# OctoNav: Towards Generalist Embodied Navigation

arXiv: https://arxiv.org/abs/2506.09839 · HTML: https://mlsanity.com/paper/2506.09839/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 69 of its 82 references that are in the map.
- First posted on arXiv 11 Jun 2025.

## Placed in

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

## Builds on (most cited first, 30 of 69)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [Video-LLaVA: Learning United Visual Representation by Alignment Before Projection](https://mlsanity.com/paper/2311.10122/) (2023)
- [Matterport3D: Learning from RGB-D Data in Indoor Environments](https://mlsanity.com/paper/1709.06158/) (2017)
- [Habitat: A Platform for Embodied AI Research](https://mlsanity.com/paper/1904.01201/) (2019)
- [Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments](https://mlsanity.com/paper/1711.07280/) (2017)
- [Graph of Thoughts: Solving Elaborate Problems with Large Language Models](https://mlsanity.com/paper/2308.09687/) (2023)
- [EVA-CLIP: Improved Training Techniques for CLIP at Scale](https://mlsanity.com/paper/2303.15389/) (2023)
- [Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models](https://mlsanity.com/paper/2503.06749/) (2025)
- [Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI](https://mlsanity.com/paper/2109.08238/) (2021)
- [On Evaluation of Embodied Navigation Agents](https://mlsanity.com/paper/1807.06757/) (2018)
- [LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models](https://mlsanity.com/paper/2311.17043/) (2023)
- [Habitat 2.0: Training Home Assistants to Rearrange their Habitat](https://mlsanity.com/paper/2106.14405/) (2021)
- [Video-R1: Reinforcing Video Reasoning in MLLMs](https://mlsanity.com/paper/2503.21776/) (2025)
- [Gibson Env: Real-World Perception for Embodied Agents](https://mlsanity.com/paper/1808.10654/) (2018)
- [Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environments](https://mlsanity.com/paper/2004.02857/) (2020)
- [Object Goal Navigation using Goal-Oriented Semantic Exploration](https://mlsanity.com/paper/2007.00643/) (2020)
- [ProcTHOR: Large-Scale Embodied AI Using Procedural Generation](https://mlsanity.com/paper/2206.06994/) (2022)
- [Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning](https://mlsanity.com/paper/1609.05143/) (2016)
- [Vision-Language Foundation Models as Effective Robot Imitators](https://mlsanity.com/paper/2311.01378/) (2023)
- [REVERIE: Remote Embodied Visual Referring Expression in Real Indoor Environments](https://mlsanity.com/paper/1904.10151/) (2019)

