RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation

• URL: http://arxiv.org/abs/2509.16198v5
• Date: Mon, 20 Oct 2025 14:22:14 GMT
• Title: RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation
• Abstract summary: 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.
• Score: 27.834864953082302
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models excel at generating individual functions or single files of code, yet generating complete repositories from scratch remains a fundamental challenge. This capability is key to building coherent software systems from high-level specifications and realizing the full potential of automated code generation. The process requires planning at two levels: deciding what features and modules to build (proposal stage) and defining their implementation details (implementation stage). Current approaches rely on natural language planning, which often produces unclear specifications, misaligned components, and brittle designs due to its inherent ambiguity and lack of structure. To address these limitations, we introduce the Repository Planning Graph (RPG), a structured representation that encodes capabilities, file structures, data flows, and functions in a unified graph. By replacing free-form natural language with an explicit blueprint, RPG enables consistent long-horizon planning for repository generation. Building on RPG, we develop ZeroRepo, a graph-driven framework that operates in three stages: proposal-level planning, implementation-level construction, and graph-guided code generation with test validation. To evaluate, we construct RepoCraft, a benchmark of six real-world projects with 1,052 tasks. On RepoCraft, ZeroRepo produces nearly 36K Code Lines and 445K Code Tokens, on average 3.9$\times$ larger than the strongest baseline (Claude Code), and 68$\times$ larger than other baselines. It achieves 81.5% coverage and 69.7% test accuracy, improving over Claude Code by 27.3 and 35.8 points. Further analysis shows that RPG models complex dependencies, enables more sophisticated planning through near-linear scaling, and improves agent understanding of repositories, thus accelerating localization.

