In recent years, Large Language Models (LLMs) have demonstrated high reasoning capabilities, drawing attention for their applications as agents in various decision-making processes. One notably promising application of LLM agents is robotic manipulation. Recent research has shown that LLMs can generate text planning or control code for robots, providing substantial flexibility and interaction capabilities. However, these methods still face challenges in terms of flexibility and applicability across different environments, limiting their ability to adapt autonomously. Current approaches typically fall into two categories: those relying on environment-specific policy training, which restricts their transferability, and those generating code actions based on fixed prompts, which leads to diminished performance when confronted with new environments. These limitations significantly constrain the generalizability of agents in robotic manipulation. To address these limitations, we propose a novel method called EnvBridge. This approach involves the retention and transfer of successful robot control codes from source environments to target environments. EnvBridge enhances the agent's adaptability and performance across diverse settings by leveraging insights from multiple environments. Notably, our approach alleviates environmental constraints, offering a more flexible and generalizable solution for robotic manipulation tasks. We validated the effectiveness of our method using robotic manipulation benchmarks: RLBench, MetaWorld, and CALVIN. Our experiments demonstrate that LLM agents can successfully leverage diverse knowledge sources to solve complex tasks. Consequently, our approach significantly enhances the adaptability and robustness of robotic manipulation agents in planning across diverse environments.

翻译：近年来，大型语言模型（LLMs）展现出强大的推理能力，其作为智能体应用于各类决策过程备受关注。LLM智能体在机器人操作领域展现出尤为广阔的应用前景。近期研究表明，LLM能够为机器人生成文本规划或控制代码，提供显著的灵活性与交互能力。然而，现有方法在跨环境灵活性与适用性方面仍面临挑战，限制了其自主适应能力。当前研究主要分为两类：一类依赖环境特定的策略训练，其可迁移性受限；另一类基于固定提示生成代码动作，在面对新环境时性能显著下降。这些局限性严重制约了机器人操作智能体的泛化能力。为突破这些限制，我们提出了一种名为EnvBridge的创新方法。该方法通过保留源环境中的成功机器人控制代码并将其迁移至目标环境，利用多环境知识增强智能体在多样化场景中的适应性与性能。值得注意的是，本方法有效缓解了环境约束，为机器人操作任务提供了更灵活、更具泛化能力的解决方案。我们在机器人操作基准测试集RLBench、MetaWorld和CALVIN上验证了方法的有效性。实验表明，LLM智能体能够成功利用多样化知识源解决复杂任务。因此，本方法显著提升了机器人操作智能体在跨环境规划中的适应性与鲁棒性。