| CARVIEW |
Select Language
HTTP/2 200
server: GitHub.com
content-type: text/html; charset=utf-8
last-modified: Tue, 04 Nov 2025 03:46:27 GMT
access-control-allow-origin: *
etag: W/"69097713-119f"
expires: Tue, 30 Dec 2025 07:49:54 GMT
cache-control: max-age=600
content-encoding: gzip
x-proxy-cache: MISS
x-github-request-id: B4C4:2F7ECD:9CB940:B00003:695381C9
accept-ranges: bytes
age: 0
date: Tue, 30 Dec 2025 07:39:54 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210028-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1767080394.288899,VS0,VE250
vary: Accept-Encoding
x-fastly-request-id: af967981d51c6e45ad30241b0a15893a876fa4c5
content-length: 1967
Home |
Stopping Agents
Stopping Agents
Language agents for optimal stopping
Stopping agents are language agents — large language models that generate decisions — specialized for optimal stopping of conversations.
Specifically, stopping agents observe the ongoing conversation text and
make sequential wait or quit decisions that optimally tradeoff between waiting
to accumulate more information and incurring waiting costs.
This project is based on the following research:
Manzoor, Emaad, and Ascarza, Eva and Netzer, Oded. Learning When to Quit in Sales Conversations. arXiv preprint arXiv:2511.01181 (2025).
