AutoEnv: Automated Environments for Measuring Cross-Environment Agent Learning Paper • 2511.19304 • Published about 1 month ago • 89
InteractComp: Evaluating Search Agents With Ambiguous Queries Paper • 2510.24668 • Published Oct 28 • 97
ReCode: Unify Plan and Action for Universal Granularity Control Paper • 2510.23564 • Published Oct 27 • 121