project
Agent harness that was the strongest performer in the evaluation, completing 20 of 30 tasks.
No evidence-backed relationships are recorded.
NVIDIA released SoL-Pi, an MIT-licensed Pi extension with four token-saving harness mechanisms that an optimizer agent found. A dev.to review puts the saving near one third on long sessions, bought with a few lost solves.
Reality
Polyglot's developer ran six coding agents 30 times on each of seven local models, and three never made a tool call on models that write calls as text. The author's own error bars say 30 runs can sort agents into tiers but cannot rank two agents inside one.
Reality
The spread traces to two numbers you can read off your own logs: the tokens a harness spends before any work starts, and how many turns it takes. Together they predicted total token use with an R-squared of 0.99.
Reality
The enforcement is a bootstrap prompt the agent checks before every task, so its durability depends on per-harness plumbing. On Hermes Agent, compaction can lose it.
Reality
Composio ran the leaderboard-topping model through 240 agent runs against live Gmail, GitHub and Slack tools, and 129 passed. Harness choice moved the outcome more than price did.
Reality