Saved in:
Bibliographic Details
Main Authors: Requena, Borja, Letson, Austin, Nowakowski, Krystian, Beltran-Ferreiro, Izan, Sarra, Leopoldo
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.24273
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913128281800704
author Requena, Borja
Letson, Austin
Nowakowski, Krystian
Beltran-Ferreiro, Izan
Sarra, Leopoldo
author_facet Requena, Borja
Letson, Austin
Nowakowski, Krystian
Beltran-Ferreiro, Izan
Sarra, Leopoldo
contents 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 this agentic approach using qualitatively different benchmarks and compare various frontier language models and design choices. Our results show competitive performance compared to state-of-the-art approaches, while using a significantly simpler architecture and a fraction of their cost. Additionally, we 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_24273
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Minimal Agent for Automated Theorem Proving
Requena, Borja
Letson, Austin
Nowakowski, Krystian
Beltran-Ferreiro, Izan
Sarra, Leopoldo
Artificial Intelligence
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 this agentic approach using qualitatively different benchmarks and compare various frontier language models and design choices. Our results show competitive performance compared to state-of-the-art approaches, while using a significantly simpler architecture and a fraction of their cost. Additionally, we 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.
title A Minimal Agent for Automated Theorem Proving
topic Artificial Intelligence
url https://arxiv.org/abs/2602.24273