# TraceDev: A Traceability-Driven Multi-agent Framework for Requirement-to-Code Development arXiv: https://arxiv.org/abs/2607.18886 ยท HTML: https://mlsanity.com/paper/2607.18886/ ## Key facts - Cited by 1 papers in the map (data through 14 Oct 2026). - Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. - Builds on 28 of its 68 references that are in the map. - First posted on arXiv 21 Jul 2026. ## Placed in - LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/) ## Builds on (most cited first, 28 of 28) - [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021) - [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025) - [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021) - [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022) - [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023) - [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024) - [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023) - [Large Language Models for Software Engineering: A Systematic Literature Review](https://mlsanity.com/paper/2308.10620/) (2023) - [CheckEval: A reliable LLM-as-a-Judge framework for evaluating text generation using checklists](https://mlsanity.com/paper/2403.18771/) (2024) - [A Survey on Large Language Models for Software Engineering](https://mlsanity.com/paper/2312.15223/) (2023) - [CodeTree: Agent-guided Tree Search for Code Generation with Large Language Models](https://mlsanity.com/paper/2411.04329/) (2024) - [Plan and Budget: Effective and Efficient Test-Time Scaling on Reasoning Large Language Models](https://mlsanity.com/paper/2505.16122/) (2025) - [Large Language Models for Code Generation: A Comprehensive Survey of Challenges, Techniques, Evaluation, and Applications](https://mlsanity.com/paper/2503.01245/) (2025) - [The Current Challenges of Software Engineering in the Era of Large Language Models](https://mlsanity.com/paper/2412.14554/) (2024) - [Traceability Transformed: Generating more Accurate Links with Pre-Trained BERT Models](https://mlsanity.com/paper/2102.04411/) (2021) - [RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation](https://mlsanity.com/paper/2509.16198/) (2025) - [Prompts Matter: Insights and Strategies for Prompt Engineering in Automated Software Traceability](https://mlsanity.com/paper/2308.00229/) (2023) - [Empowering Agile-Based Generative Software Development through Human-AI Teamwork](https://mlsanity.com/paper/2407.15568/) (2024) - [Deep Learning-based Software Engineering: Progress, Challenges, and Opportunities](https://mlsanity.com/paper/2410.13110/) (2024) - [Large Language Models (LLMs) for Requirements Engineering (RE): A Systematic Literature Review](https://mlsanity.com/paper/2509.11446/) (2025) - [Smaller but Better: Self-Paced Knowledge Distillation for Lightweight yet Effective LCMs](https://mlsanity.com/paper/2408.03680/) (2024) - [Towards Mitigating API Hallucination in Code Generated by LLMs with Hierarchical Dependency Aware](https://mlsanity.com/paper/2505.05057/) (2025) - [Natural Language Processing for Requirements Traceability](https://mlsanity.com/paper/2405.10845/) (2024) - [From Requirements to Code: Understanding Developer Practices in LLM-Assisted Software Engineering](https://mlsanity.com/paper/2507.07548/) (2025) - [Leveraging Historical Associations between Requirements and Source Code to Identify Impacted Classes](https://mlsanity.com/paper/1808.06359/) (2018) - [ARS: Adaptive Reasoning Suppression for Efficient Large Reasoning Language Models](https://mlsanity.com/paper/2510.00071/) (2025) - [Adopting Use Case Descriptions for Requirements Specification: an Industrial Case Study](https://mlsanity.com/paper/2506.13303/) (2025) - [UserTrace: User-Level Requirements Generation and Traceability Recovery from Software Project Repositories](https://mlsanity.com/paper/2509.11238/) (2025) ## Built on by (most cited first, 1 of 1) - [Don't Guess, Just Ask: Evaluating Interactive Requirement Clarification for Repository-Level Software Development](https://mlsanity.com/paper/2610.13022/) (2026) ## Abstract (arXiv) In modern software development, the rapid advancement of Large Language Models (LLMs) has made the end-to-end transformation of Natural Language Requirements (NLRs) into executable repository-level code increasingly feasible. However, existing approaches typically rely on simplified instructions (e.g., single-sentence descriptions), failing to reflect complex software development scenarios. Moreover, they lack explicit requirement traceability mechanisms, making it difficult to precisely align and validate generated code against original requirements. To address these limitations, we propose TraceDev, a multi-agent framework for automated software development grounded in use cases that contain multiple functional points and complex semantics. TraceDev employs five role-specific agents, including a Requirement Refiner, Designer, Developer, Tester, and Validator. Notably, the Validator Agent constructs and maintains a heterogeneous traceability graph that links requirements, design models, and code artifacts for interacting with the preceding four agents. The traceability graph maintains consistency across various artifacts and serves as a structured context for efficient memory management, supporting reliable repository-level code generation. We evaluate TraceDev on two widely used datasets (including 125 use cases) compared with two state-of-the-art approaches. On the ETOUR dataset, TraceDev achieves a success rate of 53.63%, outperforming baseline approaches by up to 186.63%. A similar trend is observed on the SMOS dataset, where TraceDev attains a success rate of 56.82%, exceeding baseline approaches by up to 340.80%. These results demonstrate the effectiveness of TraceDev in repository-level code generation from requirements.