HTMLCure: Turning Browser Experience into State Guided Repair for Interactive HTML

• URL: http://arxiv.org/abs/2605.26807v1
• Date: Tue, 26 May 2026 10:22:56 GMT
• Title: HTMLCure: Turning Browser Experience into State Guided Repair for Interactive HTML
• Abstract summary: 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.
• Score: 33.943617790688556
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: LLMs can now produce full HTML pages, but many of those pages are only superficially correct: they render once, then fail under scroll, hover, click, resize, or gameplay. Evaluation from screenshots can miss these failures, and filtering discards many pages that are still repairable. We introduce HTMLCure, a browser experience framework that evaluates HTML after the system has interacted with it. The evaluator executes the page across viewports and interaction states, records deterministic browser evidence, and gives the VLM curated keyframes from the executed trajectory rather than isolated screenshots. The same state signal drives a closed loop repair engine: HTMLCure diagnoses the current page, chooses a state specific repair family, runs each candidate again, and exports quality cleared pages for SFT. On a 97K prompt corpus, this expands the directly usable seed into a candidate pool of 63703 quality cleared pages, from which we construct the final refined SFT set of 40K pages. Under the same backbone and training recipe, HTMLCure-27B-Refined reaches 50.6 on HTMLBench-400 with 45.2% deterministic test case pass, placing it in the same performance band as strong reference rows such as Kimi-K2.6 and GPT-5.4. On the released MiniAppBench validation split, it reaches 81.2 average, improving raw 27B SFT by 15.3 points and approaching the level of strong reference systems.

Related papers

• WebWorld: The Browser as a World Model for Self-Improving Web Code [34.5278922037561]
  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.
  arXiv  Detail & Related papers  (2026-08-31T10:00:12Z)
• 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)
• 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)
• From Bug Reports to Browser-Executable Procedures: An LLM-Driven Agent for Web GUI Bug Reproduction [1.746500363342869]
  ReBug is a context-aware agent system that reconstructs, executes, and validates browser-level reproduction procedures from web GUI bug reports.<n>We evaluate ReBug on 667 real-world bug reports from four open-source web applications.
  arXiv  Detail & Related papers  (2026-08-04T12:50:43Z)
• From Blind Edits to Verified Repair: Building Trustworthy User-Side LLM Agents for Web Accessibility [0.5872014229110213]
  A Chrome extension extracts a page's style sheets, condenses them to fit a local model's context window, and injects the result reversibly into the live page.<n>A dual-condition protocol measures harm as carefully as benefit, applied to six small open-weight models (7B to 14B) on ten violation-rich and ten highly accessible live sites.<n>A verified repair instrument pairs a trilingual seeded-violation benchmark with an audit-inject-verify loop that accepts a change only if violations strictly decrease.
  arXiv  Detail & Related papers  (2026-07-26T17:21:24Z)
• Domain-Conditioned Safety in Frontier Computer-Using Agents: A 793-Episode Browser Benchmark, a Coding-Domain Cross-Reference, and a Reproducibility Audit of Recent Red-Teaming [0.0]
  Recent computer-using-agent (CUA) red-teaming papers report prompt-injection attack success rates (ASR) of 42-98%.<n>We ask whether those techniques, reproduced as hand-crafted templates, still work against current frontier CUAs.
  arXiv  Detail & Related papers  (2026-06-03T01:21:59Z)
• WebRISE: Requirement-Induced State Evaluation for MLLM-Generated Web Artifacts [46.85286238215375]
  Existing benchmarks for MLLM-generated web artifacts assess interaction through local evidence.<n>We introduce WebRISE, which compiles task requirements into Interaction Contract Graphs.
  arXiv  Detail & Related papers  (2026-06-02T06:29:40Z)
• WCXB: A Multi-Type Web Content Extraction Benchmark [0.0]
  We introduce the Web Content Extraction Benchmark (WCXB), a dataset of 2,008 web pages from 1,613 domains.<n>The dataset includes a 1,497-page development set and a 511-page held-out test set with matched page type distributions.<n>We evaluate 13 extraction systems and find that while top systems converge on articles, performance diverges sharply on structured page types.
  arXiv  Detail & Related papers  (2026-05-20T12:28:12Z)
• How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings [56.70440596502351]
  The past year has seen over 20 open document parsing models, yet benchmarks almost exclusively on OmniDocBench.<n>We present PureDocBench, a benchmark thatrenders document images from HTML/CSS, covering 10 domains, 66 pages, and 1,475 pages.
  arXiv  Detail & Related papers  (2026-05-08T09:30:31Z)
• AICC: Parse HTML Finer, Make Models Better -- A 7.3T AI-Ready Corpus Built by a Model-Based HTML Parser [54.623900859999424]
  We introduce MinerU-HTML, a novel extraction pipeline that reformulates content extraction as a sequence labeling problem.<n>On MainWebBench, our benchmark of 7,887 annotated web pages, MinerU-HTML 81.8% ROUGE-N F1 compared to Trafilatura's 63.6%, with exceptional structured element preservation.
  arXiv  Detail & Related papers  (2025-11-20T14:15:23Z)
• MacroBench: A Novel Testbed for Web Automation Scripts via Large Language Models [10.977990951788422]
  We introduce MacroBench, a code-first benchmark that evaluates whether LLMs can synthesize reusable browser-automation programs (macros) from natural-language goals by reading HTML/DOM and emitting Selenium.<n> MacroBench instantiates seven self-hosted sites covering 681 tasks across interaction complexity and targeting difficulty.<n>Across 2,636 model-task runs, we observe stratified success: GPT-4o-mini (96.8%), GPT-4o (95.3%), Gemini (89.0%), DeepSeek (83.4%)
  arXiv  Detail & Related papers  (2025-10-05T21:15:11Z)
• Decoding Latent Attack Surfaces in LLMs: Prompt Injection via HTML in Web Summarization [1.3537117504260623]
  Large Language Models (LLMs) are increasingly integrated into web-based systems for content summarization.<n>This study explores how non-visible HTML elements can be exploited to embed adversarial instructions without altering the visible content of a webpage.
  arXiv  Detail & Related papers  (2025-09-06T21:05:18Z)
• HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems [62.36019283532854]
  Retrieval-Augmented Generation (RAG) has been shown to improve knowledge capabilities and alleviate the hallucination problem of LLMs.<n>We propose RAG, which uses HTML instead of plain text as the format of retrieved knowledge in RAG.
  arXiv  Detail & Related papers  (2024-11-05T09:58:36Z)
• AutoScraper: A Progressive Understanding Web Agent for Web Scraper Generation [54.17246674188208]
  Web scraping is a powerful technique that extracts data from websites, enabling automated data collection, enhancing data analysis capabilities, and minimizing manual data entry efforts. Existing methods, wrappers-based methods suffer from limited adaptability and scalability when faced with a new website. We introduce the paradigm of generating web scrapers with large language models (LLMs) and propose AutoScraper, a two-stage framework that can handle diverse and changing web environments more efficiently.
  arXiv  Detail & Related papers  (2024-04-19T09:59:44Z)

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.