Learning from experience is critical for developing capable, self-improving large language model (LLM) agents. Existing methods typically extract knowledge from accumulated trajectories via reflection, memory, rules, or skills. However, agents in realistic environments continuously encounter novel tasks, often offering only a one-shot opportunity to improve. These executions yield rich but highly noisy contexts, entangling broadly useful lessons with task-specific artifacts.
Zhan Shi
As seen in:
Nature,
Wiley Online Library,
arXiv,
PLOS,
Frontiers,
Frontiers in Nutrition,
MDPI,
ACS Publications,
Royal Society of Chemistry,
BioRxiv
and
Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile
Get in touch with Zhan
Contact Zhan, search articles and posts on X, monitor coverage, and track replies from one place.
Learn more about Muck Rack