← all papers · overview

PABU: Progress-aware Belief Update For Efficient LLM Agents

Abstract

Large Language Model (LLM) agents commonly condition actions on full action-observation histories, which introduce task-irrelevant information that easily leads to redundant actions and higher inference cost. We propose Progress-Aware Belief Update (PABU), a belief-state framework that compactly represents an agent's state by explicitly modeling task progress and selectively retaining past actions

Related papers

Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).