智能体时代中的因果发现
Causal Discovery in the Era of Agents
摘要
近期，人们试图将大型语言模型与因果发现技术相结合，让这些模型来推断成对关系、构建图结构，或者将语言模型的输出作为先验和约束条件。这些方法能够加快分析过程，但也可能掩盖某种因果证据究竟是基于数据与假设，还是基于文本关联、提示产生的结果以及虚构的机制。我们认为，在因果发现过程中，代理角色应该有所不同：代理应负责检查数据、获取上下文信息、解释方法中的假设，并明确图结构的输出结果，但不应提供边、方向、先验、约束或因果结论。我们提出这样的原则：代理应辅助整个工作流程，而因果判断则应基于数据、明确的假设、正式的算法、诊断结果以及用户或领域专家的决策。我们在causal-learn+平台上实现了这一原则——该平台能够协调数据分析、预处理、方法推荐、专家知识的整合、正式发现与解释等过程，从而服务于因果learn的算法体系。以Big Five人格数据为例，可以看到在代理辅助下进行的因果发现过程，同时避免了语言模型的不稳定性成为因果证据的来源。该平台可在causallearn.com上访问。
English Abstract
Recent attempts to combine large language models (LLMs) with causal discovery ask models to infer pairwise directions, propose graph structures, or inject language-model outputs as priors and constraints. These approaches promise faster analysis, but they also obscure whether a causal evidence is supported by data and assumptions or by textual associations, prompt artifacts and hallucinated mechanisms. We argue for a different role for agents in causal discovery. Agents should inspect data, retrieve context, explain method assumptions and clarify graph outputs, but they should not supply edges, orientations, priors, constraints or causal conclusions. We propose the principle that agents assist the workflow, while causal claims remain grounded in data, explicit assumptions, formal algorithms, diagnostics and user or domain-expert decisions. We instantiate this principle in causal-learn+, an online platform that coordinates data analysis, preprocessing, method recommendation, expert-knowledge incorporation, formal discovery and interpretation around the algorithmic ecosystem of causal-learn. A case study on Big Five personality data illustrates agent-assisted pipeline of causal discovery without turning language-model unreliability into causal evidence. The platform is available at causallearn.com.