compared to state-of-the-art approaches, while using a significantly simpler architecture. Our results demonstrate consistent advantages of an iterative approach over multiple single-shot generations, especially in terms of sample efficiency and cost effectiveness. The implementation is released open-source as a candidate reference for future research and as an accessible prover for the community.