Related papers

• Repo0: Design-Driven Zero-to-All Code Generation [24.362494910000844]
  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.
  arXiv  Detail & Related papers  (2026-08-20T10:03:14Z)
• PlanningBench: Generating Scalable and Verifiable Planning Data for Evaluating and Training Large Language Models [52.48858778580074]
  Planning is a fundamental capability for large language models (LLMs)<n>PlanningBench is a framework for generating scalable, diverse, verifiable planning data for both evaluation and training.
  arXiv  Detail & Related papers  (2026-05-20T08:10:15Z)
• 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)
• Closing the Loop: Universal Repository Representation with RPG-Encoder [26.428468203770663]
  We propose RPG-Encoder, a framework that generalizes the Repository Planning Graph (RPG) into a unified representation.<n> RPG-Encoder closes the reasoning loop through three mechanisms.<n>It establishes state-of-the-art localization performance on SWE-bench Verified with 93.7% Acc@5 and exceeds the best baseline by over 10% in localization accuracy on SWE-bench Live Lite.
  arXiv  Detail & Related papers  (2026-02-02T13:30:00Z)
• ProjDevBench: Benchmarking AI Coding Agents on End-to-End Project Development [49.63491095660809]
  ProjDevBench is an end-to-end benchmark that provides project requirements to coding agents and evaluates the resulting repositories.<n>We curate 20 programming problems across 8 categories, covering both concept-oriented tasks and real-world application scenarios.<n>Our evaluation reports an overall acceptance rate of 27.38%: agents handle basic functionality but struggle with complex system design, time optimization, and resource management.
  arXiv  Detail & Related papers  (2026-02-02T05:17:23Z)
• Towards Realistic Project-Level Code Generation via Multi-Agent Collaboration and Semantic Architecture Modeling [7.753074942497876]
  We introduce CodeProjectEval, a project-level code generation dataset built from 18 real-world repositories with 12.7 files and 2,388.6 lines of code per task.<n>We propose ProjectGen, a multi-agent framework that decomposes projects into architecture design, skeleton generation, and code filling stages.<n>Experiments show that ProjectGen achieves state-of-the-art performance, passing 52/124 test cases on the small-scale project-level code generation dataset DevBench.
  arXiv  Detail & Related papers  (2025-11-05T12:12:35Z)
• CodeWiki: Evaluating AI's Ability to Generate Holistic Documentation for Large-Scale Codebases [7.75137961900221]
  We present bftextCodeWiki, a unified framework for automated repository-level documentation across seven programming languages.<n>CodeWiki introduces three key innovations: (i) hierarchical decomposition that preserves architectural context across multiple levels of granularity, (ii) recursive multi-agent processing with dynamic task delegation for scalable generation, and (iii) multi-modal synthesis that integrates textual descriptions with visual artifacts such as architecture diagrams and data-flow representations.<n>CodeWiki achieves a 68.79% quality score with proprietary models, outperforming the closed-source DeepWiki baseline (64.06%) by 4.73%
  arXiv  Detail & Related papers  (2025-10-28T13:52:46Z)
• 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)
• A Hierarchical and Evolvable Benchmark for Fine-Grained Code Instruction Following with Multi-Turn Feedback [30.446511584123492]
  Large language models (LLMs) have advanced significantly in code generation, yet their ability to follow complex programming instructions with layered and diverse constraints remains underexplored.<n>We introduce MultiCodeIF, a comprehensive benchmark designed to evaluate instruction-following in code generation across multiple dimensions.<n>We synthesize and evolve 2,021 code tasks sourced from 14 programming languages, supporting multi-turn evaluation through feedback-driven task variants.
  arXiv  Detail & Related papers  (2025-07-01T11:51:40Z)
• HDLxGraph: Bridging Large Language Models and HDL Repositories via HDL Graph Databases [57.51078142561683]
  Large Language Models (LLMs) have demonstrated their potential in hardware design tasks.<n>Yet, their performance in real-world, repository-level HDL projects with thousands or even tens of thousands of code lines is hindered.<n>We propose HDLxGraph, a novel framework that integrates Graph Retrieval Augmented Generation (Graph RAG) with LLMs.
  arXiv  Detail & Related papers  (2025-05-21T16:14:10Z)
• Code-Driven Planning in Grid Worlds with Large Language Models [2.6080756513915824]
  We propose an iterative programmatic planning framework for solving grid-based tasks by synthesizing interpretable agent policies expressed in code.<n>Instead of relying on traditional search or reinforcement learning, our approach uses code generation as policy synthesis.
  arXiv  Detail & Related papers  (2025-05-15T23:23:31Z)
• LocAgent: Graph-Guided LLM Agents for Code Localization [25.395102705800916]
  LocAgent is a framework that addresses code localization through graph-based representation.<n>Our method with the fine-tuned Qwen-2.5-Coder-Instruct-32B model achieves comparable results to SOTA proprietary models at greatly reduced cost.
  arXiv  Detail & Related papers  (2025-03-12T05:55:01Z)
• Plan-over-Graph: Towards Parallelable LLM Agent Schedule [53.834646147919436]
  Large Language Models (LLMs) have demonstrated exceptional abilities in reasoning for task planning.<n>This paper introduces a novel paradigm, plan-over-graph, in which the model first decomposes a real-life textual task into executable subtasks and constructs an abstract task graph.<n>The model then understands this task graph as input and generates a plan for parallel execution.
  arXiv  Detail & Related papers  (2025-02-20T13:47:51Z)
• Unlocking Reasoning Potential in Large Langauge Models by Scaling Code-form Planning [94.76546523689113]
  We introduce CodePlan, a framework that generates and follows textcode-form plans -- pseudocode that outlines high-level, structured reasoning processes. CodePlan effectively captures the rich semantics and control flows inherent to sophisticated reasoning tasks. It achieves a 25.1% relative improvement compared with directly generating responses.
  arXiv  Detail & Related papers  (2024-09-19T04:13:58Z)
• CodeRAG-Bench: Can Retrieval Augment Code Generation? [78.37076502395699]
  We conduct a systematic, large-scale analysis of code generation using retrieval-augmented generation.<n>We first curate a comprehensive evaluation benchmark, CodeRAG-Bench, encompassing three categories of code generation tasks.<n>We examine top-performing models on CodeRAG-Bench by providing contexts retrieved from one or multiple sources.
  arXiv  Detail & Related papers  (2024-06-20T16:59:52Z)
• On the Impacts of Contexts on Repository-Level Code Generation [5.641402231731082]
  We present RepoExec, a novel benchmark designed to evaluate repository-level code generation.<n>We focus on three key aspects: executability, functional correctness through comprehensive test case generation, and accurate utilization of cross-file contexts.
  arXiv  Detail & Related papers  (2024-06-17T10:45:22Z)
• CodeGRAG: Bridging the Gap between Natural Language and Programming Language via Graphical Retrieval Augmented Generation [58.84212778960507]
  CodeGRAG builds the graphical view of code blocks based on the control flow and data flow of them to better interpret the programming domain knowledge.<n>CodeGRAG significantly improves the code generation ability of LLMs and can even offer performance gain for cross-lingual code generation.
  arXiv  Detail & Related papers  (2024-05-03T02:48:55Z)
• ML-Bench: Evaluating Large Language Models and Agents for Machine Learning Tasks on Repository-Level Code [76.84199699772903]
  ML-Bench is a benchmark rooted in real-world programming applications that leverage existing code repositories to perform tasks. To evaluate both Large Language Models (LLMs) and AI agents, two setups are employed: ML-LLM-Bench for assessing LLMs' text-to-code conversion within a predefined deployment environment, and ML-Agent-Bench for testing autonomous agents in an end-to-end task execution within a Linux sandbox environment.
  arXiv  Detail & Related papers  (2023-11-16T12:03:21Z)
• Octopus: Embodied Vision-Language Programmer from Environmental Feedback [58.04529328728999]
  Embodied vision-language models (VLMs) have achieved substantial progress in multimodal perception and reasoning. To bridge this gap, we introduce Octopus, an embodied vision-language programmer that uses executable code generation as a medium to connect planning and manipulation. Octopus is designed to 1) proficiently comprehend an agent's visual and textual task objectives, 2) formulate intricate action sequences, and 3) generate executable code.
  arXiv  Detail & Related papers  (2023-10-12T17:59:58Z)
• Self-planning Code Generation with Large Language Models [54.41645432114179]
  This paper proposes a self-planning code generation approach with large language models.<n>In the planning phase, the model outlines concise and formatted planning steps from the intent.<n>In the implementation phase, the model generates code step by step, guided by the preceding planning steps.
  arXiv  Detail & Related papers  (2023-03-12T15:36:03Z)

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.