Metraipolis › archive › dc_414cdef6bc27
PRAXIS: Graph-Grounded Tacit Knowledge for Domain Code Generation — arXiv:2608.19784
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.19784
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T11:49:45.818Z
- SHA-256 of the archived text
64120868d3f51ceeeca956c2fcacf8bbadefdba88f343be843752234844f31b1- Stable URL of this page
https://metraipolis.com/documento/dc_414cdef6bc27
How to cite
PRAXIS: Graph-Grounded Tacit Knowledge for Domain Code Generation — arXiv:2608.19784 — arXiv (en), https://arxiv.org/abs/2608.19784 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_414cdef6bc27 (Metraipolis archive dc_414cdef6bc27, sha256 64120868d3f51ceeeca956c2fcacf8bbadefdba88f343be843752234844f31b1)
BibTeX
@misc{dc414cdef6bc27,
title = {PRAXIS: Graph-Grounded Tacit Knowledge for Domain Code Generation — arXiv:2608.19784},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.19784},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_414cdef6bc27; sha256 64120868d3f51ceeeca956c2fcacf8bbadefdba88f343be843752234844f31b1},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.19784. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
LLM agents have achieved strong performance on general software engineering tasks, yet struggle with domain-specific code generation. We identify the root cause as the agent's lack of tacit knowledge, including domain-specific business rules, interface contracts, and operational conventions that developers internalize through practice but never document. This knowledge is deeply buried beneath the domain code, dispersed across code entities and their dependency relations, and invisible to the agent that lacks it. These properties make tacit knowledge inherently difficult to retrieve or learn. In this work, we propose PRAXIS, a framework that enables agents to systematically extract, represent, and reuse tacit knowledge for domain code generation. PRAXIS acquires tacit knowledge by simulating human development workflows within the target codebase, distills it into structured units organized on the code dependency graph, and proactively surfaces it to the agent at the point of code interaction. Extensive experiments demonstrate that PRAXIS outperforms state-of-the-art agents equipped with powerful agentic search capabilities, as well as experience-based and skill-based methods. The approach integrates seamlessly into various agent frameworks and LLMs with consistent performance improvements, and supports continual evolution with performance steadily scaling as practice accumulates. Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-08-21 in cs.SE). Categorie arXiv: Software Engineering (cs.SE). Pagina del lavoro: https://arxiv.org/abs/2608.19784 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-18T11:48:10.189Z dalla pagina https://arxiv.org/catchup/cs.SE/2026-08-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).