This paper shows that letting an AI search many places at the same time (in parallel) can beat making it think in long, slow chains.
Agent-Omit teaches AI agents to skip unneeded thinking and old observations, cutting tokens while keeping accuracy high.
PACEvolve is a new recipe that helps AI agents improve their ideas step by step over long periods without getting stuck.
This paper builds an AI agent, ML-Master 2.0, that can work on machine learning projects for a very long time without forgetting what matters.