| --- |
| license: mit |
| base_model: Qwen/Qwen3-8B-Base |
| pipeline_tag: text-generation |
| language: |
| - en |
| tags: |
| - hybrid-reasoning |
| - latent-reasoning |
| - agent |
| - tool-use |
| --- |
| |
| # HybridAgent-8B-Agentic |
|
|
| - Paper: [Hybrid Reasoning Agents](https://arxiv.org/pdf/2610.18861) |
| - Code: https://github.com/togethercomputer/HybridAgent |
| - 14B HybridAgent: [togethercomputer/HybridAgent-14B-Agentic](https://huggingface.co/togethercomputer/HybridAgent-14B-Agentic) |
|
|
| ## Overview |
|
|
| HybridAgent is an LLM agent that dynamically navigates between latent reasoning and text-based interaction within a single generation process. It thinks in continuous latent space through a lightweight HybridLink and acts through text, calling a Python interpreter and a web search tool across multiple turns over one shared working memory. Its latent thoughts stay directly interpretable: every latent step can be read out as pseudo-text. |
|
|
| This checkpoint is the 8B HybridAgent for **agentic reasoning tasks**, built on Qwen3-8B-Base with HybridSFT followed by HybridRL. |
|
|
| ## Files |
|
|
| Standard Transformers files for the backbone (`model.safetensors`, `config.json`, `generation_config.json`, the tokenizer with the two anchor tokens `<latent>` and `</latent>`) plus the HybridLink weights `adapter.pt` with `adapter_config.json`. Loading the backbone with `transformers` alone gives a text-only model; hybrid generation with latent mode and tools needs the HybridAgent code. |
|
|
| ## Usage |
|
|
| ```bash |
| git clone https://github.com/togethercomputer/HybridAgent.git && cd HybridAgent |
| pip install -r requirements.txt && pip install -e . |
| cp .env.example .env # TAVILY_API_KEY for the search tool |
| |
| # batch inference on a JSONL file of questions |
| python -m hybrid_inference.run_batch --model togethercomputer/HybridAgent-8B-Agentic \ |
| --input examples/questions.jsonl --output outputs/results.jsonl |
| |
| # inspect the latent thoughts of a trajectory as pseudo-text (HTML report) |
| python -m interpretable_latent_mode --model togethercomputer/HybridAgent-8B-Agentic \ |
| --question "How many trailing zeros does 100! have?" --output report.html |
| ``` |
|
|
| ```python |
| import torch |
| from hybrid_agent import HybridGenerationEngine, SYSTEM_PROMPT, build_tool_executor, load_hybrid_agent |
| |
| model, tokenizer = load_hybrid_agent("togethercomputer/HybridAgent-8B-Agentic", device="cuda") |
| engine = HybridGenerationEngine(model, tokenizer, torch.device("cuda"), build_tool_executor(), SYSTEM_PROMPT, |
| "How many trailing zeros does 100! have?", batch_size=1, record_latent_readout=True) |
| engine.run(torch.Generator(device="cuda").manual_seed(0)) |
| print(engine.row_result(engine.rows[0])["output_rendered"]) |
| ``` |
|
|
| ## Citation |
|
|
| ```bibtex |
| @misc{zou2026hybridagent, |
| title={Hybrid Reasoning Agents}, |
| author={Jiaru Zou and Yunzhe Qi and Sirui Chen and Federico Bianchi and Shang Zhu and Pan Lu and Jingrui He and James Zou}, |
| year={2026}, |
| eprint={2610.18861}, |
| archivePrefix={arXiv}, |
| primaryClass={cs.CL}, |
| url={https://arxiv.org/abs/2610.18861}, |
| } |
| ``` |
