vibehacker
News
arXiv / Microsoft Research ·

Microsoft's Agensh: leaderless coding-agent teams keep improving from 1 to 1,024 agents

Agensh drops the central orchestrator: each worker claims its own sub-task, builds and tests it, and merges into a shared Git repo while posting findings to a shared board, all on top of a Copilot single-agent harness with a 6-hour budget. On ProgramBench's five hardest tasks with GPT-5.6-sol, going from 1 to 128 agents lifted the mean test-pass rate from 19.31% to 28.78%, and 1,024 agents pushed pandoc from 33.89% to 55.06%, though the paper doesn't report what large teams cost.

More news

View all

SOCi makes its MCP server generally available

Announced Nov 19, SOCi's MCP server is now GA for all customers, letting MCP capable assistants call its platform, agentic and reporting tools. It ships alongside more than 140 integrations feeding its context layer…

SOCi

Spotted something we missed? Start a thread.