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 software implements the algorithm proposed in our paper:

Manzoor, Emaad, and Ascarza, Eva and Netzer, Oded. “Learning When to Quit in Sales Conversations.” arXiv preprint arXiv:????.????? (2025).