# WebSight: A Vision-First Architecture for Robust Web Agents

arXiv: https://arxiv.org/abs/2508.16987 · HTML: https://mlsanity.com/paper/2508.16987/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 30 of its 65 references that are in the map.
- First posted on arXiv 23 Aug 2025.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

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

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [Rainbow: Combining Improvements in Deep Reinforcement Learning](https://mlsanity.com/paper/1710.02298/) (2017)
- [UI-TARS: Pioneering Automated GUI Interaction with Native Agents](https://mlsanity.com/paper/2501.12326/) (2025)
- [Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks](https://mlsanity.com/paper/2208.10442/) (2022)
- [ResNeSt: Split-Attention Networks](https://mlsanity.com/paper/2004.08955/) (2020)
- [WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models](https://mlsanity.com/paper/2401.13919/) (2024)
- [Predictability and Surprise in Large Generative Models](https://mlsanity.com/paper/2202.07785/) (2022)
- [Neural Episodic Control](https://mlsanity.com/paper/1703.01988/) (2017)
- [Model-Free Episodic Control](https://mlsanity.com/paper/1606.04460/) (2016)

## Built on by (most cited first, 8 of 8)

- [Auto-scaling Continuous Memory for GUI Agent](https://mlsanity.com/paper/2510.09038/) (2025)
- [From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI](https://mlsanity.com/paper/2606.14502/) (2026)
- [Planner Matters! An Efficient and Unbalanced Multi-agent Collaboration Framework for Long-horizon Planning](https://mlsanity.com/paper/2605.02168/) (2026)
- [Plover: Steering GUI Agents through Plan-Centric Interaction](https://mlsanity.com/paper/2607.15193/) (2026)
- [MetaCaptioner: Towards Generalist Visual Captioning with Open-source Suites](https://mlsanity.com/paper/2510.12126/) (2025)
- [Tuning Qwen2.5-VL to Improve Its Web Interaction Skills](https://mlsanity.com/paper/2604.09571/) (2026)
- [Agent JIT Compilation for Latency-Optimizing Web Agent Planning and Scheduling](https://mlsanity.com/paper/2605.21470/) (2026)
- [WebCraftBench: Evaluating Web Application Generation from a Software Testing Perspective](https://mlsanity.com/paper/2609.15387/) (2026)

## Abstract (arXiv)

We introduce WebSight, a vision-based autonomous web agent, designed to interact with web environments purely through visual perception, eliminating dependence on HTML or DOM-based inputs. Central to our approach we introduce our new model, WebSight-7B, a fine-tuned vision-language model optimized for UI element interaction, trained using LoRA on a web-focused subset of the Wave-UI-25K dataset. WebSight integrates this model into a modular multi-agent architecture, comprising planning, reasoning, vision-action, and verification agents, coordinated through an episodic memory mechanism. WebSight-7B achieves a top-1 accuracy of 58.84% on the Showdown Clicks benchmark, outperforming several larger generalist models while maintaining lower latency. The full WebSight agent achieves a 68.0% success rate on the WebVoyager benchmark, surpassing systems from labs such as OpenAI (61.0%) and HCompany (Runner H, 67.0%). Among tasks completed, WebSight answers correctly 97.14% of the time, indicating high precision. Together, WebSight and WebSight-7B establish a new standard for interpretable, robust, and efficient visual web navigation.