# Prune-Then-Plan: Step-Level Calibration for Stable Frontier Exploration in Embodied Question Answering Source: [Prune-Then-Plan: Step-Level Calibration for Stable Frontier Exploration in Embodied Question Answering]() Collection index: [llms.txt]() Data updated: 2025-11-27T05:02:27.865Z Authors: Noah Frahm, Prakrut Patel, Yue Zhang, Shoubin Yu, Mohit Bansal, Roni Sengupta Published: 2025-11-24T22:50:50.000Z ## Abstract Large vision-language models (VLMs) have improved embodied question answering (EQA) agents by providing strong semantic priors for open-vocabulary reasoning. However, when used directly for step-level exploration, VLMs often exhibit frontier oscillations, unstable back-and-forth movements caused by overconfidence and miscalibration, leading to inefficient navigation and degraded answer quality. We propose Prune-Then-Plan, a simple and effective framework that stabilizes exploration through step-level calibration. Instead of trusting raw VLM scores, our method prunes implausible frontier choices using a Holm-Bonferroni inspired pruning procedure and then delegates final decisions to a coverage-based planner. This separation converts overconfident predictions into conservative, interpretable actions by relying on human-level judgments to calibrate the step-level behavior of VLMs. Integrated into the 3D-Mem EQA framework, our approach achieves relative improvements of up to 49% and 33% in visually grounded SPL and LLM-Match metrics respectively over baselines. Overall, our method achieves better scene coverage under equal exploration budgets on both OpenEQA and EXPRESS-Bench datasets. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()