Metraipolis › archive › dc_461cdff1ea87

Catalyzing Interactive HTML Generation Capabilities via High-Fidelity Reinforcement Learning — arXiv:2611.05151

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.05151
License (as archived): CC0-1.0
Archived: 2026-11-04T21:38:16.695Z
SHA-256 of the archived text: 402fc5f71b9fc521964e1b970ebdb6a1ae85268c7c98a39faf9c968b3ae8fc63
Stable URL of this page: https://metraipolis.com/documento/dc_461cdff1ea87

How to cite

Catalyzing Interactive HTML Generation Capabilities via High-Fidelity Reinforcement Learning — arXiv:2611.05151 — arXiv (en), https://arxiv.org/abs/2611.05151 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_461cdff1ea87 (Metraipolis archive dc_461cdff1ea87, sha256 402fc5f71b9fc521964e1b970ebdb6a1ae85268c7c98a39faf9c968b3ae8fc63)

BibTeX

@misc{dc461cdff1ea87,
  title = {Catalyzing Interactive HTML Generation Capabilities via High-Fidelity Reinforcement Learning — arXiv:2611.05151},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.05151},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_461cdff1ea87; sha256 402fc5f71b9fc521964e1b970ebdb6a1ae85268c7c98a39faf9c968b3ae8fc63},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.05151. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Generating HTML from natural-language specifications is an important application of code large language models (LLMs). Despite producing renderable pages, current models often fail to ensure functionality and visual quality during actual interaction. Existing methods typically target task-specific webpage supervision, leaving demanding interactive artifact optimization underexplored. Using mini-games as a challenging testbed, we expose limitations in interaction experience, reward signal, and credit assignment fidelity that are obscured by shallow webpage interactions. We introduce WebCatalyst, a browser-interaction reinforcement learning framework with three complementary components: a game-level GUI assessor for sustained interaction and evaluation, Visual Anchor for mitigating VLM reward hacking, and Action-Trace Credit for grounding token-level credit assignment in runtime execution traces. Trained on fewer than 1K requests, predominantly for games, WebCatalyst raises the Cookie-Bench Mini Games score from 68.8 to 75.3 and also the WebGen-Bench accuracy from 48.8 to 56.9 on Qwen3.6-35B-A3B, outperforming Claude Opus 4.7 in average rank across evaluated metrics. Further analysis shows that Visual Anchor prevents aesthetic degradation, while runtime-grounded credit assignment accelerates functional improvement. Together, our results show that improving feedback fidelity is the key to substantially advancing interactive HTML generation.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.05151 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-04T21:35:49.587Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).