arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2604.17883cs.SEcs.HCcs.LG
收藏

规模化的人工智能编码协作需要一个可治理的共识层

Scaling Human-AI Coding Collaboration Requires a Governable Consensus Layer

Tencent(腾讯)

Tianfu Wang, Zhezheng Hao, Yin Wu, Wei Wu, Haowen Yang, Linxiao Gong, Qiang Lin, Hande Dong, Nicholas Jing Yuan, Hui Xiong

AI总结:

本文提出Agentic Consensus共识层,通过类型属性图替代代码作为主要工程产物,解决AI辅助开发中代码与聊天历史维度塌陷导致的系统不透明问题,强调通过共识熵衡量协作流程的对齐度和干预距离。

摘要:

Vibe编码能快速生成正确可执行的代码,但无法记录结构承诺、依赖关系或证据。评审者无法确定假设的不变量、变化内容或回归原因。这不是生成失败,而是控制失败:AI辅助开发的主导产物(代码加聊天历史)导致维度塌陷,将复杂系统拓扑扁平化为低维文本,使系统在变化下变得不透明和脆弱。我们提出Agentic Consensus:一种共识层C,作为可操作的世界模型,以类型属性图表示,取代代码作为工程的主要产物。可执行产物从C中推导并通过同步算子Phi(实现)和Psi(重 hydrate)保持对应。证据直接链接到C中的结构声明,使每个承诺可审计,并将未充分规范的情况明确为可测量的共识熵而非沉默猜测。评估必须超越代码正确性,转向对齐保真度、共识熵和干预距离。我们提出基准任务家族,用于衡量基于共识的工作流是否比基于聊天的基线减少人类干预。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