BODHI: Precise OS Kernel Specification Inference
Researchers propose BODHI, a domain-knowledge prompting method that significantly improves LLM performance in generating formal OS kernel specifications. On the OSV-Bench benchmark, BODHI with Claude Opus 4.6 achieves 96.73% Pass@1, substantially surpassing previous best results.
Article intelligence
Key points
- BODHI augments few-shot prompts with a structured C-to-Python translation guide covering 15 domain-specific patterns.
- It improves Pass@1 from 55.10% to 96.73% on OSV-Bench with 245 tasks.
- The method works across 9 models from 6 providers, with gains of 11% to 32%.
Why it matters
This matters because BODHI augments few-shot prompts with a structured C-to-Python translation guide covering 15 domain-specific patterns.
Technical impact
May affect model selection, inference cost, product capability, and evaluation benchmarks.
[2605.23931] BODHI: Precise OS Kernel Specification Inference
[Submitted on 22 Apr 2026]
Title:BODHI: Precise OS Kernel Specification Inference
View a PDF of the paper titled BODHI: Precise OS Kernel Specification Inference, by Zhiming Chang and 1 other authors
View PDF HTML (experimental)
Abstract:The formal verification of operating system kernels requires precise specifications that capture the intended behavior of system calls. Writing these specifications manually demands deep domain expertise, motivating the use of large language models (LLMs) to automate the process. However, in OSV-Bench, a benchmark of 245 specification generation tasks derived from the Hyperkernel OS kernel, the best reported Pass@1 is 55.10%. We propose a domain knowledge prompting method (BODHI), which augments the standard few-shot prompt with a structured C-to-Python translation guide covering 15 categories of domain-specific translation patterns. Inspired by Structured Chain-of-Thought (SCoT) prompting, the guide organizes translation by separation of concerns, addressing pre-condition extraction and post-condition generation as distinct categories. Evaluated on nine models from six providers (Anthropic, Mistral, Amazon, DeepSeek, Meta, Alibaba), covering dense, mixture-of-experts and reasoning architectures, BODHI improves every model tested, with gains ranging from +11% to +32%. The best configuration (Claude Opus 4.6 + BODHI) reaches 96.73% Pass@1. BODHI reduces both syntax and semantic errors, with the strongest effect on models that have sufficient instruction-following capability to utilize structured reference material. These results demonstrate that domain knowledge injection is a model-agnostic technique that substantially bridges the gap between general-purpose code generation and formal specification synthesis.
Subjects:
Artificial Intelligence (cs.AI); Programming Languages (cs.PL); Software Engineering (cs.SE)
Cite as: arXiv:2605.23931 [cs.AI]
(or arXiv:2605.23931v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2605.23931
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Ziyang Li [view email] [v1] Wed, 22 Apr 2026 19:29:16 UTC (31 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled BODHI: Precise OS Kernel Specification Inference, by Zhiming Chang and 1 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.AI
new | recent | 2026-05
Change to browse by:
cs cs.PL cs.SE
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)