Metraipolis › archive › dc_c4cff3306a52
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
- 2026-11-04T18:35:27.872Z
- SHA-256 of the archived text
1cc1af83f381433ab054c8be6e79e6b5e32bb20ffd6f9cc250f85035eee7a000- Stable URL of this page
https://metraipolis.com/documento/dc_c4cff3306a52
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_c4cff3306a52 (Metraipolis archive dc_c4cff3306a52, sha256 1cc1af83f381433ab054c8be6e79e6b5e32bb20ffd6f9cc250f85035eee7a000)
BibTeX
@misc{dcc4cff3306a52,
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_c4cff3306a52; sha256 1cc1af83f381433ab054c8be6e79e6b5e32bb20ffd6f9cc250f85035eee7a000},
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 2026-11-04T18:32:37.357Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).