EvoGit: Decentralized Code Evolution via Git-Based Multi-Agent Collaboration
Beichen Huang, Ran Cheng, Kay Chen Tan

TL;DR
EvoGit is a decentralized framework where autonomous coding agents collaboratively evolve software through a Git-based version graph, enabling scalable, asynchronous, and minimal-human intervention development.
Contribution
It introduces a novel Git-based multi-agent system for autonomous, decentralized software evolution without centralized control or explicit messaging.
Findings
Successfully built a web application from scratch.
Evolved a language-model-guided solver for bin-packing.
Demonstrated scalable, asynchronous agent collaboration.
Abstract
We introduce EvoGit, a decentralized multi-agent framework for collaborative software development driven by autonomous code evolution. EvoGit deploys a population of independent coding agents, each proposing edits to a shared codebase without centralized coordination, explicit message passing, or shared memory. Instead, all coordination emerges through a Git-based phylogenetic graph that tracks the full version lineage and enables agents to asynchronously read from and write to the evolving code repository. This graph-based structure supports fine-grained branching, implicit concurrency, and scalable agent interaction while preserving a consistent historical record. Human involvement is minimal but strategic: users define high-level goals, periodically review the graph, and provide lightweight feedback to promote promising directions or prune unproductive ones. Experiments demonstrate…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsSoftware Engineering Research · Advanced Software Engineering Methodologies · Model-Driven Software Engineering Techniques
