Rohan Paul (@rohanpaul_ai) · 10/11/2026, 18:32:55
Meta's GitSwarm: Multi-Agent System Leverages Shared Git History to Reuse Failed Attempts for Program Reconstruction
Meta introduces GitSwarm, a framework where multiple homogeneous agents collaborate via a shared Git repository to reuse historical attempts, including failures. Without a central scheduler, agents autonomously read past commits and track dependencies, achieving 79.4% accuracy on ProgramBench—significantly outperforming single-agent continuous execution (65.1%)—demonstrating the critical value of preserving 'failed states' for enhancing agent collaboration efficiency.
SOURCE COVERAGEFull Original Report
Rohan Paul (@rohanpaul_ai) · 2026-10-11 10
New Meta paper shows that AI agents can build on each other's work, even failed attempts, when every step lives in a shared Git repo.
Most ways to give agents more compute treat each run on its own. When a run ends, its partial results and failures vanish, so later runs may need to rediscover them.
GitSwarm runs many identical agents on a shared repo, with no boss assigning tasks. Each agent reads past work, picks what to try, and commits its result with a list of earlier commits it used, even from other branches.
On 50 program-rebuilding tasks from ProgramBench, GitSwarm scored 79.4%, while a single Codex agent told to keep working peaked at 65.1% at similar compute. Later agents built on 94.7% of saved contributions.
Instead of pushing a single agent to keep going, run several over a shared Git history that keeps every attempt, failures included.
