Metraipolis › archive › dc_53e2baceea12

TeleGen: Improving LLM-Based Web Application Generation via Runtime Telemetry — arXiv:2610.04981

Source: arXiv
Original: https://arxiv.org/abs/2610.04981
License (as archived): CC0-1.0
Archived: 2026-10-06T05:26:36.623Z
SHA-256 of the archived text: 81ab20c0eef3c1c84dd036e0b3f6cb8000edf6d185b14bf1f98c5a556faf9d53
Stable URL of this page: https://metraipolis.com/documento/dc_53e2baceea12

How to cite

TeleGen: Improving LLM-Based Web Application Generation via Runtime Telemetry — arXiv:2610.04981 — arXiv, https://arxiv.org/abs/2610.04981 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_53e2baceea12 (Metraipolis archive dc_53e2baceea12, sha256 81ab20c0eef3c1c84dd036e0b3f6cb8000edf6d185b14bf1f98c5a556faf9d53)

BibTeX

@misc{dc53e2baceea12,
  title = {TeleGen: Improving LLM-Based Web Application Generation via Runtime Telemetry — arXiv:2610.04981},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.04981},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_53e2baceea12; sha256 81ab20c0eef3c1c84dd036e0b3f6cb8000edf6d185b14bf1f98c5a556faf9d53},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04981. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models can generate runnable web applications from natural-language requirements, but many generated applications still fail interactive tasks. Existing generate-execute-repair pipelines execute the generated application and use task outcomes or error messages to guide code revision. However, this feedback often misses the runtime behavior between a browser action and the final task outcome, making interaction-level failures difficult to diagnose. Therefore, we propose TeleGen, an observability-enhanced framework for LLM-based web application generation. TeleGen instruments generated applications, collects runtime telemetry during task execution, and compresses raw telemetry logs into concise briefs for repair. We evaluate TeleGen on WebGen-Bench and Web-Bench. On WebGen-Bench, TeleGen improves task success from 67.7% with repair without telemetry to 76.2%, an increase of 8.5 percentage points. On Web-Bench, it improves cumulative Pass@2 from 21.7% to 29.8%. Ablation results show that runtime telemetry provides a useful diagnostic signal, while telemetry briefs make this signal more effective and less costly to use. Further analysis shows that telemetry is especially helpful for failures involving hidden execution paths, such as navigation, form workflows, and frontend-backend coordination.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Software Engineering (cs.SE) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.04981 — 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 2026-10-06T05:24:05.952Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).