'Best-of-n with resets' remains a hard-to-beat baseline for multi-agent workflows
mariofilhoml · x · 2026-10-16
The author argues that in multi-agent workflow design and evaluation, "best-of-n with resets" — sampling multiple times and resetting state between retries — is a hard-to-beat baseline. More elaborate agent orchestration schemes often fail to outperform this simple strategy, making it an essential control in any agent eval setup.
More from coding & agent
- FireTrident lets thousands of coding agents work on one codebase at once — dinasaur_404 · 2026-10-16
- Dev builds MCP layer so Claude Code can work on servers without ever holding SSH keys — NETMESAFE · 2026-10-16
- As coding agents run longer autonomously, one dev's tip: don't parallel-session, just breathe — teropa · 2026-10-16
- 'Refusing to code with AI in 2026 is like refusing Google in 2005' — prasenx · 2026-10-16
- Claude Code adds idle compaction to save 1h prompt cache on idle sessions — EricBuess · 2026-10-16
- Handling agents that crash mid-task: the hard part is the unknown outcome across the network — Responsible-Dare5139 · 2026-10-16