Lan-Zhe Guo

Agents trained on static benchmarks falter dramatically in open-world settings, revealing a critical gap in their adaptability to real-world complexities.

MLLMs face severe scalability limitations, with performance dropping by up to 80% on complex visual reasoning tasks, revealing a critical gap in their structural reasoning capabilities.

Multi-agent LLM systems can adapt to new tasks without sacrificing structural integrity, thanks to a novel framework that guarantees role evolution preserves key operational contracts.

LoopLMs don't reliably scale at test time because of an inherent stability vs. effectiveness trade-off, but a new training method can fix that.