Meta-Harness: End-to-End Optimization of Model Harnesses
Source
Yoonho Lee
Author
Yoonho Lee
Date
Terms in this piece · Glossary
agent harness — The scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
Why it matters
agent harnessThe scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.Full definition → engineering, automated: this optimizes the scaffolding around a model — what it stores, retrieves, and feeds back — rather than the weights. Read it once you have realized the harness, not the model, is where most of your AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → quality actually comes from.
Key quotes
“Meta-Harness takes a different approach: it gives the proposer a filesystem containing the full source code, scores, and execution traces of
every prior candidate.”
Yoonho Lee
“In practice, this means up to 10M tokens of diagnostic context per step, vs. at most 26K for all prior methods we
surveyed.”
Yoonho Lee
“On Claude Opus 4.6 , Meta-Harness achieves 76.4% pass rate, surpassing Terminus-KIRA (74.7%) and ranking
#2 among all Opus 4.6 agents.”
Yoonho Lee
“A single discovered retrieval harness improves accuracy by +4.7 points on average (34.1% → 38.8%) across five held-out
models.”