## Built on by (most cited first, 30 of 34)

- [The Landscape of Agentic Reinforcement Learning for LLMs: A Survey](https://mlsanity.com/paper/2509.02547/) (2025)
- [A Survey on Agentic Multimodal Large Language Models](https://mlsanity.com/paper/2510.10991/) (2025)
- [EVOLVE-VLA: Test-Time Training from Environment Feedback for Vision-Language-Action Models](https://mlsanity.com/paper/2512.14666/) (2025)
- [MobileVLA-R1: Reinforcing Vision-Language-Action for Mobile Robots](https://mlsanity.com/paper/2511.17889/) (2025)
- [ActiveVLN: Towards Active Exploration via Multi-Turn RL in Vision-and-Language Navigation](https://mlsanity.com/paper/2509.12618/) (2025)
- [NaviTrace: Evaluating Embodied Navigation of Vision-Language Models](https://mlsanity.com/paper/2510.26909/) (2025)
- [Explore with Long-term Memory: A Benchmark and Multimodal LLM-based Reinforcement Learning Framework for Embodied Exploration](https://mlsanity.com/paper/2601.10744/) (2026)
- [VLingNav: Embodied Navigation with Adaptive Reasoning and Visual-Assisted Linguistic Memory](https://mlsanity.com/paper/2601.08665/) (2026)
- [TIC-VLA: A Think-in-Control Vision-Language-Action Model for Robot Navigation in Dynamic Environments](https://mlsanity.com/paper/2602.02459/) (2026)
- [AwareVLN: Reasoning with Self-awareness for Vision-Language Navigation](https://mlsanity.com/paper/2605.22816/) (2026)
- [Reinforcement Learning for Large Model: A Survey](https://mlsanity.com/paper/2508.08189/) (2025)
- [CoMaTrack: Competitive Multi-Agent Game-Theoretic Tracking with Vision-Language-Action Models](https://mlsanity.com/paper/2603.22846/) (2026)
- [FineCog-Nav: Integrating Fine-grained Cognitive Modules for Zero-shot Multimodal UAV Navigation](https://mlsanity.com/paper/2604.16298/) (2026)
- [UrbanVLA: A Vision-Language-Action Model for Urban Micromobility](https://mlsanity.com/paper/2510.23576/) (2025)
- [SeeNav-Agent: Enhancing Vision-Language Navigation with Visual Prompt and Step-Level Policy Optimization](https://mlsanity.com/paper/2512.02631/) (2025)
- [FantasyVLN: Unified Multimodal Chain-of-Thought Reasoning for Vision-Language Navigation](https://mlsanity.com/paper/2601.13976/) (2026)
- [Lifelong Embodied Navigation Learning](https://mlsanity.com/paper/2603.06073/) (2026)
- [Structured Observation Language for Efficient and Generalizable Vision-Language Navigation](https://mlsanity.com/paper/2603.27577/) (2026)
- [NavSpace: How Navigation Agents Follow Spatial Intelligence Instructions](https://mlsanity.com/paper/2510.08173/) (2025)
- [All-day Multi-scenes Lifelong Vision-and-Language Navigation with Tucker Adaptation](https://mlsanity.com/paper/2603.14276/) (2026)
- [Turning Adaptation into Assets: Cross-Domain Bridging for Online Vision-Language Navigation](https://mlsanity.com/paper/2605.23257/) (2026)
- [SDA-PLANNER: State-Dependency Aware Adaptive Planner for Embodied Task Planning](https://mlsanity.com/paper/2509.26375/) (2025)
- [PIGEON: VLM-Driven Object Navigation via Points of Interest Selection](https://mlsanity.com/paper/2511.13207/) (2025)
- [ImagineNav++: Prompting Vision-Language Models as Embodied Navigator through Scene Imagination](https://mlsanity.com/paper/2512.17435/) (2025)
- [ReasonNavi: Human-Inspired Global Map Reasoning for Zero-Shot Embodied Navigation](https://mlsanity.com/paper/2602.15864/) (2026)
- [Rethinking Agentic Reinforcement Learning In Large Language Models](https://mlsanity.com/paper/2604.27859/) (2026)
- [LightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied Navigation](https://mlsanity.com/paper/2608.30935/) (2026)
- [MobileVLA-R1 2.0: RL-Enhanced Reasoning for Mobile Robot Control](https://mlsanity.com/paper/2609.06251/) (2026)
- [VISOR: VIsual Spatial Object Reasoning for Language-driven Object Navigation](https://mlsanity.com/paper/2602.07555/) (2026)
- [HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation](https://mlsanity.com/paper/2604.08232/) (2026)

## Abstract (arXiv)

Embodied navigation stands as a foundation pillar within the broader pursuit of embodied AI. However, previous navigation research is divided into different tasks/capabilities, e.g., ObjNav, ImgNav and VLN, where they differ in task objectives and modalities, making datasets and methods are designed individually. In this work, we take steps toward generalist navigation agents, which can follow free-form instructions that include arbitrary compounds of multi-modal and multi-capability. To achieve this, we propose a large-scale benchmark and corresponding method, termed OctoNav-Bench and OctoNav-R1. Specifically, OctoNav-Bench features continuous environments and is constructed via a designed annotation pipeline. We thoroughly craft instruction-trajectory pairs, where instructions are diverse in free-form with arbitrary modality and capability. Also, we construct a Think-Before-Action (TBA-CoT) dataset within OctoNav-Bench to provide the thinking process behind actions. For OctoNav-R1, we build it upon MLLMs and adapt it to a VLA-type model, which can produce low-level actions solely based on 2D visual observations. Moreover, we design a Hybrid Training Paradigm (HTP) that consists of three stages, i.e., Action-/TBA-SFT, Nav-GPRO, and Online RL stages. Each stage contains specifically designed learning policies and rewards. Importantly, for TBA-SFT and Nav-GRPO designs, we are inspired by the OpenAI-o1 and DeepSeek-R1, which show impressive reasoning ability via thinking-before-answer. Thus, we aim to investigate how to achieve thinking-before-action in the embodied navigation field, to improve model's reasoning ability toward generalists. Specifically, we propose TBA-SFT to utilize the TBA-CoT dataset to fine-tune the model as a cold-start phrase and then leverage Nav-GPRO to improve its thinking ability. Finally, OctoNav-R1 shows superior performance compared with previous methods.