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

2026-04-10

AI Summary

This work addresses the trade-off between contextual fidelity and architectural stability arising from ambiguous user intents in intent-driven software engineering by proposing the Contract-Coding framework. The framework leverages autonomous symbolic grounding to map vague intents into formal language contracts, which serve as a single source of truth to enable topological decoupling among modules and support parallelized architecture synthesis. It achieves, for the first time, intent-driven architectural composition with guaranteed topological independence at repository scale. Evaluated on the Greenfield-5 benchmark, the approach significantly outperforms existing agents with a 47% functional success rate while maintaining near-perfect structural integrity.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Computer Vision: Visual Reasoning & Symbolic Representations

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work

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.

Problem

• intent-driven software engineering
• Context-Fidelity Trade-off
• repo-level code generation
• architectural collapse
• vague user intents

Innovation

• Contract-Coding
• Autonomous Symbolic Grounding
• Language Contract
• Architectural Parallelism
• Repository-Level Code Generation