EvoGraph: Hybrid Directed Graph Evolution Toward Software 3.0
EvoGraph is a new framework designed to enable software systems to autonomously evolve their source code and related artifacts. It utilizes a typed directed graph and specialized language models to address various software engineering challenges, achieving significant improvements in security and efficiency. The framework aims to pave the way for Software 3.0, where systems can adapt continuously while remaining under control.
- ▪EvoGraph fixes 83% of known security vulnerabilities and translates COBOL to Java with 93% functional equivalence.
- ▪The framework maintains documentation freshness within two minutes and reduces latency by 40%.
- ▪EvoGraph achieves 82-96% semantic equivalence across multiple programming languages while cutting computational costs by 90% compared to large language models.
Hacker News (Newest) files mainly under programming. We currently carry 5,306 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | arXiv.org |
| Canonical URL | https://arxiv.org/abs/2508.05199 |
| Publication time | Sat, 30 May 2026 04:06:13 +0000 |
| Retrieval time | 2026-05-30T04:11:57.314Z |
| Last seen | 2026-05-30T04:11:57.314Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | ly1AMuEjn768 |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Software Engineering arXiv:2508.05199 (cs) [Submitted on 7 Aug 2025] Title:EvoGraph: Hybrid Directed Graph Evolution toward Software 3.0 Authors:Igor Costa, Christopher Baran View a PDF of the paper titled EvoGraph: Hybrid Directed Graph Evolution toward Software 3.0, by Igor Costa and 1 other authors View PDF HTML (experimental) Abstract:We introduce **EvoGraph**, a framework that enables software systems to evolve their own source code, build pipelines, documentation, and tickets. EvoGraph represents every artefact in a typed directed graph, applies learned mutation operators driven by specialized small language models (SLMs), and selects survivors with a multi-objective fitness.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv.org.
Discussion
0 commentsMore from arXiv.org
