
We introduce Agent Alpha, a unified framework that synergizes generation, exploration, and evaluation through step-level MCTS for computer-use agents, achieving state-of-the-art on OS-World.
Feb 3, 2026

TL;DR ACDZero masters automated cyber defense by pairing Monte Carlo Tree Search with graph-neural-network embeddings of the network state — a planning-centric alternative to deep RL that achieves better defense reward, robustness, and sample efficiency.
Jan 1, 2026