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.
40
Product
ClawMark
- Mentions · 7d0
- Mentions · 30d2
- All mentions2
- First seenOct 17, 2026
- Last mentioned8d ago
Timeline
2 articles · newest firstCoworkEnv synthesizes training environments for long-horizon coworker agents
SFT on Qwen3-VL-8B-Instruct raised the Claw-Eval mean from 46.6 to 64.1, including a 31.9-point multi-turn gain.
48
Appears with
- CoworkEnvproduct · 1
- PocketWorkerai model · 1
- Claw-Evalproduct · 1
- Qwen3-VL-8B-Instructai model · 1
- GAIA2product · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.