# OptiSight: Bridging Semantic Reasoning and Geometric Control for Embodied Navigation

arXiv: https://arxiv.org/abs/2608.23354 · HTML: https://mlsanity.com/paper/2608.23354/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 14 of its 29 references that are in the map.
- First posted on arXiv 24 Aug 2026.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)

## Builds on (most cited first, 14 of 14)

- [Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks](https://mlsanity.com/paper/2401.14159/) (2024)
- [CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models](https://mlsanity.com/paper/2503.22020/) (2025)
- [Robotic Control via Embodied Chain-of-Thought Reasoning](https://mlsanity.com/paper/2407.08693/) (2024)
- [Qwen3.5-Omni Technical Report](https://mlsanity.com/paper/2604.15804/) (2026)
- [Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks](https://mlsanity.com/paper/2412.06224/) (2024)
- [NavCoT: Boosting LLM-Based Vision-and-Language Navigation via Learning Disentangled Reasoning](https://mlsanity.com/paper/2403.07376/) (2024)
- [Nav-R1: Reasoning and Navigation in Embodied Scenes](https://mlsanity.com/paper/2509.10884/) (2025)
- [MSGNav: Unleashing the Power of Multi-modal 3D Scene Graph for Zero-Shot Embodied Navigation](https://mlsanity.com/paper/2511.10376/) (2025)
- [Imaginative World Modeling with Scene Graphs for Embodied Agent Navigation](https://mlsanity.com/paper/2508.06990/) (2025)
- [ALRM: Agentic LLM for Robotic Manipulation](https://mlsanity.com/paper/2601.19510/) (2026)
- [Habitat-GS: A High-Fidelity Navigation Simulator with Dynamic Gaussian Splatting](https://mlsanity.com/paper/2604.12626/) (2026)
- [FantasyVLN: Unified Multimodal Chain-of-Thought Reasoning for Vision-Language Navigation](https://mlsanity.com/paper/2601.13976/) (2026)
- [Logic-Guided Socially-aware Robot Navigation World Model](https://mlsanity.com/paper/2510.23509/) (2025)
- [SceneGraphVLM: Dynamic Scene Graph Generation from Video with Vision-Language Models](https://mlsanity.com/paper/2605.13667/) (2026)

## Abstract (arXiv)

Autonomous indoor navigation requires both semantic understanding and precise geometric control. We propose OptiSight, a hybrid framework that combines Vision-Language Model reasoning with deterministic visual servoing through a finite-state Chain-of-Thought architecture. Grounded-SAM localizes open-vocabulary targets, while camera projection geometry converts visual observations into navigation commands without requiring dense mapping. The VLM is queried only at key decision points, reducing computational overhead while geometric control handles continuous navigation. Experiments in AI Habitat demonstrate reliable zero-shot navigation across diverse indoor scenarios, including obstacle avoidance and semantic ambiguity, while operating within an 8~GB VRAM budget. The source code is available at https://github.com/avanalperen/OptiSight-Python-Multimodal-CoT-for-Visual-Reasoning.