Products

Isabelle Pool Server 发布:面向定理证明训练的池化验证服务

Isabelle Pool Server: a pooled verification service for prover training and multi-agent proving

Why we picked it

做定理证明训练或多智能体证明的朋友可以看看这个:一个预热会话池化的 Isabelle 验证服务,单机 32 并发能跑到单 worker 的 24 倍,8 worker 时比 PIDE MCP 还快,Python 客户端和 MCP 服务器都配好了,直接拉容器就能接进你的训练管线。

Isabelle Pool Server(IPS)是一个通过 HTTP API 提供的池化验证服务,内部维护一组预热的无头 Isabelle 会话,支持会话租借与回收、内存感知的准入控制和每次调用的时限约束。验证接口覆盖单步执行、块级证明检查和整理论构建三种粒度,并提供检查点机制用于低成本分支与回溯,从头构建则作为最终裁决。

Body

服务以单个容器运行并带监控,可通过 Python 客户端、两个 MCP 服务器和原生 HTTP API 访问。实测在单 worker 时与 PIDE MCP 持平,8 个 worker 时超越后者(对照其 2026 年 10 月的提交版本,该工具现已更名 PIDE AI)。会话就绪后,IPS 在单台主机上可扩展到 32 个并发 worker,达到单 worker 速率的 24 倍;内存紧张时会拒绝新会话而不是丢弃已有会话。

对做 prover 训练或多智能体证明的研究团队来说,稳定的并发验证吞吐直接决定强化学习循环和数据生成效率,IPS 以自由软件形式在 GitHub 公开,可作为这类训练管线的基础设施组件。

Original · arXiv cs.AI

Isabelle Pool Server: a pooled verification service for prover training and multi-agent proving

Isabelle Pool Server (IPS), a verification service with a pool of warm headless Isabelle sessions behind an HTTP API, with session leasing and reclamation, memory-aware admission control, and a time budget on every call. Its verification interface spans single-step execution, block-level proof checking and whole-theory builds, with checkpoints for cheap branching and backtracking, and a build from scratch as the final arbiter. The service runs as a single container with monitoring and is accessible via a Python client, two MCP servers and a raw HTTP API. In our measurements IPS is level with PIDE MCP, a PIDE frontend for agents, at one worker and ahead of it at eight, at its commit of October 2026 (the tool is now PIDE AI). Once its sessions are up it scales to 32 concurrent workers on one host at 24 times the single-worker rate, and under memory pressure it refuses new sessions rather than losing existing ones. IPS is free software and publicly available at https://github.com/Deep-LCF/Isabelle-Pool-Server

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Products" desk. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Isabelle, MCP and tools, theorem proving, multi-agent systems.

Source attribution: curated from arXiv cs.AI (@Xuanwei Ren, Wenda Li).