Metraipolis › archive › dc_b81d1faad5fb
EnvCraft: Synthesizing Executable Environments in Agentic RL for Claw-like Agent — arXiv:2609.05576
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.05576
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T12:49:48.225Z
- SHA-256 of the archived text
9c1211f25a9135656565aeacc6ae5bb62a4d40472158e028cde2292258317f12- Stable URL of this page
https://metraipolis.com/documento/dc_b81d1faad5fb
How to cite
EnvCraft: Synthesizing Executable Environments in Agentic RL for Claw-like Agent — arXiv:2609.05576 — arXiv (en), https://arxiv.org/abs/2609.05576 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b81d1faad5fb (Metraipolis archive dc_b81d1faad5fb, sha256 9c1211f25a9135656565aeacc6ae5bb62a4d40472158e028cde2292258317f12)
BibTeX
@misc{dcb81d1faad5fb,
title = {EnvCraft: Synthesizing Executable Environments in Agentic RL for Claw-like Agent — arXiv:2609.05576},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.05576},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b81d1faad5fb; sha256 9c1211f25a9135656565aeacc6ae5bb62a4d40472158e028cde2292258317f12},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.05576. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The paradigm of LLMs has rapidly shifted from passive language interfaces to autonomous Claw-like agents that execute long-horizon tasks across stateful workspaces. While Agentic Reinforcement Learning (Agentic RL) provides a promising path to optimize these agents, its scaling is heavily bottlenecked by the severe scarcity of interactive training environments. Existing synthetic environments are strictly limited to tool-calling endpoints, rendering them insufficient for accommodating the end-to-end real-world demands of claw-like agents. To bridge this gap, we introduce EnvCraft, an automated framework for synthesizing executable environments and scalable training data. Specifically, EnvCraft employs an environment synthesis engine to build sandbox-isolated workspaces, alongside a topology-aware data generation engine to produce coherent task trajectories. Overall, we synthesize 139 interactive environments comprising approximately 20K complex tasks for Agentic RL training. Experiments on Qwen3/3.5 models (8B-32B) show that our method yields gains of up to +11.9% on Claw-style benchmarks and +8.0% on general tool-use benchmarks, with concurrent reductions in inference token cost. The results confirm that synthesized executable environments provide robust and generalizable learning signals for training. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CL). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.05576 — 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 2026-10-16T12:30:25.234Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).