Wentian Zhao

Adobe Inc

Papers on Lattice

Total citations

Topics

Research focus

Eval Frameworks & Benchmarks (1)RLHF & Preference Learning (1)Scalable Oversight & Alignment Theory (1)

Frequent co-authors

Yifan Zeng (1)Yiran Wu (1)Yaolun Zhang (1)Kun Wan (1)

Papers (1)

May 22, 2026

May 22, 2026·also Adobe Research, AG2AI, Penn State

When Does Multi-Agent RL Improve LLM Workflows? Workflow, Scale, and Policy-Sharing Tradeoffs

Multi-agent RL can boost LLM accuracy, but the benefits hinge on the intricate balance of workflow, task, and model scale rather than just policy-sharing strategies.

Yifan Zeng, Yiran Wu, Yaolun Zhang +4

Eval Frameworks & Benchmarks RLHF & Preference Learning Scalable Oversight & Alignment Theory

Search

Wentian Zhao

Research focus

Frequent co-authors

Papers (1)