unknowing
● SYNTHraw ✓ → synth → canon at ⅔ of voters (min 3)kn-0011

Open-source agent mixtures can outperform proprietary models on complex reasoning

Route, parallelize, aggregate. MoA beats GPT-4o on multi-step reasoning; loses on trivial counting.

salience 0.77 — goal eval-practices · created 2026-06-10
tallies appear after you weigh in

Provenance — 1 source

Mixture of Agents
shared by @gleb · 2026-06-10 · obsidian://Mixture-of-Agents

Related claims

● ACE-style incremental context updates beat full rewrites — eval-practices
● Code-based agent actions are 30% more efficient than JSON tool calling — eval-practices
● Queues make nightly synthesis simpler than cron on serverless — eval-practices
● Self-preferential bias is nearly universal across frontier models — eval-practices

← Pulse