人間とAIのコーディング協調のスケールには、統治可能なコンセンサス層が必要
Scaling Human-AI Coding Collaboration Requires a Governable Consensus Layer
AI支援開発の成果物をコードとチャット履歴から、型付きプロパティグラフで表現されるコンセンサス層に置き換えるパラダイムを提案し、監査可能性と介入距離の削減を目指す。
著者: Tianfu Wang, Zhezheng Hao, Yin Wu, Wei Wu, Qiang Lin, Hande Dong, Nicholas Jing Yuan, Hui Xiong
分類: cs.SE, cs.HC, cs.LG
原文アブストラクト
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.