When Engineering Outruns Intelligence: Rethinking Instruction-Guided Navigation
Abstract
Recent ObjectNav systems credit large language models (LLMs) for sizable zero-shot gains, yet it remains unclear how much comes from language versus geometry. We revisit this question by re-evaluating an instruction-guided pipeline, InstructNav, under a detector-controlled setting and introducing two training-free variants that only alter the action value map: a geometry-only Frontier Proximity Explorer (FPE) and a lightweight Semantic-Heuristic Frontier (SHF) that polls the LLM with simple frontier votes. Across HM3D and MP3D, FPE matches or exceeds the detector-controlled instruction follower while using no API calls and running faster; SHF attains comparable accuracy with a smaller, localized language prior. These results suggest that carefully engineered frontier geometry accounts for much of the reported progress, and that language is most reliable as a light heuristic rather than an end-to-end planner. Code available at: https://github.com/matinaghaei/instructnav-scrutinized
Cite
@article{arxiv.2507.20021,
title = {When Engineering Outruns Intelligence: Rethinking Instruction-Guided Navigation},
author = {Matin Aghaei and Lingfeng Zhang and Mohammad Ali Alomrani and Mahdi Biparva and Yingxue Zhang},
journal= {arXiv preprint arXiv:2507.20021},
year = {2026}
}
Comments
Updated version with additional ablations, clarifications, and code release