LLM-Assisted Repository-Level Generation with Structured Spec-Driven Engineering

• URL: http://arxiv.org/abs/2605.02455v1
• Date: Mon, 04 May 2026 10:58:22 GMT
• Title: LLM-Assisted Repository-Level Generation with Structured Spec-Driven Engineering
• Abstract summary: State-of-the-art Large Language Models (LLMs) excel in code generation at the function level, but output quality significantly declines when scaling to repository-level systems.<n>To address this, we propose structured spec-driven engineering (SSDE)<n>We argue that structured specifications as LLM inputs make high-quality, repository-level code generation a tangible goal, while at the same time offering superior verifiability.
• Score: 4.751657370831477
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: State-of-the-art Large Language Models (LLMs) excel in code generation at the function level. However, the output quality significantly declines when scaling to repository-level systems. Current workflows relying only on natural language prompts suffer from inherent ambiguity and a lack of verifiability. To address this, we propose structured spec-driven engineering (SSDE), a paradigm that leverages structured artifacts to guide LLM generation. We argue that structured specifications as LLM inputs make high-quality, repository-level code generation a tangible goal, while at the same time offering superior verifiability, leading to significant potential for improvement. We first investigate the feasibility of this vision through a pilot study generating Model-View-Controller (MVC) business logic for three software systems using five LLMs, and then highlight the potential, challenges, and future roadmap for SSDE.

