Traditional long-horizon LLM agents often hand off context through full-history prompting, retaining all previous action--observation interactions. As execution proceeds, this history keeps growing, increasing inference cost and potentially degrading accuracy. Existing methods control this growth by preserving compact conclusions while removing earlier observations, but doing so can discard evidence that later becomes relevant.
Chen Hou
As seen in:
MSN,
Wiley Online Library,
arXiv,
Frontiers,
MDPI,
SFGate,
The Conversation,
ACS Publications,
Nutrition Journal,
Phys.org
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 Chen
Contact Chen, search articles and posts on X, monitor coverage, and track replies from one place.
Learn more about Muck Rack