{"ID":2826388,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.19682","arxiv_id":"2512.19682","title":"GenEnv: Difficulty-Aligned Co-Evolution Between LLM Agents and Environment Simulators","abstract":"Training capable Large Language Model (LLM) agents is critically bottlenecked by the high cost and static nature of real-world interaction data. We address this by introducing GenEnv, a framework that establishes a difficulty-aligned co-evolutionary game between an agent and a scalable, generative environment simulator. Unlike traditional methods that evolve models on static datasets, GenEnv instantiates a dataevolving: the simulator acts as a dynamic curriculum policy, continuously generating tasks specifically tailored to the agent's ``zone of proximal development''. This process is guided by a simple but effective $α$-Curriculum Reward, which aligns task difficulty with the agent's current capabilities. We evaluate GenEnv on five benchmarks, including API-Bank, ALFWorld, BFCL, Bamboogle, and TravelPlanner. Across these tasks, GenEnv improves agent performance by up to \\textbf{+40.3\\%} over 7B baselines and matches or exceeds the average performance of larger models. Compared to Gemini 2.5 Pro-based offline data augmentation, GenEnv achieves better performance while using 3.3$\\times$ less data. By shifting from static supervision to adaptive simulation, GenEnv provides a data-efficient pathway for scaling agent capabilities.","short_abstract":"Training capable Large Language Model (LLM) agents is critically bottlenecked by the high cost and static nature of real-world interaction data. We address this by introducing GenEnv, a framework that establishes a difficulty-aligned co-evolutionary game between an agent and a scalable, generative environment simulator...","url_abs":"https://arxiv.org/abs/2512.19682","url_pdf":"https://arxiv.org/pdf/2512.19682v2","authors":"[\"Jiacheng Guo\",\"Ling Yang\",\"Peter Chen\",\"Qixin Xiao\",\"Yinjie Wang\",\"Xinzhe Juan\",\"Jiahao Qiu\",\"Ke Shen\",\"Mengdi Wang\"]","published":"2025-12-22T18:57:13Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}