# SeeNav-Agent: Enhancing Vision-Language Navigation with Visual Prompt and Step-Level Policy Optimization

arXiv: https://arxiv.org/abs/2512.02631 · HTML: https://mlsanity.com/paper/2512.02631/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 25 of its 30 references that are in the map.
- First posted on arXiv 2 Dec 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)
- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 25 of 25)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations](https://mlsanity.com/paper/2312.08935/) (2023)
- [AI2-THOR: An Interactive 3D Environment for Visual AI](https://mlsanity.com/paper/1712.05474/) (2017)
- [Group-in-Group Policy Optimization for LLM Agent Training](https://mlsanity.com/paper/2505.10978/) (2025)
- [Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding](https://mlsanity.com/paper/2010.07954/) (2020)
- [History Aware Multimodal Transformer for Vision-and-Language Navigation](https://mlsanity.com/paper/2110.13309/) (2021)
- [EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents](https://mlsanity.com/paper/2502.09560/) (2025)
- [What does CLIP know about a red circle? Visual prompt engineering for VLMs](https://mlsanity.com/paper/2304.06712/) (2023)
- [PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs](https://mlsanity.com/paper/2402.07872/) (2024)
- [Improving Vision-and-Language Navigation with Image-Text Pairs from the Web](https://mlsanity.com/paper/2004.14973/) (2020)
- [Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning](https://mlsanity.com/paper/2405.10292/) (2024)
- [BEVBert: Multimodal Map Pre-training for Language-guided Navigation](https://mlsanity.com/paper/2212.04385/) (2022)
- [SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigation](https://mlsanity.com/paper/2410.08189/) (2024)
- [Dense Reward for Free in Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2402.00782/) (2024)
- [SPA-RL: Reinforcing LLM Agents via Stepwise Progress Attribution](https://mlsanity.com/paper/2505.20732/) (2025)
- [VLN-R1: Vision-Language Navigation via Reinforcement Fine-Tuning](https://mlsanity.com/paper/2506.17221/) (2025)
- [UniGoal: Towards Universal Zero-shot Goal-oriented Navigation](https://mlsanity.com/paper/2503.10630/) (2025)
- [Nav-R1: Reasoning and Navigation in Embodied Scenes](https://mlsanity.com/paper/2509.10884/) (2025)
- [VLM See, Robot Do: Human Demo Video to Robot Action Plan via Vision Language Model](https://mlsanity.com/paper/2410.08792/) (2024)
- [End-to-End Navigation with Vision Language Models: Transforming Spatial Reasoning into Question-Answering](https://mlsanity.com/paper/2411.05755/) (2024)
- [OctoNav: Towards Generalist Embodied Navigation](https://mlsanity.com/paper/2506.09839/) (2025)
- [CogNav: Cognitive Process Modeling for Object Goal Navigation with LLMs](https://mlsanity.com/paper/2412.10439/) (2024)
- [Mem2Ego: Empowering Vision-Language Models with Global-to-Ego Memory for Long-Horizon Embodied Navigation](https://mlsanity.com/paper/2502.14254/) (2025)
- [CompassNav: Steering From Path Imitation To Decision Understanding In Navigation](https://mlsanity.com/paper/2510.10154/) (2025)

## Built on by (most cited first, 3 of 3)

- [AdaptVision: Efficient Vision-Language Models via Adaptive Visual Acquisition](https://mlsanity.com/paper/2512.03794/) (2025)
- [VerNav: Verifier-First Low-Latency Vision-and-Language Navigation](https://mlsanity.com/paper/2609.00920/) (2026)
- [Seek Before You Move: Evidence Seeking for Progress Grounding in Vision-Language Navigation](https://mlsanity.com/paper/2609.37353/) (2026)

## Abstract (arXiv)

Existing Vision-Language Navigation (VLN) agents based on Large Vision-Language Models (LVLMs) often suffer from perception errors, reasoning errors, and planning errors, which significantly hinder their navigation performance. To address these limitations, a novel VLN agent framework, named SeeNav-Agent, is proposed in this work. First, to reduce perception hallucinations of the visual module of the VLN agent, a dual-view Visual Prompt (VP) technique is introduced in the input space, which can also improve the agent's understanding of current spatial states. Subsequently, a novel step-level Reinforcement Fine-Tuning (RFT) method, Step Reward Group Policy Optimization (SRGPO), is designed for the post-training of VLN agents. In SRGPO, we first define verifiable process rewards for the navigation task, and then perform efficient step-level advantage estimation by randomly grouping different navigation steps. SRGPO provides dense reward signals for the reinforcement learning process of the VLN agent and enhances its planning capability. Experimental results on the EmbodiedBench Navigation benchmark indicate that by introducing the zero-shot VP module, the GPT-4.1 achieves a navigation success rate of 86.7%, surpassing the current best LVLM by approximately 20 percentage points (pp). Through post-training based on SRGPO, the Qwen2.5-VL-3B model reaches a navigation success rate of 72.3%, outperforming the best existing LVLM model by 5.6 pp. Moreover, compared to RFT algorithms such as GRPO and GiGPO, the proposed SRGPO demonstrates significant improvements in training stability, convergence efficiency, and generalization capability.