arXiv:2608. 03689v1 Announce Type: new Abstract: Large language models are increasingly capable of synthesizing executable frontend projects, yet existing benchmarks still treat web generation as a static evaluation problem.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
arXiv:2609.15387v3 Announce Type: replace-cross Abstract: Human evaluation provides a direct measure of the quality of LLM-generated web applications. However, fitting human judgments through automat...
arXiv:2601. 02430v3 Announce Type: replace-cross Abstract: Web applications (web apps) have become a key arena for large language models (LLMs) to demonstrate their code generation capabilities and commercial potential.
arXiv:2609.15387v1 Announce Type: cross Abstract: Human evaluation provides a direct measure of the quality of LLM-generated web applications. However, fitting human judgments through automated evalu...
arXiv:2604. 18543v4 Announce Type: replace Abstract: Constructing environments for training and evaluating claw-like agents remains a manual, human-intensive process that does not scale.
The paper introduces KNOWS, a benchmark for evaluating web agents that act as assistants by retrieving, synthesizing, and presenting information across complex, multi-step browser tasks. It outlines a task design rubric, evaluation protocol combining deterministic checks with LLM judgments, and reports that current agents achieve only modest success, with the best performing agent succeeding on less than 3% of tasks. The study highlights significant gaps in agents’ tool use, visual understanding, and long‑horizon reasoning.
WatchPoint is a simulated‑user system that generates and runs diagnostic scripts against a live web application, producing structured observations to guide coding model retries. Unlike prior methods that rely on screenshots or non‑executable metrics, WatchPoint operates on Web‑Bench—a benchmark of 50 multi‑file web projects with 1,000 sequential tasks verified by deterministic end‑to‑end tests. It recovers 57.6% of diagnosed tasks, matching a human tester’s 54.5% recovery rate, and identifies when such simulated feedback is beneficial or should be withheld.