← Back to all news
arXiv AI By Kaiwen Wu, Chaochao Lu

CauProphet: Teaching Agents to Develop Causal Cognition like Humans

Read the original on arXiv AI →

CauProphet is a new agent that learns and updates causal knowledge within a Causal Cognition framework. It constructs a structured Causal Belief for each task by combining relevant knowledge with current evidence, uses this belief for decision-making, and continuously refines both the belief and its underlying causal knowledge as new observations arrive. Experiments show that CauProphet progressively acquires causal knowledge, transfers it to future decisions, and outperforms baseline agents in financial prediction tasks and other scientific and everyday scenarios.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Jun 17

Closing the Feedback Loop: From Experience Extraction to Insight Governance in Verbal Reinforcement Learning

arXiv:2606. 17591v1 Announce Type: new Abstract: Training-free verbal reinforcement learning enables LLM agents to learn from world feedback -- objective signals such as dynamic task outcomes, market returns, or demand forecasts -- by extracting verbal rules from experience and injecting them as context, updating the agent's behavior without parameter changes.

By Yanwei Cui, Xing Zhang, Yulong Zhang, Li Shao, Xiaofeng Shi, Guanghui Wang, Peiyang He
llmsagentsreinforcement-learning
More like this →
arXiv AI
Oct 1

Reasoning Externalization for Faithful Large Language Model Narratives of Stock Return Predictions

The paper introduces a framework that uses large language models (LLMs) to generate natural‑language narratives explaining cross‑sectional stock return predictions. It combines temporal Shapley additive explanations (SHAP) from an XGBoost model with historical regime analogs to provide context. A controlled study shows that progressively externalizing numerical and relational reasoning improves evidence faithfulness and accuracy, while historical analogs boost human‑rated usefulness.

By Sujung Kim, Seung Hwan Cho, Sangjin Park, Young-Min Kim
llms
More like this →
arXiv Machine Learning
1d ago

ForecastCompass: Guiding Agentic Forecasting with Adaptive Factor Memory

ForecastCompass (FoCo) is an adaptive factor-based memory framework designed to enhance agentic forecasting. It structures forecasting experience using a hierarchical task taxonomy and maintains two memory components: factor memory for reusable predictive dimensions and reasoning memory for probability updating, uncertainty handling, and calibration. Through a verbalized memory-revision process guided by retrospective analyses, FoCo iteratively refines its knowledge, leading to improved probabilistic accuracy and calibration in experiments with GPT-5-mini and Gemini-2.5-Flash on Prophet Arena and FutureX.

By Yurui Chang, Yongkang Du, Yuanpu Cao, Jinghui Chen, Lu Lin
llmsagents
More like this →