Discover and Prove: An Open-source Agentic Framework for Hard Mode Automated Theorem Proving in Lean 4

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Chengwu, Yin, Yichun, Yuan, Ye, Xie, Jiaxuan, Li, Botao, Li, Siqi, Shen, Jianhao, Xu, Yan, Shang, Lifeng, Zhang, Ming
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917415940521984
author Liu, Chengwu
Yin, Yichun
Yuan, Ye
Xie, Jiaxuan
Li, Botao
Li, Siqi
Shen, Jianhao
Xu, Yan
Shang, Lifeng
Zhang, Ming
author_facet Liu, Chengwu
Yin, Yichun
Yuan, Ye
Xie, Jiaxuan
Li, Botao
Li, Siqi
Shen, Jianhao
Xu, Yan
Shang, Lifeng
Zhang, Ming
contents Most ATP benchmarks embed the final answer within the formal statement -- a convention we call "Easy Mode" -- a design that simplifies the task relative to what human competitors face and may lead to optimistic estimates of model capability. We call the stricter, more realistic setting "Hard Mode": the system must independently discover the answer before constructing a formal proof. To enable Hard Mode research, we make two contributions. First, we release MiniF2F-Hard and FIMO-Hard, expert-reannotated Hard Mode variants of two widely-used ATP benchmarks. Second, we introduce Discover And Prove (DAP), an agentic framework that uses LLM natural-language reasoning with explicit self-reflection to discover answers, then rewrites Hard Mode statements into Easy Mode ones for existing ATP provers. DAP sets the state of the art: on CombiBench it raises solved problems from 7 (previous SOTA, Pass@16) to 10; on PutnamBench it is the first system to formally prove 36 theorems in Hard Mode -- while simultaneously revealing that state-of-the-art LLMs exceed 80% answer accuracy on the same problems where formal provers manage under 10%, exposing a substantial gap that Hard Mode benchmarks are uniquely suited to measure.
format Preprint
id arxiv_https___arxiv_org_abs_2604_15839
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Discover and Prove: An Open-source Agentic Framework for Hard Mode Automated Theorem Proving in Lean 4
Liu, Chengwu
Yin, Yichun
Yuan, Ye
Xie, Jiaxuan
Li, Botao
Li, Siqi
Shen, Jianhao
Xu, Yan
Shang, Lifeng
Zhang, Ming
Artificial Intelligence
Computation and Language
Logic in Computer Science
Most ATP benchmarks embed the final answer within the formal statement -- a convention we call "Easy Mode" -- a design that simplifies the task relative to what human competitors face and may lead to optimistic estimates of model capability. We call the stricter, more realistic setting "Hard Mode": the system must independently discover the answer before constructing a formal proof. To enable Hard Mode research, we make two contributions. First, we release MiniF2F-Hard and FIMO-Hard, expert-reannotated Hard Mode variants of two widely-used ATP benchmarks. Second, we introduce Discover And Prove (DAP), an agentic framework that uses LLM natural-language reasoning with explicit self-reflection to discover answers, then rewrites Hard Mode statements into Easy Mode ones for existing ATP provers. DAP sets the state of the art: on CombiBench it raises solved problems from 7 (previous SOTA, Pass@16) to 10; on PutnamBench it is the first system to formally prove 36 theorems in Hard Mode -- while simultaneously revealing that state-of-the-art LLMs exceed 80% answer accuracy on the same problems where formal provers manage under 10%, exposing a substantial gap that Hard Mode benchmarks are uniquely suited to measure.
title Discover and Prove: An Open-source Agentic Framework for Hard Mode Automated Theorem Proving in Lean 4
topic Artificial Intelligence
Computation and Language
Logic in Computer Science
url https://arxiv.org/abs/2604.15839