Preprint
Jul 2026
STOCKTAKE: Measuring the Gap Between Perception and Action in LLM Agents with a Fair Oracle
STOCKTAKE is introduced, a 26-week supply-chain replenishment benchmark built as a factored partially observable Markov decision process with six hidden factor processes, designed so that a fair reference policy is computable: an exact Bayes filter per factor drives a rollout policy on the identical observation stream the agent receives.
Sagar Deb, Ashwanth Krishnan
· 0 citations