EverMind open-sources Raven, a multi-agent system that evolves a custom harness per model
dair_ai · x · 2026-10-05
EverMind AI released Raven, an open-source multi-agent system that builds a separate harness for each model and domain, evolves those harnesses from their failures, and coordinates everything through a host agent.
- How it works: the host agent splits a goal into a task graph and routes each part to a model-harness pair for research, code, design, or on-call work. Harness components are diagnosed, mutated, and recombined; a candidate replaces the current harness only after passing a statistical check.
- Results: with DeepSeek-V4-Flash, the research harness scores 69.3% on BrowseComp and 60.0% on Humanity's Last Exam, versus at most 62.4% and 43.3% for two other harnesses on the same model.
- Skills: a curated skill library lifts SkillsBench Pass@1 from 9.2% (no skills) to 22.6%.
Paper and Chat-with-Paper links in the original post.
More from coding & agent
- AI Swarm hackathon draws hundreds to build monitoring tools after HF and German Wiki incidents — generativist · 2026-10-05
- SPLASH 2026 keynote asks how to keep the engineer in software engineering amid AI coding agents — satnam6502 · 2026-10-05
- GLM vs Qwen tool calling differences force separate handlers in Codex proxy — TheZachMueller · 2026-10-05
- Why running third-party models in Codex needs a tool-calling proxy layer — TheZachMueller · 2026-10-05
- explainroo: a fully local, zero-API pipeline for narrated explainer videos — brandybuckferryman · 2026-10-05
- Dev says nearly all his web searches now run through personal agents as web goes headless — illscience · 2026-10-05