Repo0: Design-Driven Zero-to-All Code Generation

• URL: http://arxiv.org/abs/2608.19854v1
• Date: Thu, 20 Aug 2026 10:03:14 GMT
• Title: Repo0: Design-Driven Zero-to-All Code Generation
• Abstract summary: Repo0 is a continuous structural evolution framework for zero-to-all code generation.<n>We evaluate Repo0 on six real-world repositories from RepoCraft using GPT-5 mini and DeepSeek V3.2.
• Score: 24.362494910000844
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language model agents have made substantial progress in code generation, yet most existing systems assume a predefined repository architecture. This assumption does not hold in zero-to-all code generation, where an agent must construct an entire software project directly from natural-language requirements while maintaining a modular repository architecture throughout development. We present Repo0, a continuous structural evolution framework for zero-to-all code generation. Repo0 maintains an explicit architectural state instantiated as a Dual-Directed-Acyclic-Graph (Dual-DAG), consisting of a requirement-level DAG, a component-level DAG, and their alignment relation. Starting from natural-language requirements, it iteratively evolves component boundaries through structural actions guided by modularity metrics until structural convergence, after which the converged architecture guides test-driven development code generation. We evaluate Repo0 on six real-world repositories from RepoCraft using GPT-5 mini and DeepSeek V3.2. Repo0 achieves the highest Functionality Coverage and Pass Rate across all settings. Compared with RPG, the strongest repository-planning baseline, Repo0 improves Functionality Coverage by up to 20.08 percentage points and Pass Rate by up to 29.74 percentage points. Ablation and structural-evolution analyses further demonstrate the importance of the Dual-DAG architectural state, modularity-guided structural evolution, and explicit structural convergence.

Related papers

• CodeSpec: Dual Executable Specifications for Agentic Long-Horizon Feature Development [7.386271204083454]
  We propose CodeSpec, a dual executable specification method for repository-level feature development.<n>It builds reliable functional chains from evidence pairing sub-requirement semantics with repository architectures.<n>On FeatureBench, which targets feature development in existing repositories, CodeSpec achieves 70.7%, 55.0%, and 49.9% pass rates.
  arXiv  Detail & Related papers  (2026-07-29T11:20:49Z)
• Agentic Designer: Progressive Multi-Agent Collaboration for Structure-Aware Interior Layout Generation [84.5255199507027]
  Agentic Designer is a progressive framework that formulates structure-aware interior layout generation as an iterative and constraint-verified decision process.<n>By layout decomposing into modular stages of proposal, verification, synthesis and adjustment, the framework coordinates three specialized agents, a Generator, an Evaluator, and a Refiner.<n>This mechanism enforces stepwise geometric validation and correction before each placement is committed, thereby preventing error accumulation.
  arXiv  Detail & Related papers  (2026-07-23T02:46:11Z)
• GRACE-RAG: Governed Retrieval Architecture for Canonical Evidence Synthesis, Enabling Lightweight Deployment in Closed-Domain Institutional Settings [2.084969478024457]
  This paper introduces GRACE-RAG, a retrieval-governed, graph-augmented RAG architecture that externalizes structural reasoning from the generative stage to a structured retrieval layer.<n> Experiments show consistent improvements in completeness, depth, and anticipatory coverage, with overall quality gains of up to 20% under mid-scale models.
  arXiv  Detail & Related papers  (2026-05-08T12:53:53Z)
• Understanding by Reconstruction: Reversing the Software Development Process for LLM Pretraining [66.89012795621349]
  Large Language Models (LLMs) often struggle with the deep, long-horizon reasoning required for complex software engineering.<n>We propose a novel paradigm: understanding via reconstruction.<n>We introduce a framework that synthesizes latent agentic trajectories using a multi-agent simulation.
  arXiv  Detail & Related papers  (2026-03-11T09:23:20Z)
• Architecture-Aware Multi-Design Generation for Repository-Level Feature Addition [53.50448142467294]
  RAIM is a multi-design and architecture-aware framework for repository-level feature addition.<n>It shifts away from linear patching by generating multiple diverse implementation designs.<n>Experiments on the NoCode-bench Verified dataset demonstrate that RAIM establishes a new state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-03-02T12:50:40Z)
• ReusStdFlow: A Standardized Reusability Framework for Dynamic Workflow Construction in Agentic AI [11.130786494338876]
  ReusStdFlow is a framework centered on a novel Extraction-Construction'' paradigm.<n>It employs a dual knowledge architecture-integrating graph and vector databases-to facilitate retrieval of both topological structures and functional semantics.<n>Tested on 200 real-world n8n, the system achieves over 90% accuracy in both extraction and construction.
  arXiv  Detail & Related papers  (2026-02-16T16:56:53Z)
• ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development [72.4729759618632]
  We introduce ABC-Bench, a benchmark to evaluate agentic backend coding within a realistic, executable workflow.<n>We curated 224 practical tasks spanning 8 languages and 19 frameworks from open-source repositories.<n>Our evaluation reveals that even state-of-the-art models struggle to deliver reliable performance on these holistic tasks.
  arXiv  Detail & Related papers  (2026-01-16T08:23:52Z)
• NL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding Agents [79.29376673236142]
  Existing benchmarks fail to rigorously evaluate the long-horizon capabilities required to build complete software systems.<n>We present NL2Repo Bench, a benchmark explicitly designed to evaluate the long-horizon repository generation ability of coding agents.
  arXiv  Detail & Related papers  (2025-12-14T15:12:13Z)
• Completion by Comprehension: Guiding Code Generation with Multi-Granularity Understanding [37.78627994991325]
  CoCo is a novel framework that enables code Completion by of multi-granularity context from large-scale code repositories.<n>Experiments on CrossCodeEval and RepoEval benchmarks demonstrate that CoCo consistently surpasses state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-12-04T07:37:59Z)
• 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)
• Loong: Synthesize Long Chain-of-Thoughts at Scale through Verifiers [103.4410890572479]
  We introduce the Loong Project: an open-source framework for scalable synthetic data generation and verification.<n>LoongBench is a curated seed dataset containing 8,729 human-vetted examples across 12 domains.<n>LoongEnv is a modular synthetic data generation environment that supports multiple prompting strategies to produce new question-answer-code triples.
  arXiv  Detail & Related papers  (2025-09-03T06:42:40Z)

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.