Lune

ACL Findings2026

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

Yi Lin, Lujin Zhao, Yijie Shi

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 "specificationfollowing" to robust, intent-driven architecture synthesis. Our code is available at https:// github.com/imliinyi/Contract-Coding.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Reflexion: language agents with verbal reinforcement learning cites Toolformer: Language Models Can Teach Themselves to Use Tools
  • Reflexion: language agents with verbal reinforcement learning cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering cites SWE-bench: Can Language Models Resolve Real-world Github Issues?
  • SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering cites Reflexion: language agents with verbal reinforcement learning
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on20

  1. Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
  2. Toolformer: Language Models Can Teach Themselves to Use ToolsTimo Schick, Jane Dwivedi-Yu, Roberto Dessì, Roberta Raileanu et al.NeurIPS 2023 · 5,989 citations
  3. Reflexion: language agents with verbal reinforcement learningNoah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan et al.NeurIPS 2023 · 5,828 citations
  4. SWE-bench: Can Language Models Resolve Real-world Github Issues?Carlos E. Jimenez, John Yang, Alexander Wettig, Shunyu Yao et al.ICLR 2024 · 2,082 citations
  5. SWE-agent: Agent-Computer Interfaces Enable Automated Software EngineeringJohn Yang, Carlos E. Jimenez, Alexander Wettig, Kilian Lieret et al.NeurIPS 2024 · 2,059 citations

Related papers

  1. ContractEval: A Benchmark for Evaluating Contract-Satisfying Assertions in Code GenerationSoohan Lim, Joonghyuk Hahn, Hyunwoo Park, Sang-Ki Ko et al.ACL Findings 2026
  2. Is Vibe Coding Safe? Benchmarking Vulnerability of Agent-Generated Code in Real-World TasksSongwen Zhao, Danqing Wang, Kexun Zhang, Jiaxuan Luo et al.ICML 2026 · 22 citations
  3. Building Software by Rolling the Dice: A Qualitative Study of Vibe CodingYi-Hung Chou, Boyuan Jiang, Yi Wen Chen, Mingyue Weng et al.FSE 2026 · 1 citation
  4. SWE-IF: Aligning Code Evaluation with Human PreferenceMing Zhong, Xiang Zhou, Ting-Yun Chang, Qingze Wang et al.ICML 2026 · 3 citations
  5. VeRO: A Harness for Agents to Optimize AgentsVarun Ursekar, Apaar Shanker, Veronica Chatrath, Yuan Xue et al.ICML 2026 · 6 citations
Dusk over the sea between two cliffs drawn in fine vertical lines