大规模问题规约：代理集成计算难题
Problem Reductions at Scale: Agentic Integration of Computationally Hard Problems
- HKUST (GZ)（香港科技大学（广州））
- Institute of Science Tokyo（东京科学研究所）
- RIKEN AIP（理化学研究所AIP）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出通过代理工程实现大规模问题规约库，利用无代码贡献路线、多层验证栈和自动化流程，快速构建包含100多种问题类型和200多种规约规则的工具，实现问题与求解器的高效连接。
AI中文摘要：
解决NP难优化问题通常需要针对特定求解器重新公式化，如量子硬件、商业优化器或领域启发式方法。一个能够在多项式时间内进行硬问题之间规约的工具，可以让从业者通过单一接口将任何支持的问题路由到任何支持的求解器。然而，构建这样的库却一直难以实现。我们展示，通过设计约束、验证系统和反馈循环等 harness 工程实践，可以克服这一障碍。我们的 harness 包含无代码贡献路线供领域专家使用，多层验证栈从类型级检查到代理特征测试（AI代理扮演终端用户角色），以及完全自动化的实现-审查-集成流水线。大约三个月内，我们构建了一个命令行工具，其背后是一个包含100多种问题类型和200多种规约规则的库，超过170000行Rust代码。结果表明，经过良好工程设计的 harness 让代理能够以超出以往规约库努力的规模和速度构建经过良好测试的软件。由于规约图具有传递性，新注册的求解器对于任何单一问题类型立即可用，对于通过规约路径连接的所有问题。源代码可在https://github.com/CodingThrust/problem-reductions获取。
英文摘要：
Solving an NP-hard optimization problem often requires reformulating it for a specific solver -- quantum hardware, a commercial optimizer, or a domain heuristic. A tool for polynomial-time reductions between hard problems would let practitioners route any supported problem to any supported solver through a single interface. Building such a library at scale, however, has remained out of reach. We show that harness engineering, the practice of designing constraints, verification systems, and feedback loops that channel AI coding agents, can overcome this barrier. Our harness combines a no-code contribution route for domain experts, a multilayer verification stack ranging from type-level checks to agentic feature tests (AI agents role-playing as end users), and a fully automated implementation-review-integration pipeline. In about three months, we built a command-line tool backed by a library of 100+ problem types and 200+ reduction rules in over 170k lines of Rust. The result suggests that a well-engineered harness lets agents build well-tested software at a scale and pace beyond prior reduction-library efforts. Because the reduction graph composes transitively, a new solver registered for any single problem type instantly becomes available to every problem connected by a reduction path. The source code is available at https://github.com/CodingThrust/problem-reductions.
