EvoGraph: Hybrid Directed Graph Evolution toward Software 3.0

• URL: http://arxiv.org/abs/2508.05199v1
• Date: Thu, 07 Aug 2025 09:36:30 GMT
• Title: EvoGraph: Hybrid Directed Graph Evolution toward Software 3.0
• Abstract summary: We introduce **EvoGraph**, a framework that enables software systems to evolve their own source code, build pipelines, documentation, and tickets.<n>EvoGraph fixes 83% of known security vulnerabilities, translates to Java with 93% functional equivalence, and maintains documentation freshness within two minutes.<n>We extend our approach to **evoGraph**, leveraging language-specific SLMs for modernizing.NET, Lisp, CGI, ColdFusion, legacy Python, and Cs.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-sa/4.0/
• 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. On three benchmarks, EvoGraph fixes 83% of known security vulnerabilities, translates COBOL to Java with 93% functional equivalence (test verified), and maintains documentation freshness within two minutes. Experiments show a 40% latency reduction and a sevenfold drop in feature lead time compared with strong baselines. We extend our approach to **evoGraph**, leveraging language-specific SLMs for modernizing .NET, Lisp, CGI, ColdFusion, legacy Python, and C codebases, achieving 82-96% semantic equivalence across languages while reducing computational costs by 90% compared to large language models. EvoGraph's design responds to empirical failure modes in legacy modernization, such as implicit contracts, performance preservation, and integration evolution. Our results suggest a practical path toward Software 3.0, where systems adapt continuously yet remain under measurable control.

