Back to Tools Directory
🚀 Ultra Recipe for Training Long-Horizon Search Agents - matching frontier AI's search capability with a 20B model + stateful harness
Categories & Topics
search-agentsmodel-traininglong-horizonstateful-harness
Repository Stats
1.0k
GitHub Stars
151
Forks
1.0k
Watchers
1
Open Issues
License
Apache License 2.0
Repository
pat-jj/harness-1Last Updated
Today
September 20, 2026
Related Tools
AlayaWorld
884
Full-stack open-source interactive long-horizon world model.
deep-swe
1.7k
Measuring frontier coding agents on original, long-horizon engineering tasks
Nemotron
2.1k
Developer Asset Hub for NVIDIA Nemotron — A one-stop resource for training recipes, usage cookbooks, datasets, and full end-to-end reference examples to build with Nemotron models
PaperGuru-Benchmark
1.3k
Lifecycle-Aware Memory for long-horizon LLM agents — 66.05% on PaperBench, 94.66% on SurveyBench, 10 peer-reviewed acceptances at FSE/ICML/TOSEM/AEI/ICoGB
RealReplicaBench
1.3k
RealReplicaBench: Benchmarking Long-Horizon Agents in High-Fidelity, Stateful, and Reproducible Replicas of Real Online Services