Cite
Notes
Only stored in your browser.
Attribution
SciAgentGym: Benchmarking Multi-Step Scientific Tool-use in LLM Agents
arXiv 2026
The Landscape of Agentic Reinforcement Learning for LLMs: A Survey
arXiv 2025
BMMR: A Large-Scale Bilingual Multimodal Multi-Discipline Reasoning Dataset
from 3 papers
Lei Bai
Zhenfei Yin
Philip Torr
Qi Zhang
Tao Gui
Xuanjing Huang
Zhiheng Xi
Binze Hu
Chen Zhang
Guanyu Li