This paper introduces AREX, a self-improving agent that recursively refines its answers by verifying intermediate results and using the partially verified state to guide subsequent refinement, aiming to improve the efficiency of deep research. Practitioners might care about AREX's approach to reducing the cost of discovery and verification in complex research tasks.
Firehose
Filtered to Papers, tagged “mixture-of-experts models” · clear filters
Browse: People · Companies · Papers · Podcasts · Hacker News