GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
mims-harvard
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
mims-harvard
Model Tree
Qwen/Qwen3-8B
Input Modalities
Output Modalities
Supported Functionality
The model is exposed through the
athena-r1 Python package,
which handles the tool-call protocol and conversation management. Two
services back the agent: vLLM (model server) and ToolUniverse (tool server).
bash
# 1. Installpip install "athena-r1[vllm,web] @ git+https://github.com/mims-harvard/ATHENA.git"# 2. Start backing servicesbash scripts/launch_tooluniverse.sh # → :8080bash scripts/launch_vllm.sh 8000 mims-harvard/ATHENA-R1-Qwen3-8B# 3. Run the agent (Python)python -c "from athena_r1 import AthenaR1agent = AthenaR1(model='mims-harvard/ATHENA-R1-Qwen3-8B',vllm_url='http://0.0.0.0:8000/v1',tool_server='http://0.0.0.0:8080',)print(agent.answer('Dose adjustment for metformin in CKD eGFR 35?').answer)"
For a chat UI (bundled browser demo with live-streamed reasoning):
bash
python web/agui_server.py # → http://localhost:8090/ (AG-UI server + demo)
For an OpenAI-compatible API endpoint:
bash
python web/openai_server.py # → http://localhost:9000/v1/chat/completions
| Parameter | Value |
|---|---|
| temperature | 0.7 |
| top_p | 0.95 |
| top_k | 20 |
| min_p | 0.0 |
| presence_penalty | 0 |
| max_round | 40 |
| concurrent Qs | 4 |
Open-ended setting: each question is answered free-form, then mapped to one of the original answer choices.
| Benchmark | n | ATHENA-R1 | GPT-5 |
|---|---|---|---|
| DrugPC (open-ended drug reasoning) | 3,168 | 94.7% | 76.9% |
| TreatmentPC (patient-specific treatment) | 456 | 82.9% | 72.2% |
ATHENA-R1 exceeds GPT-5 by 17.8 points on DrugPC and 10.7 on TreatmentPC.
See the
docs/eval_results.md
file in the code repo for the full benchmark tables and the two-level
self-learning ablation.
<tool_call>...</tool_call> blocks; the runtime dispatches them through
ToolUniverse, appends results to the conversation, and re-prompts. Loop
continues until [FinalAnswer] or max_round is hit.ATHENA-R1 is a research artifact for treatment-reasoning research and decision support. It is not a medical device and must not be used for direct patient care.
bibtex
@article{gao2026athena,title = {An AI agent for treatment reasoning over a biomedical tool universe},author = {Gao, Shanghua and ... and Zitnik, Marinka},journal = {arXiv preprint},year = {2026}}
MIT.
Evidence retrieval is powered by ToolUniverse, a library of curated biomedical tools.