arXiv：cs.LG· Tianfu Wang, Zhezheng Hao, Yin Wu, Wei Wu, Haowen Yang, Linxiao Gong, Qiang Lin, Hande Dong, Nicholas Jing Yuan, Hui Xiong·· 4 小时前
扩大人机协作编程需要可治理的共识层：Agentic Consensus 与 Consensus Control
Scaling Human-AI Coding Collaboration Requires a Governable Consensus Layer
AI 导读
论文提出可治理的共识层 Agentic Consensus，用带版本的项目状态模型把选定意图、结构性承诺、可执行产物与证据关联起来，让人类和 AI 在实现前澄清意图、并对可检查和修改的承诺协调改动。其评审工作流已在 Consensus Control 中实现，10 名参与者在日常项目上试用后反馈对智能体提交改动的理解更清晰、更快，同批参与者的三条件对比收集了 60 份回答。
正文
Abstract:Vibe coding turns natural-language intent into working software, but code generation alone does not give humans and agents a shared account of what they are building. As collaboration spans participants, components, and releases, design choices must remain understandable and open to revision. We argue that scaling human and AI coding collaboration requires a governable consensus layer. Agentic Consensus organizes collaboration around a versioned project-state model linking selected intent, structural commitments, executable artifacts, and evidence. Participants can clarify intent before implementation and coordinate proposed changes against commitments that humans can inspect and revise. Bidirectional synchronization connects intended changes to implementation and exposes conflicts or stale evidence as artifacts evolve. We implemented its review workflow in Consensus Control. In a small exploratory human study, 10 participants used the system on projects from their everyday work and reported clearer, faster understanding of agent-submitted changes. A three-condition comparison with the same participants collected 60 responses, with near-ceiling decision scores and measured representation and pipeline costs. Our research agenda asks how shared project state can preserve human understanding and control as agent contributions accumulate.
| Subjects: | Software Engineering (cs.SE); Human-Computer Interaction (cs.HC); Machine Learning (cs.LG) |
| Cite as: | arXiv:2604.17883 [cs.SE] |
| (or arXiv:2604.17883v2 [cs.SE] for this version) | |
| https://doi.org/10.48550/arXiv.2604.17883 arXiv-issued DOI via DataCite |
Submission history
From: Tianfu Wang [view email]
[v1]
Mon, 20 Apr 2026 06:53:32 UTC (259 KB)
[v2]
Tue, 13 Oct 2026 18:49:02 UTC (1,862 KB)
来源：arXiv：cs.LG · arxiv.org