# OSFoundry: Building and Evolving Operating Systems with Specification-Guided Agents

arXiv: https://arxiv.org/abs/2609.25018 · HTML: https://mlsanity.com/paper/2609.25018/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 27 of its 53 references that are in the map.
- First posted on arXiv 8 Aug 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 27 of 27)

- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [Agentless: Demystifying LLM-based Software Engineering Agents](https://mlsanity.com/paper/2407.01489/) (2024)
- [CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges](https://mlsanity.com/paper/2401.07339/) (2024)
- [SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?](https://mlsanity.com/paper/2509.16941/) (2025)
- [AutoCodeRover: Autonomous Program Improvement](https://mlsanity.com/paper/2404.05427/) (2024)
- [RepairAgent: An Autonomous, LLM-Based Agent for Program Repair](https://mlsanity.com/paper/2403.17134/) (2024)
- [Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses](https://mlsanity.com/paper/2604.25850/) (2026)
- [Clover: Closed-Loop Verifiable Code Generation](https://mlsanity.com/paper/2310.17807/) (2023)
- [ProgramBench: Can Language Models Rebuild Programs From Scratch?](https://mlsanity.com/paper/2605.03546/) (2026)
- [SpecGen: Automated Generation of Formal Program Specifications via Large Language Models](https://mlsanity.com/paper/2401.08807/) (2024)
- [AutoVerus: Automated Proof Generation for Rust Code](https://mlsanity.com/paper/2409.13082/) (2024)
- [DeepSWE: Measuring Frontier Coding Agents on Original, Long-Horizon Engineering Tasks](https://mlsanity.com/paper/2607.07946/) (2026)
- [CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation](https://mlsanity.com/paper/2602.24286/) (2026)
- [AlphaVerus: Bootstrapping Formally Verified Code Generation through Self-Improving Translation and Treefinement](https://mlsanity.com/paper/2412.06176/) (2024)
- [Automated Proof Generation for Rust Code via Self-Evolution](https://mlsanity.com/paper/2410.15756/) (2024)
- [Code Researcher: Deep Research Agent for Large Systems Code and Commit History](https://mlsanity.com/paper/2506.11060/) (2025)
- [KernelGPT: Enhanced Kernel Fuzzing via Large Language Models](https://mlsanity.com/paper/2401.00563/) (2023)
- [Spec-Driven Development:From Code to Contract in the Age of AI Coding Assistants](https://mlsanity.com/paper/2602.00180/) (2026)
- [VeRO: A Harness for Agents to Optimize Agents](https://mlsanity.com/paper/2602.22480/) (2026)
- [SEC-bench Pro: Can Language Models Solve Long-Horizon Software Security Tasks?](https://mlsanity.com/paper/2605.26548/) (2026)
- [OSVBench: Benchmarking LLMs on Specification Generation Tasks for Operating System Verification](https://mlsanity.com/paper/2504.20964/) (2025)
- [kAgent: An execution-guided crash resolution agent for the Linux kernel](https://mlsanity.com/paper/2504.20412/) (2025)
- [QiMeng-Xpiler: Transcompiling Tensor Programs for Deep Learning Systems with a Neural-Symbolic Approach](https://mlsanity.com/paper/2505.02146/) (2025)
- [Sharpen the Spec, Cut the Code: A Case for Generative File System with SYSSPEC](https://mlsanity.com/paper/2512.13047/) (2025)
- [VibeServe: Can AI Agents Build Bespoke LLM Serving Systems?](https://mlsanity.com/paper/2605.06068/) (2026)
- [Taming System Complexity: Demystifying Software Engineering Agents in Diagnosing Linux Kernel Faults](https://mlsanity.com/paper/2505.19489/) (2025)
- [SpecDB: LLM-Generated Customized Databases via Feature-Oriented Decomposition](https://mlsanity.com/paper/2605.31097/) (2026)

## Abstract (arXiv)

Operating systems must evolve continuously. Yet their development remains code-centric and largely manual: even a localized change can require recovering implicit assumptions, coordinating multiple subsystems, and repeatedly building, booting, testing, and debugging the complete system. General-purpose coding agents automate individual edits, but their prompt-centric workflows repeatedly reconstruct task boundaries and OS semantics from scattered context, limiting their reliability for sustained OS evolution. This paper presents OSFoundry, an OS-specialized agent harness that makes design intent persistent throughout OS development. Its key insight is to separate stable intent from diverse implementation. Instead of relying on free-form natural-language prompts to convey design intent, OSFoundry uses SysSpec*, a shared development blueprint comprising a task-bounding Plan and an OS-specific Specification: the Plan bounds what a change should achieve, while the Specification records the interfaces, modular dependencies, and concurrency semantics that its implementation must preserve. Agents implement and validate code against this same blueprint, refining both SysSpec* and the implementation when execution or review exposes a mismatch. We evaluate OSFoundry along three ways. First, OSFoundry generates SpecOS from SysSpec*; the resulting complete OS boots and passes all 70 functional tests. Second, specification patches evolve SpecOS with a GUI and three performance optimizations that improve performance by up to 4.41x. Third, across 11 recent Linux-kernel bug-fix tasks, OSFoundry achieves 1.8x the accuracy of Codex using GPT-5.5. These results show that persistent specifications can shift OS construction and evolution from repeated manual kernel engineering toward specification-guided development.