Metraipolis › archive › dc_a098f2204bc3

WebCoder: Scaling General Frontend Development with Artifact-Grounded Agentic Reinforcement Learning — arXiv:2610.23104

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.23104
License (as archived)
CC0-1.0
Archived
2026-10-19T08:42:26.898Z
SHA-256 of the archived text
cf30ecd1bd1a29d471567156110668877a0dce933c841c5fdc2577ee2fb2442a
Stable URL of this page
https://metraipolis.com/documento/dc_a098f2204bc3

How to cite

WebCoder: Scaling General Frontend Development with Artifact-Grounded Agentic Reinforcement Learning — arXiv:2610.23104 — arXiv (en), https://arxiv.org/abs/2610.23104 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a098f2204bc3 (Metraipolis archive dc_a098f2204bc3, sha256 cf30ecd1bd1a29d471567156110668877a0dce933c841c5fdc2577ee2fb2442a)
BibTeX
@misc{dca098f2204bc3,
  title = {WebCoder: Scaling General Frontend Development with Artifact-Grounded Agentic Reinforcement Learning — arXiv:2610.23104},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.23104},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a098f2204bc3; sha256 cf30ecd1bd1a29d471567156110668877a0dce933c841c5fdc2577ee2fb2442a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.23104. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Real-world frontend development requires agents to compose reproduction, generation, modification, and repair over an evolving application state. Learning a general policy for this process requires translating heterogeneous execution feedback into task-aligned rewards and effective credit assignment across long sequences of interdependent actions. We introduce WebCoder, a general frontend development agent trained with artifact-grounded agentic reinforcement learning. Our key idea is to assess diverse development activities through their effects on a shared executable artifact and its satisfaction of task requirements. We build Webdev-World, an executable environment that integrates code editing, application execution, browser inspection, and on-demand skills while preserving project state across interactions. An independent verifier evaluates the final application against task requirements to provide terminal rewards, while changes in intermediate artifact progress redistribute the resulting rollout advantage across development segments. Context compaction and message-tree sample construction support training on trajectories beyond a single context window while avoiding repeated loss computation on shared generated history. We further introduce Webdev-Bench to evaluate composed development requirements within a single project. On Webdev-Bench, WebCoder-27B raises requirement satisfaction from 64.8 for its Qwen3.8-27B base model to 72.8, exceeding Claude-Opus-4.8 (65.1) and GPT-5.4 (59.6); on Vision2Web, it improves the average visual and functional score from 41.1 to 62.4, on par with Claude-Opus-4.8. Ablation studies confirm the contributions of artifact-grounded credit assignment and long-horizon training.

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/2610.23104 — 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 2026-10-19T08:39:10.060Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).