语言智能体遇上因果性——桥接 LLM 与因果世界模型
Language Agents Meet Causality -- Bridging LLMs and Causal World Models
AI总结：
本文提出将因果表示学习与 LLM 结合的框架，通过可由自然语言查询的因果世界模型增强智能体推理与规划，并在多类任务中验证其优势。
摘要：
大型语言模型（LLM）近期在规划和推理应用中展现出巨大潜力。这些任务需要鲁棒的系统，而这可以说要求系统对环境具备因果理解。虽然 LLM 能够从预训练数据中获取并反思常识性因果知识，但这些信息往往是不完整、不正确的，或无法适用于特定环境。相比之下，因果表示学习（CRL）专注于识别给定环境中潜在的因果结构。我们提出一个将 CRL 与 LLM 相结合的框架，以实现具备因果意识的推理和规划。该框架学习一个因果世界模型，其中因果变量与自然语言表达式相连接。这种映射为 LLM 提供了灵活的接口，使其能够以文本形式处理并生成对动作和状态的描述。实际上，因果世界模型充当了一个模拟器，LLM 可以对其进行查询并与之交互。我们在跨越不同时间尺度和环境复杂度的因果推断与规划任务上评估了该框架。实验证明了该方法的有效性：这种具备因果意识的方法优于基于 LLM 的推理器，尤其是在更长的规划时域下。
英文摘要：
Large Language Models (LLMs) have recently shown great promise in planning and reasoning applications. These tasks demand robust systems, which arguably require a causal understanding of the environment. While LLMs can acquire and reflect common sense causal knowledge from their pretraining data, this information is often incomplete, incorrect, or inapplicable to a specific environment. In contrast, causal representation learning (CRL) focuses on identifying the underlying causal structure within a given environment. We propose a framework that integrates CRLs with LLMs to enable causally-aware reasoning and planning. This framework learns a causal world model, with causal variables linked to natural language expressions. This mapping provides LLMs with a flexible interface to process and generate descriptions of actions and states in text form. Effectively, the causal world model acts as a simulator that the LLM can query and interact with. We evaluate the framework on causal inference and planning tasks across temporal scales and environmental complexities. Our experiments demonstrate the effectiveness of the approach, with the causally-aware method outperforming LLM-based reasoners, especially for longer planning horizons.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
