Putnam 2025 Problems in Rocq using Opus 4.6 and Rocq-MCP

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Baudart, Guillaume, Lelarge, Marc, Stérin, Tristan, Viennot, Jules
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917518688387072
author Baudart, Guillaume
Lelarge, Marc
Stérin, Tristan
Viennot, Jules
author_facet Baudart, Guillaume
Lelarge, Marc
Stérin, Tristan
Viennot, Jules
contents We report on an experiment in which Claude Opus~4.6, equipped with a suite of Model Context Protocol (MCP) tools for the Rocq proof assistant, autonomously proved 10 of 12 problems from the 2025 Putnam Mathematical Competition. The MCP tools, designed with Claude by analyzing logs from a prior experiment on miniF2F-Rocq, encode a "compile-first, interactive-fallback" strategy. Running on an isolated VM with no internet access, the agent deployed 141 subagents over 17.7 hours of active compute (51.6h wall-clock), consuming approximately 1.9 billion tokens. All proofs are publicly available.
format Preprint
id arxiv_https___arxiv_org_abs_2603_20405
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Putnam 2025 Problems in Rocq using Opus 4.6 and Rocq-MCP
Baudart, Guillaume
Lelarge, Marc
Stérin, Tristan
Viennot, Jules
Machine Learning
Computation and Language
Logic in Computer Science
We report on an experiment in which Claude Opus~4.6, equipped with a suite of Model Context Protocol (MCP) tools for the Rocq proof assistant, autonomously proved 10 of 12 problems from the 2025 Putnam Mathematical Competition. The MCP tools, designed with Claude by analyzing logs from a prior experiment on miniF2F-Rocq, encode a "compile-first, interactive-fallback" strategy. Running on an isolated VM with no internet access, the agent deployed 141 subagents over 17.7 hours of active compute (51.6h wall-clock), consuming approximately 1.9 billion tokens. All proofs are publicly available.
title Putnam 2025 Problems in Rocq using Opus 4.6 and Rocq-MCP
topic Machine Learning
Computation and Language
Logic in Computer Science
url https://arxiv.org/abs/2603.20405