WebWorld: The Browser as a World Model for Self-Improving Web Code

• URL: http://arxiv.org/abs/2608.30530v1
• Date: Mon, 31 Aug 2026 10:00:12 GMT
• Title: WebWorld: The Browser as a World Model for Self-Improving Web Code
• Abstract summary: WebWorld lets a VLM prior interact with this browser-as-world-model autonomously.<n>WebWorld-27B improves Raw-27B by 5.3 points on HTMLBench-400 and 14.9 points on MiniAppBench-Val.
• Score: 34.5278922037561
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: VLM-driven self-improvement of web code has a structural flaw: the model that proposes the repair is the model that judges it, and visual plausibility under that judge is a poor proxy for whether the page actually works. What the loop is missing is a counterparty the VLM cannot fool, and the browser already is that counterparty: a deterministic, executable simulator of how an HTML artifact behaves under user actions, and in everything but name a world model for web code. We present WebWorld, the interface that lets a VLM prior interact with this browser-as-world-model autonomously and decides which interactions become supervision. Each round, the VLM emits a critique that the planner compiles into a typed interaction contract; the browser re-executes the candidate and issues an acceptance certificate only when both target progress and preservation of every previously verified capability hold; certified transitions accumulate as a quality ratchet that is the only thing the SFT export ever sees. Under matched training, WebWorld-27B improves Raw-27B by 5.3 points on HTMLBench-400 and 14.9 points on MiniAppBench-Val, and reaches the level of strong frontier systems such as Kimi-K2.6 and GPT-5.4 on interactive HTML generation. Equal-size ablations show that browser-backed admission carries the gain: without the certificate, the matched 9B lift nearly disappears.

Related papers

• Framework and Benchmark for Code-Driven Agentic Testing in Web Development [25.642063881090337]
  We introduce textbfCode-driven textbfAgentic textbfTesting (CAT), a paradigm in which the agent writes Playwright code to drive the browser, gathers feedback, and autonomously explores web applications to uncover bugs.<n>We instantiate CAT with CATJudge, an agentic framework that unifies Browser-Use and Computer-Use tools within a single environment and CATTest, a benchmark of 102 AI-generated web applications with carefully annotated bugs.
  arXiv  Detail & Related papers  (2026-08-31T10:07:51Z)
• BrowserForge: Scaling Web Episode via Parallel Browser Sandboxes [54.96895469970198]
  BrowserForge generates web interaction data at scale by driving many browser sandboxes in parallel over the open web.<n> BrowserForge couples three components: an open-web sourcing stage that exposes the agent to hundreds of thousands of real, openly reachable websites.<n>A rule-plus-model cleaning pipeline removes failed runs and rewrites the surviving reasoning into a single unified chain-of-thought style.
  arXiv  Detail & Related papers  (2026-08-25T17:35:42Z)
• Wuying-Browser-Agent: Real-World Centric Fundamental Long-Horizon Browser Agents [34.59625581903402]
  Wuying-Browser-Agent is a unified framework that addresses execution, supervision, optimization, and evaluation.<n>A structured browser harness provides stable execution primitives and decision-oriented context management.<n> BrowserBench is a benchmark of 350 tasks averaging 37.9 steps.
  arXiv  Detail & Related papers  (2026-08-18T03:23:31Z)
• WebGrader: Training LLMs for Web Development with Self-Evolving Programmatic Grader [23.87868496043721]
  We propose WebGrader, a self-evolving programmatic grader that autonomously derives the required interaction flows from each website request.<n>WebGrader materializes the generated project in a live browser, grounds target actions against the source code and live DOM, and collects visual, DOM, response, and persistent-state evidence.<n>On WebGen-Bench, WebGrader trains an 8B policy to a 52.01% functional success rate, outperforming a matched appearance-plus-script reward by 7.88 points and surpassing o4-mini and DeepSeek-v4-flash.
  arXiv  Detail & Related papers  (2026-08-06T18:06:12Z)
• HTMLCure: Turning Browser Experience into State Guided Repair for Interactive HTML [33.943617790688556]
  We introduce HTMLCure, a browser experience framework that evaluates HTML after the system has interacted with it.<n> HTMLCure diagnoses the current page, chooses a state specific repair family, runs each candidate again, and exports quality cleared pages for SFT.<n>On the released MiniAppBench validation split, it reaches 81.2 average, improving raw 27B SFT by 15.3 points.
  arXiv  Detail & Related papers  (2026-05-26T10:22:56Z)
• MolmoWeb: Open Visual Web Agent and Open Data for the Open Web [60.29597961827816]
  MolmoWebMix is a mixture of browser task demonstrations and web-GUI perception data.<n>MolmoWeb-8B is a family of fully open multimodal web agents.<n>We will release model checkpoints, training data, code, and a unified evaluation harness to enable open research on web agents.
  arXiv  Detail & Related papers  (2026-04-09T17:54:02Z)
• WebTestBench: Evaluating Computer-Use Agents towards End-to-End Automated Web Testing [57.7131457251794]
  We introduce WebTestBench, a benchmark for evaluating end-to-end automated web testing.<n>We decompose the testing process into two cascaded sub-tasks, checklist generation and defect detection, and propose WebTester.<n>Our findings expose a substantial gap between current computer-use agent capabilities and industrial-grade deployment demands.
  arXiv  Detail & Related papers  (2026-03-26T09:27:29Z)
• AutoWebWorld: Synthesizing Infinite Verifiable Web Environments via Finite State Machines [43.251303612671194]
  AutoWebWorld is a framework for synthesizing controllable and verifiable web environments.<n>Unlike real websites, where state transitions are implicit, AutoWebWorld explicitly defines all states, actions, and transition rules.<n>It generates over 11,663 verified trajectories from 29 diverse web environments at only $0.04 per trajectory.
  arXiv  Detail & Related papers  (2026-02-15T20:03:19Z)
• IWR-Bench: Can LVLMs reconstruct interactive webpage from a user interaction video? [56.33950760097989]
  IWR-Bench is a novel benchmark for evaluating the capabilities of Large Vision-Language Models (LVLMs) in interactive webpage reconstruction from video.<n>IWR-Bench comprises 113 meticulously curated tasks from 100 real-world websites, with 1,001 actions.<n>This benchmark evaluates models on two fundamental challenges: comprehensive multi-modal reasoning to infer interaction logic from video and assets, and advanced code generation to translate this logic into functional code.
  arXiv  Detail & Related papers  (2025-09-29T12:38:06Z)
• Fingerprinting web servers through Transformer-encoded HTTP response headers [0.0]
  We leverage state-of-the-art deep learning, big data, and natural language processing to enhance the detection of vulnerable web server versions. We conducted experiments by sending various ambiguous and non-standard HTTP requests to 4.77 million domains.
  arXiv  Detail & Related papers  (2024-03-26T17:24:28Z)
• A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis [69.15016747150868]
  We introduce WebAgent, an agent that learns from self-experience to complete tasks on real websites. WebAgent plans ahead by decomposing instructions into canonical sub-instructions, summarizes long HTML documents into task-relevant snippets, and acts on websites. We empirically demonstrate that our modular recipe improves the success on real websites by over 50%, and that HTML-T5 is the best model to solve various HTML understanding tasks.
  arXiv  Detail & Related papers  (2023-07-24T14:56:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.