Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.13100 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913032402108416 |
|---|---|
| author | Lin, Yi Zhao, Lujin Shi, Yijie |
| author_facet | Lin, Yi Zhao, Lujin Shi, Yijie |
| contents | The shift toward intent-driven software engineering (often termed "Vibe Coding") exposes a critical Context-Fidelity Trade-off: vague user intents overwhelm linear reasoning chains, leading to architectural collapse in complex repo-level generation. We propose Contract-Coding, a structured symbolic paradigm that bridges unstructured intent and executable code via Autonomous Symbolic Grounding. By projecting ambiguous intents into a formal Language Contract, our framework serves as a Single Source of Truth (SSOT) that enforces topological independence, effectively isolating inter-module implementation details, decreasing topological execution depth and unlocking Architectural Parallelism. Empirically, while state-of-the-art agents suffer from different hallucinations on the Greenfield-5 benchmark, Contract-Coding achieves 47\% functional success while maintaining near-perfect structural integrity. Our work marks a critical step towards repository-scale autonomous engineering: transitioning from strict "specification-following" to robust, intent-driven architecture synthesis. Our code is available at https://github.com/imliinyi/Contract-Coding. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_13100 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Contract-Coding: Towards Repo-Level Generation via Structured Symbolic Paradigm Lin, Yi Zhao, Lujin Shi, Yijie Software Engineering Artificial Intelligence The shift toward intent-driven software engineering (often termed "Vibe Coding") exposes a critical Context-Fidelity Trade-off: vague user intents overwhelm linear reasoning chains, leading to architectural collapse in complex repo-level generation. We propose Contract-Coding, a structured symbolic paradigm that bridges unstructured intent and executable code via Autonomous Symbolic Grounding. By projecting ambiguous intents into a formal Language Contract, our framework serves as a Single Source of Truth (SSOT) that enforces topological independence, effectively isolating inter-module implementation details, decreasing topological execution depth and unlocking Architectural Parallelism. Empirically, while state-of-the-art agents suffer from different hallucinations on the Greenfield-5 benchmark, Contract-Coding achieves 47\% functional success while maintaining near-perfect structural integrity. Our work marks a critical step towards repository-scale autonomous engineering: transitioning from strict "specification-following" to robust, intent-driven architecture synthesis. Our code is available at https://github.com/imliinyi/Contract-Coding. |
| title | Contract-Coding: Towards Repo-Level Generation via Structured Symbolic Paradigm |
| topic | Software Engineering Artificial Intelligence |
| url | https://arxiv.org/abs/2604.13100 |