让大模型与模拟环境动态进化，自动匹配任务难度提升智能体能力。
GenEnv: Difficulty-Aligned Co-Evolution Between LLM Agents and Environment Simulators
- 用生成式环境动态调整任务难度，贴合模型当前水平。
- 在5个基准上比70亿参数基线提升最高40.3%，媲美更大模型。
- 数据量仅需对手3.3分之一，适合资源有限的智能体训练。
训练高效的大语言模型智能体受限于真实交互数据的高成本与静态特性。本文提出GenEnv框架，实现智能体与可扩展生成式环境模拟器之间的难度对齐协同进化。不同于传统在静态数据集上训练的方法，GenEnv构建了动态数据生成机制：环境模拟器作为动态教学策略，持续生成针对智能体“最近发展区”的定制化任务。该过程由简单有效的α-课程奖励引导，使任务难度始终与智能体能力相匹配。我们在API-Bank、ALFWorld、BFCL、Bamboogle和TravelPlanner五个基准上评估，结果表明，GenEnv相较70亿参数基线性能提升最高达40.3%，并达到或超过更大模型的平均水平。相比基于Gemini 2.5 Pro的离线数据增强方法，其性能更优且数据使用量减少3.3倍。通过从静态监督转向自适应模拟，GenEnv为智能体能力的高效扩展提供了新路径。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。