Towards Realistic Project-Level Code Generation via Multi-Agent Collaboration and Semantic Architecture Modeling

• URL: http://arxiv.org/abs/2511.03404v1
• Date: Wed, 05 Nov 2025 12:12:35 GMT
• Title: Towards Realistic Project-Level Code Generation via Multi-Agent Collaboration and Semantic Architecture Modeling
• Authors: Qianhui Zhao, Li Zhang, Fang Liu, Junhang Cheng, Chengru Wu, Junchen Ai, Qiaoyuanhe Meng, Lichen Zhang, Xiaoli Lian, Shubin Song, Yuanping Guo,
• Abstract summary: 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.
• Score: 7.753074942497876
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In recent years, Large Language Models (LLMs) have achieved remarkable progress in automated code generation. In real-world software engineering, the growing demand for rapid iteration and continuous delivery underscores the importance of project-level code generation, where LLMs are expected to generate complete software projects directly from complex user requirements. Although existing studies have made initial explorations, they still face key limitations, including unrealistic datasets and unreliable evaluation metrics that fail to reflect real-world complexity, the semantic gap between human-written requirements and machine-interpretable structures, and difficulties in managing hierarchical dependencies and maintaining quality throughout the generation process. To address these limitations, we first 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 on average, supplemented with documentation and executable test cases for automatic evaluation. We further propose ProjectGen, a multi-agent framework that decomposes projects into architecture design, skeleton generation, and code filling stages with iterative refinement and memory-based context management. Within this framework, we introduce the Semantic Software Architecture Tree (SSAT), a structured and semantically rich representation that effectively bridges user requirements and source code implementation. 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, a 57% improvement over the baseline approaches, and 310 test cases on CodeProjectEval, representing an improvement of roughly tenfold compared to the baselines.

Related papers

• 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)
• 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)
• ArchAgent: Scalable Legacy Software Architecture Recovery with LLMs [44.137226823695066]
  ArchAgent is a scalable agent-based framework that combines static analysis, adaptive code segmentation, and LLM-powered synthesis.<n>It reconstructs multiview, business-aligned architectures from cross-repositorys.<n>ArchAgent introduces scalable diagram generation with contextual pruning and integrates cross-repository data to identify business-critical modules.
  arXiv  Detail & Related papers  (2026-01-19T12:39:05Z)
• 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)
• Retrieval-Augmented Code Generation: A Survey with Focus on Repository-Level Approaches [6.740646039135986]
  Retrieval-Augmented Generation (RAG) has emerged as a powerful paradigm that integrates external retrieval mechanisms with LLMs.<n>We provide a comprehensive review of research on Retrieval-Augmented Code Generation (RACG), with an emphasis on repository-level approaches.<n>Our goal is to establish a unified analytical framework for understanding this rapidly evolving field and to inspire continued progress in AI-powered software engineering.
  arXiv  Detail & Related papers  (2025-10-06T15:20:03Z)
• LoCoBench: A Benchmark for Long-Context Large Language Models in Complex Software Engineering [85.58151741052616]
  LoCoBench is a benchmark specifically designed to evaluate long-context LLMs in realistic, complex software development scenarios.<n>Our benchmark provides 8,000 evaluation scenarios systematically generated across 10 programming languages.<n>LoCoBench introduces 8 task categories that capture essential long-context understanding capabilities.
  arXiv  Detail & Related papers  (2025-09-11T16:55:04Z)
• Dynamic Benchmark Construction for Evaluating Large Language Models on Real-World Codes [33.80591142965565]
  We present CODE2BENCH, a pipeline for dynamically constructing robust and contamination-resistant benchmarks from real-world GitHub repositories.<n>Specifically, CODE2BENCH introduces three key innovations: (1) Automated Dynamism, achieved through periodic ingestion of recent code to minimize training data contamination; (2) Scope Graph-based dependency analysis, which enables structured classification of functions into benchmark instances with controlled dependency levels; and (3) Property-Based Testing (PBT) for the automated synthesis of rigorous test suites.
  arXiv  Detail & Related papers  (2025-08-10T05:06:36Z)
• DesignCoder: Hierarchy-Aware and Self-Correcting UI Code Generation with Large Language Models [17.348284143568282]
  DesignCoder is a novel hierarchical-aware and self-correcting automated code generation framework.<n>We introduce UI Grouping Chains, which enhance MLLMs' capability to understand and predict complex nested UI hierarchies.<n>We also incorporate a self-correction mechanism to improve the model's ability to identify and rectify errors in the generated code.
  arXiv  Detail & Related papers  (2025-06-16T16:20:43Z)
• Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning [70.04746094652653]
  We introduce PaperCoder, a framework that transforms machine learning papers into functional code repositories.<n>PaperCoder operates in three stages: planning, designs the system architecture with diagrams, identifies file dependencies, and generates configuration files.<n>We then evaluate PaperCoder on generating code implementations from machine learning papers based on both model-based and human evaluations.
  arXiv  Detail & Related papers  (2025-04-24T01:57:01Z)
• Empowering AI to Generate Better AI Code: Guided Generation of Deep Learning Projects with LLMs [4.616570111453259]
  Large language models (LLMs) struggle with generating entire deep learning projects.<n>We propose a novel planning-guided code generation method, DLCodeGen, tailored for generating deep learning projects.
  arXiv  Detail & Related papers  (2025-04-21T13:09:25Z)
• Codev-Bench: How Do LLMs Understand Developer-Centric Code Completion? [60.84912551069379]
  We present the Code-Development Benchmark (Codev-Bench), a fine-grained, real-world, repository-level, and developer-centric evaluation framework. Codev-Agent is an agent-based system that automates repository crawling, constructs execution environments, extracts dynamic calling chains from existing unit tests, and generates new test samples to avoid data leakage.
  arXiv  Detail & Related papers  (2024-10-02T09:11:10Z)
• ComplexCodeEval: A Benchmark for Evaluating Large Code Models on More Complex Code [29.178248778212588]
  ComplexCodeEval is a benchmark designed to assess large language models (LLMs) in various development tasks. It includes 3,897 Java samples and 7,184 Python samples from high-star GitHub repositories.
  arXiv  Detail & Related papers  (2024-09-16T13:43:04Z)
• 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)

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.