MedAgentGym: A Scalable Agentic Training Environment for Code-Centric Reasoning in Biomedical Data Science

ICLROral2026

Authors: Ran Xu, Yuchen Zhuang, Yishan Zhong, Yue Yu, Zifeng Wang, Xiangru Tang, Hang Wu, May Dongmei Wang, Peifeng Ruan, Donghan Yang, Tao Wang, Guanghua Xiao, Xin Liu, Carl Yang, Yang Xie, Wenqi Shi
Affiliation: Google DeepMind
Venue: ICLR 2026
Track: Oral

TL;DR

MedAgentGym is a scalable and interactive training environment designed to enhance coding-based biomedical reasoning capabilities in LLM agents.

Opening excerpt from the authors’ abstract. source

Read the paper

OpenReview

Topics

reasoning agent llm

← All ICLR 2026 Oral papers · Browse the whole archive