Related papers

• SE-GoS: Self-Evolving Graph-of-Skills for Skill Library at Scale [10.571709993050748]
  We present Self-Evolving Graph-of-Skills (SE-GoS), a training-free framework that evolves an existing GoS graph from execution traces.<n>We show that SE-GoS consistently improves task reward while reducing input tokens relative to full skill loading.
  arXiv  Detail & Related papers  (2026-09-08T04:20:11Z)
• EvoGUI: An Evolution-Aware Benchmark for GUI State-Transition Understanding [54.222234064832]
  EvoGUI is a framework that converts normalized GUI trajectories into three complementary visual question answering probes.<n>We instantiate EvoGUI-Bench from Mind2Web and WebLINX, yielding 3,000 instances across 120 domains.<n>The strongest model reaches only 60.4 EvoGain, while model scale and GUI specialization do not reliably predict performance.
  arXiv  Detail & Related papers  (2026-07-19T03:29:08Z)
• EvoOptiGraph: Weakness-Driven Coevolution via Graph-Based Structural Generation for Optimization Modeling [19.76518386029908]
  EvoOptiGraph is a framework where data and model co-evolve, driven by model weaknesses.<n>Training proceeds in two stages: supervised fine-tuning (SFT) on an initial dataset, followed by reinforcement learning with verifiable rewards (RLVR)<n>Results show that EvoOptiGraph significantly outperforms larger generalist models, agentic methods, and specialized baselines in accuracy, executability, and generalization.
  arXiv  Detail & Related papers  (2026-06-25T03:57:07Z)
• EvoForest: A Novel Machine-Learning Paradigm via Open-Ended Evolution of Computational Graphs [2.7010154811483162]
  We present EvoForest, a hybrid neuro-symbolic system for end-to-end open-ended evolution of computation.<n>Rather than merely generating features, EvoForest jointly evolves reusable computational structure, callable function families, and trainable low-dimensional continuous components.<n>For each graph configuration, EvoForest evaluates the discovered computation and uses a lightweight Ridge-based readout to score the resulting representation.
  arXiv  Detail & Related papers  (2026-03-26T00:07:45Z)
• KCoEvo: A Knowledge Graph Augmented Framework for Evolutionary Code Generation [25.38402999279553]
  We propose a knowledge graph-augmented framework that decomposes the migration task into two synergistic stages: evolution path retrieval and path-informed code generation.<n>Our approach constructs static and dynamic API graphs to model intra-version structures and cross-version transitions, enabling structured reasoning over API evolution.
  arXiv  Detail & Related papers  (2026-03-08T10:39:48Z)
• Leveraging LLMs to support co-evolution between definitions and instances of textual DSLs: A Systematic Evaluation [6.964708557733698]
  This study systematically evaluates the potential of large language models for co-evolving grammars and instances of textual DSLs.<n>Results show strong performance on small-scale cases, but performance degraded with scale.
  arXiv  Detail & Related papers  (2026-02-12T13:01:01Z)
• Semi-supervised Instruction Tuning for Large Language Models on Text-Attributed Graphs [62.544129365882014]
  We propose a novel Semi-supervised Instruction Tuning pipeline for Graph Learning, named SIT-Graph.<n> SIT-Graph is model-agnostic and can be seamlessly integrated into any graph instruction tuning method that utilizes LLMs as the predictor.<n>Extensive experiments demonstrate that when incorporated into state-of-the-art graph instruction tuning methods, SIT-Graph significantly enhances their performance on text-attributed graph benchmarks.
  arXiv  Detail & Related papers  (2026-01-19T08:10:53Z)
• VisCoder2: Building Multi-Language Visualization Coding Agents [63.63232038173407]
  We introduce three complementary resources for advancing visualization coding agents.<n>VisCoder2 significantly outperforms strong open-source baselines and approaches the performance of proprietary models.
  arXiv  Detail & Related papers  (2025-10-24T18:03:57Z)
• RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation [27.834864953082302]
  Repository Planning Graph (RPG) encodes capabilities, file structures, data flows, and functions in a unified graph.<n>ZeroRepo is a graph-driven framework that operates in three stages: proposal-level planning, implementation-level construction, and graph-guided code generation with test validation.
  arXiv  Detail & Related papers  (2025-09-19T17:58:14Z)
• KELPS: A Framework for Verified Multi-Language Autoformalization via Semantic-Syntactic Alignment [5.295540405828356]
  KELPS is an iterative framework for translating, synthesizing, and filtering informal data into formal languages.<n>First, we translate natural language into Knowledge Equations (KEs), a novel language that we designed, theoretically grounded in assertional logic.<n>Next, we convert them to target languages through rigorously defined rules that preserve both syntactic structure and semantic meaning.<n>This process yielded a parallel corpus of over 60,000 problems.
  arXiv  Detail & Related papers  (2025-07-11T15:05:06Z)
• RustEvo^2: An Evolving Benchmark for API Evolution in LLM-based Rust Code Generation [28.156862491709237]
  RustEvo is a framework for evaluating the ability of large language models to adapt to evolving Rust APIs.<n>It automates dataset creation by synthesizing 588 API changes into programming tasks mirroring real-world challenges.<n>Experiments on state-of-the-art (SOTA) LLMs reveal significant performance variations.
  arXiv  Detail & Related papers  (2025-03-21T07:33:59Z)
• RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph [63.87660059104077]
  We present RepoGraph, a plug-in module that manages a repository-level structure for modern AI software engineering solutions.<n>RepoGraph substantially boosts the performance of all systems, leading to a new state-of-the-art among open-source frameworks.
  arXiv  Detail & Related papers  (2024-10-03T05:45:26Z)
• Can Large Language Models Analyze Graphs like Professionals? A Benchmark, Datasets and Models [88.4320775961431]
  We introduce ProGraph, a benchmark for large language models (LLMs) to process graphs.<n>Our findings reveal that the performance of current LLMs is unsatisfactory, with the best model achieving only 36% accuracy.<n>We propose LLM4Graph datasets, which include crawled documents and auto-generated codes based on 6 widely used graph libraries.
  arXiv  Detail & Related papers  (2024-09-29T11:38:45Z)
• GraphEval36K: Benchmarking Coding and Reasoning Capabilities of Large Language Models on Graph Datasets [19.329274124787858]
  GraphEval36K is the first comprehensive graph dataset, comprising 40 graph coding problems and 36,900 test cases.<n>Our dataset is categorized into eight primary and four sub-categories to ensure a thorough evaluation across different types of graphs.<n>To improve the usability of our evaluation framework, we propose Structured Symbolic Decomposition (SSD)<n>SSD improves the average passing rate of GPT-4, GPT-4o, Gemini-Pro and Claude-3-Sonnet by 8.38%, 6.78%, 29.28% and 25.28%, respectively.
  arXiv  Detail & Related papers  (2024-06-23T18:01:56Z)
• Input Conditioned Graph Generation for Language Agents [31.2175071107555]
  We develop learnable and dynamic language agents using an existing framework that abstracts language agents as graphs. We learn to generate edges that represent the flow of communication based on the given input, thereby adjusting the internal communication of a language agent. Our approach surpasses the previous static approach by nearly 6% accuracy on a combined dataset of MMLU and CMMLU, and by more than 10% when trained with a sparsity-inducing loss.
  arXiv  Detail & Related papers  (2024-06-17T13:53:15Z)
• Can Language Models Solve Graph Problems in Natural Language? [51.28850846990929]
  Large language models (LLMs) are increasingly adopted for a variety of tasks with implicit graphical structures. We propose NLGraph, a benchmark of graph-based problem solving simulating in natural language.
  arXiv  Detail & Related papers  (2023-05-17T08:29:21Z)
• GraphMAE: Self-Supervised Masked Graph Autoencoders [52.06140191214428]
  We present a masked graph autoencoder GraphMAE that mitigates issues for generative self-supervised graph learning. We conduct extensive experiments on 21 public datasets for three different graph learning tasks. The results manifest that GraphMAE--a simple graph autoencoder with our careful designs--can consistently generate outperformance over both contrastive and generative state-of-the-art baselines.
  arXiv  Detail & Related papers  (2022-05-22T11:57:08Z)
• GRAPE for Fast and Scalable Graph Processing and random walk-based Embedding [0.5035217505850539]
  We present GRAPE, a software resource for graph processing and embedding. It can scale with big graphs by using specialized and smart data structures, algorithms, and a fast parallel implementation of random walk-based methods.
  arXiv  Detail & Related papers  (2021-10-12T17:49:46Z)
• GATE: Graph Attention Transformer Encoder for Cross-lingual Relation and Event Extraction [107.8262586956778]
  We introduce graph convolutional networks (GCNs) with universal dependency parses to learn language-agnostic sentence representations. GCNs struggle to model words with long-range dependencies or are not directly connected in the dependency tree. We propose to utilize the self-attention mechanism to learn the dependencies between words with different syntactic distances.
  arXiv  Detail & Related papers  (2020-10-06T20:30:35Z)
• Heuristic Semi-Supervised Learning for Graph Generation Inspired by Electoral College [80.67842220664231]
  We propose a novel pre-processing technique, namely ELectoral COllege (ELCO), which automatically expands new nodes and edges to refine the label similarity within a dense subgraph. In all setups tested, our method boosts the average score of base models by a large margin of 4.7 points, as well as consistently outperforms the state-of-the-art.
  arXiv  Detail & Related papers  (2020-06-10T14:48:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.