Problem
Research questions and friction points this paper is trying to address.
autonomous software development
LLM-based coding agents
continual improvement
high-level requirements
functional software systems
Harness-of-Harness: Multi-Day Autonomous Software Development with Continual Improvement
🤖 AI Summary
本文提出Harness-of-Harness框架，通过迭代规划-编码-测试循环，使基于LLM的编码代理能够持续改进软件开发，实现多日自主软件开发。
📝 Abstract
This paper studies autonomous software development, in which LLM-based coding agents transform high-level requirements into complete, functional, and usable software systems without human intervention. We introduce Harness-of-Harness (HoH), a framework that enables coding agents to continually improve software during autonomous development. HoH operates on existing coding-agent harnesses, and organizes their executions into iterative planning-coding-testing loops. To sustain improvement across loops, HoH balances repair with capability growth, scopes development into small and verifiable increments, separates implementation-time testing from independent evaluation, and constrains verifiable outputs rather than prescribing agent workflows. It progressively exposes deliverables, role-specific tools, and skills, encourages reuse rather than recreation, and maintains versioned project histories. On GameCraft-Bench, FrontierSWE, and ProgramBench, three harness-model pairs (Codex with GPT-5.5, OpenCode with DeepSeek-V4-Pro, and Pi with MiniMax-M3), HoH consistently outperforms the corresponding standalone harnesses, achieving an average relative gain of 52.25 percent and a maximum gain of 82.86 percent after three iterations. In a multi-day deployment with more than 70 iterations, HoH autonomously develops a first-person-shooter game, featuring a coherent storyline, fully implemented core mechanics, human-playable experience, polished visuals and integrated audio. Github: https://github.com/Flesymeb/HarnessOfHarness Project Page: https://flesymeb.github.io/HarnessOfHarness/
Innovation
Methods, ideas, or system contributions that make the work stand out.
Harness-of-Harness
autonomous software development
continual improvement
iterative planning-coding-testing loops
LLM-based coding agents
🔎 Similar Papers
No similar papers found.