Related papers

• LLM-enabled Behavior Driven Development Workflow for Formally Verified Hardware Designs [6.993866597392993]
  Controlled Natural Language (CNL) specifications can serve as a middle-ground, reducing ambiguity while retaining interpretability.<n>We introduce and define Formal Verification Gherkin Scenarios (FV Gherkin Scenarios), unlocking CNL specifications as the foundation for formally verified hardware designs.
  arXiv  Detail & Related papers  (2026-09-14T10:08:48Z)
• RealBench: A Repo-Level Code Generation Benchmark Aligned with Real-World Software Development Practices [54.956760584923295]
  Researchers have made substantial progress using Large Language Models (LLMs) for code generation.<n>However, developers typically write code based on structured designs or specifications rather than raw natural language descriptions.<n>This gap between existing benchmarks and real industry development practices means that current benchmark scores may not accurately reflect how much code generation can help automate development tasks.
  arXiv  Detail & Related papers  (2026-04-24T15:35:54Z)
• Code Fingerprints: Disentangled Attribution of LLM-Generated Code [7.515488307576106]
  We study the problem of model-level code attribution, which aims to determine the source LLM responsible for generated code.<n>We propose the Disentangled Code Attribution Network (DCAN), which separates Source-Agnostic semantic information from Source-Specific stylistic representations.<n>We construct the first large-scale benchmark dataset comprising code generated by four widely used Large Language Models (LLMs) across four programming languages.
  arXiv  Detail & Related papers  (2026-03-04T15:58:36Z)
• Beyond Basic Specifications? A Systematic Study of Logical Constructs in LLM-based Specification Generation [29.231420590756954]
  Large language models (LLMs) for the automatic generation of program specifications has emerged as a promising avenue for enhancing verification efficiency.<n>We propose incorporating logical constructs into existing LLM-based specification generation framework.<n>We conduct an empirical study aimed at exploring the impact of various types of syntactic constructs on specification generation framework.
  arXiv  Detail & Related papers  (2026-01-31T13:19:40Z)
• Evaluating and Achieving Controllable Code Completion in Code LLM [89.64782747840225]
  We present the first instruction-guided code completion benchmark, Controllable Code Completion Benchmark (C3-Bench)<n>We reveal substantial gaps in instruction-following capabilities between open-source and advanced proprietary models during code completion tasks.<n>The resulting model, Qwen2.5-Coder-C3, achieves state-of-the-art performance on C3-Bench.
  arXiv  Detail & Related papers  (2026-01-22T11:40:04Z)
• How Effective are Generative Large Language Models in Performing Requirements Classification? [4.429729688079712]
  This study explores the effectiveness of three generative large language models (LLMs) performing both binary and multi-class requirements classification.<n>Our study concludes that while factors like prompt design and LLM architecture are universally important, others-such as dataset variations-have a more situational impact, depending on the complexity of the classification task.
  arXiv  Detail & Related papers  (2025-04-23T14:41:11Z)
• CodeIF: Benchmarking the Instruction-Following Capabilities of Large Language Models for Code Generation [20.013757490442064]
  We introduce CodeIF, the first benchmark designed to assess the abilities of Large Language Models (LLMs) to adhere to task-oriented instructions.<n>CodeIF encompasses a broad range of tasks, including function synthesis, algorithmic instructions, and code explanation.<n>We conduct extensive experiments with LLMs, analyzing their strengths and limitations in meeting the demands of these tasks.
  arXiv  Detail & Related papers  (2025-02-26T14:19:49Z)
• Exploring Code Language Models for Automated HLS-based Hardware Generation: Benchmark, Infrastructure and Analysis [14.458529723566379]
  Large language models (LLMs) can be employed for programming languages such as Python and C++.<n>This paper explores leveraging LLMs to generate High-Level Synthesis (HLS)-based hardware design.
  arXiv  Detail & Related papers  (2025-02-19T17:53:59Z)
• SynerGen-VL: Towards Synergistic Image Understanding and Generation with Vision Experts and Token Folding [66.74446220401296]
  We propose SynerGen-VL, a simple yet powerful encoder-free MLLM capable of both image understanding and generation.<n>We introduce the token folding mechanism and the vision-expert-based progressive alignment pretraining strategy, which effectively support high-resolution image understanding.<n>Our code and models shall be released.
  arXiv  Detail & Related papers  (2024-12-12T18:59:26Z)
• HiVeGen -- Hierarchical LLM-based Verilog Generation for Scalable Chip Design [24.46771930751068]
  HiVeGen is a hierarchical Verilog generation framework that decomposes generation tasks into hierarchical submodules.<n> automatic Design Space Exploration (DSE) into hierarchy-aware prompt generation, introducing weight-based retrieval to enhance code reuse.<n>Real-time human-computer interaction to lower error-correction cost, significantly improving the quality of generated designs.
  arXiv  Detail & Related papers  (2024-12-06T19:37:53Z)
• FVEval: Understanding Language Model Capabilities in Formal Verification of Digital Hardware [4.480157114854711]
  We present FVEval, the first comprehensive benchmark for characterizing large language models (LLMs) performance in tasks pertaining to formal verification (FV) The benchmark consists of three sub-tasks that measure LLM capabilities at different levels. We present both collections of expert-written verification collateral and methodologies to scalably generate synthetic examples aligned with FV.
  arXiv  Detail & Related papers  (2024-10-15T21:48:57Z)
• Q*: Improving Multi-step Reasoning for LLMs with Deliberative Planning [53.6472920229013]
  Large Language Models (LLMs) have demonstrated impressive capability in many natural language tasks. LLMs are prone to produce errors, hallucinations and inconsistent statements when performing multi-step reasoning. We introduce Q*, a framework for guiding LLMs decoding process with deliberative planning.
  arXiv  Detail & Related papers  (2024-06-20T13:08:09Z)
• Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More? [54.667202878390526]
  Long-context language models (LCLMs) have the potential to revolutionize our approach to tasks traditionally reliant on external tools like retrieval systems or databases. We introduce LOFT, a benchmark of real-world tasks requiring context up to millions of tokens designed to evaluate LCLMs' performance on in-context retrieval and reasoning. Our findings reveal LCLMs' surprising ability to rival state-of-the-art retrieval and RAG systems, despite never having been explicitly trained for these tasks.
  arXiv  Detail & Related papers  (2024-06-19T00:28:58Z)
• If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agents [81.60906807941188]
  Large language models (LLMs) are trained on a combination of natural language and formal language (code) Code translates high-level goals into executable steps, featuring standard syntax, logical consistency, abstraction, and modularity.
  arXiv  Detail & Related papers  (2024-01-01T16:51:20Z)
• 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.