Framing LLM agent loops as a Context Gathering Decision Process POMDP yields a predicate-based belief state that boosts multi-hop reasoning up to 11.4% and an exhaustion gate that cuts token use up to 39% with no performance loss.
Finite-time analysis of the multiarmed bandit problem.Machine learning, 47(2):235–256
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
Develops COF algorithm for MAB-CS that intelligently checks cheap arm feasibility by pooling samples, with generalized instance-dependent lower bounds and matching upper bounds on cumulative cost and quality regret.
citing papers explorer
-
The Context Gathering Decision Process: A POMDP Framework for Agentic Search
Framing LLM agent loops as a Context Gathering Decision Process POMDP yields a predicate-based belief state that boosts multi-hop reasoning up to 11.4% and an exhaustion gate that cuts token use up to 39% with no performance loss.
-
Cost-Ordered Feasibility for Multi-Armed Bandits with Cost Subsidy
Develops COF algorithm for MAB-CS that intelligently checks cheap arm feasibility by pooling samples, with generalized instance-dependent lower bounds and matching upper bounds on cumulative cost and quality regret.