Contract-Coding: Towards Repo-Level Generation via Structured Symbolic Paradigm

TL;DR

Contract-Coding introduces a structured symbolic approach for repo-level code generation that improves intent understanding and architectural robustness, enabling scalable autonomous software engineering.

Contribution

It proposes a formal Language Contract paradigm that bridges ambiguous intents and code, enforcing modular independence and enhancing architectural parallelism.

Findings

Achieves 47% functional success on Greenfield-5 benchmark.

Reduces hallucinations compared to state-of-the-art agents.

Maintains near-perfect structural integrity in generated architectures.

Abstract

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.