Metraipolis › archive › dc_9aa1bdb2e7dc

WeEnv: The Environment for Agentic Reinforcement Learning at WeChat — arXiv:2609.30766

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.30766
License (as archived)
CC0-1.0
Archived
2026-10-08T02:04:50.607Z
SHA-256 of the archived text
83f9917ee34e566b13e7f2a6bf126889675d1fcd1337f45f415faaba80a84f86
Stable URL of this page
https://metraipolis.com/documento/dc_9aa1bdb2e7dc

How to cite

WeEnv: The Environment for Agentic Reinforcement Learning at WeChat — arXiv:2609.30766 — arXiv (en), https://arxiv.org/abs/2609.30766 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9aa1bdb2e7dc (Metraipolis archive dc_9aa1bdb2e7dc, sha256 83f9917ee34e566b13e7f2a6bf126889675d1fcd1337f45f415faaba80a84f86)
BibTeX
@misc{dc9aa1bdb2e7dc,
  title = {WeEnv: The Environment for Agentic Reinforcement Learning at WeChat — arXiv:2609.30766},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.30766},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9aa1bdb2e7dc; sha256 83f9917ee34e566b13e7f2a6bf126889675d1fcd1337f45f415faaba80a84f86},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30766. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Agentic reinforcement learning (RL) differs from conventional RL in that every task executes inside a complex environment, e.g., a virtual machine or a container. We find that agentic RL pays a heavy environment tax: a large share of the iteration time goes to the environment rather than to learning. The root cause is the lack of a full-lifecycle solution to environment management. We present WeEnv, which manages environments across packaging, initialization, and provisioning. WeEnv packages components as independently published layer groups and composes them at initialization, so that updating a component republishes one small group rather than every artifact containing it. To speed up environment initialization, WeEnv launches environments instantly and fetches contents on demand. During task execution, WeEnv provisions CPU and memory elastically, adjusting each environment's quota from its observed usage to fit the varying demands. WeEnv reduces the initialization by 5.6-14.2x over E2B, Docker, and AgentENV, cutting its share of the iteration time from up to 53.4% to 9.1%. WeEnv is deployed for agentic RL at WeChat.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-28 in cs.DC).
Categorie arXiv: Distributed, Parallel, and Cluster Computing (cs.DC).
Pagina del lavoro: https://arxiv.org/abs/2609.30766 — 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 2026-10-08T01:40:22.285Z dalla pagina https://arxiv.org/catchup/cs.DC/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).