WebGrader: Training LLMs for Web Development with Self-Evolving Programmatic Grader

• URL: http://arxiv.org/abs/2608.06474v1
• Date: Thu, 06 Aug 2026 18:06:12 GMT
• Title: WebGrader: Training LLMs for Web Development with Self-Evolving Programmatic Grader
• Abstract summary: 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.
• Score: 23.87868496043721
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models increasingly generate complete websites from natural-language descriptions, and reinforcement learning has become a central approach to closing their remaining functional gap. This training regime is bottlenecked by reward design. Hand-authored browser scripts are executable yet costly to write for open-ended requirements, while VLM and GUI-agent graders scale but may issue verdicts before observing the decisive state. We propose WebGrader, a self-evolving programmatic grader that autonomously derives the required interaction flows from each website request, represents each flow as an executable Flow Contract, and uses its execution outcome as an RL reward. 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 along the same browser trajectory. A residual-driven offline loop then discovers reusable verifier skills, screens them on disjoint validation pages, and freezes the promoted skill graph before policy training. By separating test planning, action grounding, evidence collection, and semantic judgment, WebGrader issues a Pass verdict only after observing the requested transition. 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. On WG-core-250, the policy reaches a Full Score of 44.953 and surpasses Qwen3-Coder-480B.

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)
• GTA: Generating Long-Horizon Tasks for Web Agents at Scale [82.43869456830664]
  We introduce a scalable framework, GTA, that integrates crawling, retrieval-based seeding, in-context generation, and automated quality control.<n>We instantiate the pipeline on over 50 websites covering e-commerce, government, forums, and news, with multilingual and multi-hop coverage.<n>Our contributions are three-fold: (i) formalizing multi-hop web-agent task generation, (ii) proposing an efficient and validated pipeline for automatic data creation, and (iii) releasing a dynamic benchmark with reproducible evaluation.
  arXiv  Detail & Related papers  (2026-05-28T01:05:50Z)
• 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)
• WebArbiter: A Principle-Guided Reasoning Process Reward Model for Web Agents [31.554790282560443]
  We introduce WebArbiter, a principle-inducing WebPRM that formulates reward modeling as text generation.<n>WebArbiter produces structured justifications that conclude with a preference verdict and identify the action most conducive to task completion.
  arXiv  Detail & Related papers  (2026-01-29T15:39:50Z)
• WebGen-Agent: Enhancing Interactive Website Generation with Multi-Level Feedback and Step-Level Reinforcement Learning [51.14454312533818]
  WebGen-Agent is a novel website-generation agent that leverages comprehensive and multi-level visual feedback.<n>We introduce textitStep-GRPO with Screenshot and GUI-agent Feedback to improve the ability of LLMs to act as the reasoning engine of WebGen-Agent.<n>WebGen-Agent increases the accuracy of Claude-3.5-Sonnet from 26.4% to 51.9% and its appearance score from 3.0 to 3.9, outperforming the previous state-of-the-art agent system.
  arXiv  Detail & Related papers  (2025-09-26T17:59:51Z)
• DeepDiver: Adaptive Search Intensity Scaling via Open-Web Reinforcement Learning [73.68685269970844]
  We introduce WebPuzzle, a training and 275-sample test benchmark that evaluates information seeking on the live internet.<n>We develop DeepDiver, a reinforcement-learning framework that cultivates Search Intensity Scaling (SIS)-an emergent ability to escalate search frequency and depth.<n>We detail DeepDiver's curriculum from cold-start SFT to a well designed RL procedure, and show that its seeking policy generalized from closed-ended queries to open-ended generation such as long-form writing.
  arXiv  Detail & Related papers  (2025-05-30T08:15:39Z)
• Steward: Natural Language Web Automation [19.301371856154965]
  Large language models (LLMs) have demonstrated exceptional capabilities in serving as the foundation for AI assistants. We introduce Steward, a novel LLM-powered web automation tool designed to serve as a cost-effective, scalable, end-to-end solution for automating web interactions. We discuss various design and implementation challenges, including state representation, action sequence selection, system responsiveness, detecting task completion, and caching implementation.
  arXiv  Detail & Related papers  (2024-09-23T18:06:32Z)
• 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.