ParetoSaddler improves quality and reduces cost in LLM agent harnesses
ParetoSaddler uses Bayesian bootstrap Pareto support to promote candidates showing progress in quality or cost during optimization on ClawMark and GAIA2.
Stories per day · 30 days
Relatedagent-harnesses2benchmark-evaluation1llm-agents1recursive-self-improvement1swe-bench1terminal-bench1
2 stories, newest first · one card per story
Stories tagged #pareto-optimization
HarnessPro evolves agent harnesses for better performance at lower cost
With GPT-5.5 and Codex, heavy mode gained 2.0 pass-rate points and cut per-task cost 26.1% versus RHO.