Project page: athena.openscientist.ai · Code: mims-harvard/ATHENA ATHENA-R1 is an AI agent for treatment reasoning, trained through reinforcement learning over a universe of 212 biomedical tools. It performs multi-step reasoning — identifying what evidence is needed, selecting tools, and incorporating retrieved evidence into subsequent steps — with tool calls served through the ToolUniverse (FDA labeling, Open Targets, ChEMBL, EuropePMC, etc.). Given a clinical question, the model performs multi-step tool calls, synthesises the evidence, and returns a free-form answer grounded in authoritative biomedical sources. 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). For a chat UI (bundled browser demo with live-streamed reasoning): Open-ended setting: each question is answered free-form, then mapped to one of the original answer choices. ATHENA-R1 exceeds GPT-5 by 17.8 points on DrugPC and 10.7 on TreatmentPC. See the docs/evalresults.md` file in the code repo for the full benchmark tables and the two-level self-learning ablation.…
Модальности:
Генерация текста
Области применения:
Диалог / чат Вызов функций (Tool use)
Задача: Генерация текста
Автор: mims-harvard
Теги: qwen3, agent, biomedical, treatment-reasoning, tool-use, reinforcement-learning, conversational, en
Лайков: 3 | Загрузок: 46
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
