2 papers
cs.LG2026
Chance-Constrained Personalized LLM Routing with Online Preference Learning
Ameya Anjarlekar, Rasoul Etesami, R Srikant
We study personalized LLM routing, where a router selects among heterogeneous models with different costs and capabilities. The router must minimize cumulative inference cost while…
cs.LG2025
Scalable Policy-Based RL Algorithms for POMDPs
Ameya Anjarlekar, Rasoul Etesami, R Srikant
The continuous nature of belief states in POMDPs presents significant computational challenges in learning the optimal policy. In this paper, we consider an approach that solves a…