news

May 01, 2026 Our paper โ€œConstructing Industrial-Scale Optimization Modeling Benchmarkโ€ has been accepted to ICML 2026! ๐ŸŽ‰
Jan 28, 2026 Our paper โ€œSearch Self-Play: Pushing the Frontier of Agent Capability without Supervisionโ€ has been accepted to ICLR 2026! ๐ŸŽ‰
Oct 22, 2025 We are excited to release our latest research work in Agentic RL: โ€œSearch Self-Play: Pushing the Frontier of Agent Capability without Supervisionโ€! ๐Ÿš€ The paper has been submitted to ICLR 2026 and explores novel self-play training methods for enhancing agent capabilities without supervision.
May 01, 2025 Our paper โ€œOptMATH: A Scalable Bidirectional Data Synthesis Framework for Optimization Modelingโ€ has been accepted as a poster presentation at ICML 2025! ๐ŸŽ‰