news

Oct 22, 2025 We are excited to release our latest research work in Agentic RL: “Search Self-Play: Pushing the Frontier of Agent Capability without Supervision”! 🚀 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 “OptMATH: A Scalable Bidirectional Data Synthesis Framework for Optimization Modeling” has been accepted as a poster presentation at ICML 2025! 🎉