AI RESEARCH
Learning to Order: Task Sequencing as In-Context Optimization
arXiv CS.LG
•
ArXi:2603.14550v1 Announce Type: new Task sequencing (TS) is one of the core open problems in Deep Learning, arising in a plethora of real-world domains, from robotic assembly lines to autonomous driving. Unfortunately, prior work has not convincingly nstrated the generalization ability of meta-learned TS methods to solve new TS problems, given few initial nstrations. In this paper, we nstrate that deep neural networks can meta-learn over an infinite prior of synthetically generated TS problems and achieve a few-shot generalization.