WiseSpec: Requirements-Driven Agents for Code Generation

arXiv:2609.00568v1 Announce Type: cross Abstract: Code generation aims to automatically generate source code from task requirements and has attracted significant attention with the rapid advancement of large language models (LLMs). Despite remarkable progress, LLMs often struggle to generate correct code for complex software engineering tasks because task descriptions are frequently incomplete, ambiguous, or lack critical contextual information. Existing approaches primarily improve the capabilities of coding agents through more sophisticated tools, skills, and workflows, while largely overlooking the quality of the task requirements themselves. To address this limitation, we draw inspiration from software requirements engineering and propose WiseSpec, a novel requirements-driven agent framework for repository-level code generation. WiseSpec automatically constructs structured and information-rich requirements, assesses their quality through execution-based evaluation, and iteratively refines them to better guide code generation. Experimental results show that WiseSpec consistently outperforms all baselines, achieving an average improvement of 13.17% in %Resolved.

Related

• Microskill Architecture: A Modular Skill-Driven Framework for AI-Native Code Generation
• Model-Driven Requirements Configuration with Three-Valued Uncertainty Scoring
• MACGen: Toward Functionally Correct and Secure Code Generation via Multi-Agent Collaboration
• AI Harness Engineering: A Runtime Substrate for Foundation-Model Software Agents
• Agentic Software Engineering: Foundational Pillars and a Research Roadmap

Source: arXiv cs.AI | 2026-09-02