Microsoft Research runs 1K+ coding agents with no central orchestrator, lifting pass rate to 55%
omarsar0 · x · 2026-09-28
Microsoft Research's Agensh is a scalable self-organized multi-agent harness that runs 1,000+ coding agents concurrently without a central orchestrator.
- Agents coordinate asynchronously through a shared workspace and message channel: each gathers context, claims a sub-task, works, shares findings, verifies, and merges results.
- On the five hardest ProgramBench tasks with GPT-5.6-sol, scaling from 1 to 128 agents raises mean test-pass rate from 19.31% to 28.78%; larger teams reach a given pass rate sooner.
- On pandoc, 1,024 agents push pass rate from 33.89% to 55.06%.
- The authors also report emergent forms of agent cooperation.
Most multi-agent systems today rely on hierarchy or structure; Agensh shows shared-state coordination can scale.
More from coding & agent
- SolidBot moves real steel: post-processed robot programs now heading into TCP and accuracy tests — MatthewChang · 2026-09-28
- Grok Bot and Muse too dumb for business agents, says engineer comparing Claude Code — jdjohnson · 2026-09-28
- Why your AI agent says the job is 'big': it's just latency priming — jacalulu · 2026-09-28
- Investor: Silicon Valley's consumer AI pivot opens a window for coding agent startups — edgarpavlovsky · 2026-09-28
- Developer builds dark-fantasy boss rush DEUS entirely in conversation with an Opus 5.5-powered AI — majidmanzarpour · 2026-09-28
- Agent self-monetization: 4 physical Macs equal ~$5,356/month at GitHub runner prices — arthurcolle · 2026-09-28