# Scaling Human-AI Coding Collaboration Requires a Governable Consensus Layer

arXiv: https://arxiv.org/abs/2604.17883 · HTML: https://mlsanity.com/paper/2604.17883/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 28 references that are in the map.
- First posted on arXiv 20 Apr 2026.

## Builds on (most cited first, 8 of 8)

- [Zep: A Temporal Knowledge Graph Architecture for Agent Memory](https://mlsanity.com/paper/2501.13956/) (2025)
- [The Impact of AI on Developer Productivity: Evidence from GitHub Copilot](https://mlsanity.com/paper/2302.06590/) (2023)
- [Visibility into AI Agents](https://mlsanity.com/paper/2401.13138/) (2024)
- [FeatureBench: Benchmarking Agentic Coding for Complex Feature Development](https://mlsanity.com/paper/2602.10975/) (2026)
- [A Comprehensive Survey on Benchmarks and Solutions in Software Engineering of LLM-Empowered Agentic System](https://mlsanity.com/paper/2510.09721/) (2025)
- [Agentsway -- Software Development Methodology for AI Agents-based Teams](https://mlsanity.com/paper/2510.23664/) (2025)
- [CentaurEval: Benchmarking Human-in-the-Loop Value in Agentic Coding](https://mlsanity.com/paper/2512.04111/) (2025)
- [Agint: Agentic Graph Compilation for Software Engineering Agents](https://mlsanity.com/paper/2511.19635/) (2025)

## Abstract (arXiv)

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.