AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

What You See Is What You Reach: Towards Spatial Navigation with High-Level Human Instructions

Lingfeng Zhang, Haoxiang Fu, Xiaoshuai Hao, Shuyi Zhang, Qiang Zhang, Rui Liu, Long Chen, Wenbo Ding

AAAI 2026 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Vision-language navigation agents · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use GPT-4o instead of Qwen2.5-VL-72B for instruction reasoning (ablation)SpNav · Spatial navigation benchmarksuccess rate: 28.9% -> 41.1%Improved
add a VLM reasoning stage for goal extraction (ablation)SpNav · Spatial navigation benchmarksuccess rate: 12.4% -> 41.1%Improved
use larger open-source reasoning VLM (72B vs 7B) (ablation)SpNav · Spatial navigation benchmarksuccess rate: 23.4% -> 28.9%Improved
replace NaviPoint with GPT-4o for goal pointing (ablation)SpNav · Spatial navigation benchmarksuccess rate: 41.1% -> 25.4%Hurt
use task-specific NaviPoint (7B) instead of RoboPoint (13B) (ablation)SpNav · Spatial navigation benchmarksuccess rate: 35.2% -> 41.1%Improved
fine-tune pointing VLM on 200K spatial QA pairs vs general VLMs (ablation)SpNav · Spatial navigation benchmarksuccess rate: 16.7% -> 41.1% (vs Qwen2.5-VL-72B)Improved
use Map-to-Action instead of PointNav (ablation)SpNav · Spatial navigation benchmarksuccess rate: 28.0% -> 41.1%Improved
use Map-to-Action instead of Direct-and-Avoid (ablation)SpNav · Spatial navigation benchmarksuccess rate: 15.0% -> 41.1%Improved
use hierarchical SpNav instead of general VLMs end-to-endSpNav vs Qwen2.5-VL-7B · Spatial navigation benchmarksuccess rate: 0.0% -> 41.1%Improved
use SpNav instead of MapNav (best navigation-specific baseline)SpNav · Spatial navigation benchmarkSPL: 32.1 -> 34.8Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy