Lorenzo Xiao(@lrzneedresearch):What if LLMs and agents could learn continuously from every interaction without retraining? Our new review on Test-Time Learning explores how deployed models can turn experience into adaptive state through a persistent write–read loop, improving future behavior over time.

Lorenzo Xiao

@lrzneedresearch

Agentic AI for enterpise/Human-centered NLP Previously @LTIatCMU

Joined January 2016

529 Following 2.8K Followers

Lorenzo Xiao@lrzneedresearch

2026.08.24 04:09

What if LLMs and agents could learn continuously from every interaction without retraining? Our new review on Test-Time Learning explores how deployed models can turn experience into adaptive state through a persistent write–read loop, improving future behavior over time.