AREX proposes a recursively self-improving deep-research agent
AREX, a Hugging Face paper with 115 upvotes, describes an agent that recursively self-improves at deep research tasks. It's part of a run of work on agents that refine their own strategies rather than staying fixed after training. Early research, but a signal of where autonomous research agents are heading — worth a skim if you're building retrieval or research pipelines.