作者位次 #3/13ICLR 2026Poster· Reinforcement Learning / Multi-agent
Optimas: Optimizing Compound AI Systems with Globally Aligned Local Rewards
Shirley Wu · Parth Sarthi · Shiyu Zhao · Aaron Lee · Herumb Shandilya · Adrian Mladenic Grobelnik · Nurendra Choudhary · Edward Huang · Karthik Subbian · Linjun Zhang · Diyi Yang · James Y Zou · Jure Leskovec