CrystalSTAR: Structured Action Orchestration with Trio-Reflection for Constrained Novel Crystal Discovery Submitted to COLM, 2026Download Paper
ARLArena: Demystifying Policy Gradient Stability in Agentic Reinforcement Learning Submitted to ICML, 2026Download Paper
TOAST: Multi-Agent Collaborative System for Symbolic Regression Submitted to ACL ARR, 2026Download Paper