CauProphet：让智能体像人类一样形成因果认知
CauProphet: Teaching Agents to Develop Causal Cognition like Humans
一篇让智能体积累因果经验的论文，金融预测比基线高了 25.4%，做 Agent 记忆系统的可以看看思路。
CauProphet 是一个面向 LLM 智能体的因果认知框架，为每个任务构建包含因果因素和动作效果的 Causal Belief，并随新观察持续更新。在金融研究任务中，其与次日收益的平均秩相关性超越全部基线，较基线智能体提升 25.4%。在动态真实场景中，预测准确率从 21.3% 提升至 28.6%。实验覆盖科学任务与日常任务，验证其因果分析与动作选择能力。
CauProphet: Teaching Agents to Develop Causal Cognition like Humans
Large language model (LLM) agents increasingly support long-horizon tasks by leveraging external memory and past experience. However, existing agents mainly retrieve records or summaries, lacking the ability to form and refine causal understanding of the world. Inspired by human causal cognition, we introduce CauProphet, an agent that develops and updates causal knowledge within its Causal Cognition. For each task, CauProphet combines relevant knowledge in Causal Cognition with current evidence to construct a Causal Belief, a structured belief capturing causal factors and the effects of possible actions. It uses this belief for decision-making and continuously updates both the belief and Causal Cognition as new observations emerge, enabling causal knowledge that persists beyond individual experiences. Evaluations demonstrate that CauProphet progressively acquires causal knowledge and transfers it to future decision-making. In financial research, CauProphet leverages prior discoveries to improve downstream analyses and outperforms all baselines in mean rank correlation with next-day returns, achieving a 25.4% improvement over a baseline agent. It also improves prediction accuracy from 21.3% to 28.6% in dynamic real-world settings. Further experiments validate its ability to perform reliable causal analysis and action selection across scientific and everyday tasks, demonstrating the potential of causal experience learning for next-generation LLM agents.