Scaling Human-AI Coding Collaboration Requires a Governable Consensus Layer
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918455449485312 |
|---|---|
| author | Wang, Tianfu Hao, Zhezheng Wu, Yin Wu, Wei Lin, Qiang Dong, Hande Yuan, Nicholas Jing Xiong, Hui |
| author_facet | Wang, Tianfu Hao, Zhezheng Wu, Yin Wu, Wei Lin, Qiang Dong, Hande Yuan, Nicholas Jing Xiong, Hui |
| contents | Vibe coding produces correct, executable code at speed, but leaves no record of the structural commitments, dependencies, or evidence behind it. Reviewers cannot determine what invariants were assumed, what changed, or why a regression occurred. This is not a generation failure but a control failure: the dominant artifact of AI-assisted development (code plus chat history) performs dimension collapse, flattening complex system topology into low-dimensional text and making systems opaque and fragile under change. We propose Agentic Consensus: a paradigm in which the consensus layer C, an operable world model represented as a typed property graph, replaces code as the primary artifact of engineering. Executable artifacts are derived from C and kept in correspondence via synchronization operators Phi (realize) and Psi (rehydrate). Evidence links directly to structural claims in C, making every commitment auditable and under-specification explicit as measurable consensus entropy rather than a silent guess. Evaluation must move beyond code correctness toward alignment fidelity, consensus entropy, and intervention distance. We propose benchmark task families designed to measure whether consensus-based workflows reduce human intervention compared to chat-driven baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_17883 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Scaling Human-AI Coding Collaboration Requires a Governable Consensus Layer Wang, Tianfu Hao, Zhezheng Wu, Yin Wu, Wei Lin, Qiang Dong, Hande Yuan, Nicholas Jing Xiong, Hui Software Engineering Human-Computer Interaction Machine Learning Vibe coding produces correct, executable code at speed, but leaves no record of the structural commitments, dependencies, or evidence behind it. Reviewers cannot determine what invariants were assumed, what changed, or why a regression occurred. This is not a generation failure but a control failure: the dominant artifact of AI-assisted development (code plus chat history) performs dimension collapse, flattening complex system topology into low-dimensional text and making systems opaque and fragile under change. We propose Agentic Consensus: a paradigm in which the consensus layer C, an operable world model represented as a typed property graph, replaces code as the primary artifact of engineering. Executable artifacts are derived from C and kept in correspondence via synchronization operators Phi (realize) and Psi (rehydrate). Evidence links directly to structural claims in C, making every commitment auditable and under-specification explicit as measurable consensus entropy rather than a silent guess. Evaluation must move beyond code correctness toward alignment fidelity, consensus entropy, and intervention distance. We propose benchmark task families designed to measure whether consensus-based workflows reduce human intervention compared to chat-driven baselines. |
| title | Scaling Human-AI Coding Collaboration Requires a Governable Consensus Layer |
| topic | Software Engineering Human-Computer Interaction Machine Learning |
| url | https://arxiv.org/abs/2604.17883 |