Harness-1

A 20B search agent that matches frontier AI's search capability.

News

• 2026-06-15: Released Harness-1 training data and retrieval corpora at pat-jj/harness-1-train-data: 899 SFT trajectories, 3,453 RL SEC train-split examples, and corpus shards for BrowseComp+, web, patents, and SEC.
• 2026-06-15: Released the full merged Harness-1 checkpoint as standard Hugging Face safetensors shards.

Code: https://github.com/pat-jj/harness-1

Paper: https://arxiv.org/abs/2606.02373

Training data and corpora: https://huggingface.co/datasets/pat-jj/harness-1-train-data

Tinker inference example: https://github.com/pat-jj/harness-1/blob/main/inference/tinker_inference.md

vLLM inference example: https://github.com/pat-jj/harness-1/blob/main/inference/vllm_h100_browsecompplus.md

This repository contains the full merged Harness-1 release checkpoint. The model is merged into the openai/gpt-oss-20b base model and saved as standard Hugging Face safetensors shards.

Training Data And Corpora

The Harness-1 training data and retrieval corpora are published separately as pat-jj/harness-1-train-data. It contains one train split with a stage column:

• sft: 899 raw GPT-5.4-generated v8d SFT trajectories produced by generate_sft_ultra_0417.py.
• rl: 3,453 SEC training-split query records used for RL (TRAIN_DATASETS=sec, RL_QUERY_SPLIT=train).

The same dataset repo also includes retrieval corpora under corpora/:

• corpora/browsecompplus/test: 1,144,886 chunks.
• corpora/web/train: 219,388 chunks.
• corpora/web/test: 54,735 chunks.
• corpora/patents/train: 104,842 chunks.
• corpora/patents/test: 35,551 chunks.
• corpora/sec/train: 2,115,106 chunks.

from datasets import load_dataset

ds = load_dataset("pat-jj/harness-1-train-data", split="train")
sft = ds.filter(lambda row: row["stage"] == "sft")
rl = ds.filter(lambda row: row["stage"] == "rl")

sec_corpus = load_dataset(
    "parquet",
    data_files="hf://datasets/pat-jj/harness-1-train-data/corpora/sec/train/*.parquet",
    split="train",
)