{"slug": "envcraft-synthesizing-executable-environments-in-agentic-rl-for-claw-like-agent", "title": "EnvCraft: Synthesizing Executable Environments in Agentic RL for Claw-like Agent", "summary": "Researchers introduced EnvCraft, an automated framework that synthesizes executable environments and training data for Agentic Reinforcement Learning, detailed in arXiv paper 2609.05576v1. EnvCraft's environment synthesis engine builds sandbox-isolated workspaces and its topology-aware data generation engine produces coherent task trajectories, yielding 139 interactive environments with approximately 20,000 complex tasks. Experiments on Qwen3/3.5 models ranging from 8B to 32B parameters showed 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.", "body_md": "arXiv:2609.05576v1 Announce Type: new \nAbstract: 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.", "url": "https://wpnews.pro/news/envcraft-synthesizing-executable-environments-in-agentic-rl-for-claw-like-agent", "canonical_source": "https://arxiv.org/abs/2609.05576", "published_at": "2026-09-10 04:00:00+00:00", "updated_at": "2026-09-10 04:21:28.089970+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "ai-agents", "ai-research", "ai-tools"], "entities": ["EnvCraft", "Agentic Reinforcement Learning", "Qwen3", "Qwen3.5", "arXiv"], "alternates": {"html": "https://wpnews.pro/news/envcraft-synthesizing-executable-environments-in-agentic-rl-for-claw-like-agent", "markdown": "https://wpnews.pro/news/envcraft-synthesizing-executable-environments-in-agentic-rl-for-claw-like-agent.md", "text": "https://wpnews.pro/news/envcraft-synthesizing-executable-environments-in-agentic-rl-for-claw-like-agent.txt", "jsonld": "https://wpnews.pro/news/envcraft-synthesizing-executable-environments-in-agentic-rl-for-claw-like-agent.jsonld"}}