← Back to all news
arXiv Machine Learning

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.

Related stories

arXiv Machine Learning
Oct 19

Learning Agentic Time Series Forecasting via Trajectory Distillation and Memory-Based Reinforcement Learning

The paper introduces Cast‑R1, an 8‑billion‑parameter agentic forecasting model that learns to orchestrate analytical and prediction tools through trajectory distillation and multi‑turn reinforcement learning with structured memory. The training pipeline first generates multi‑turn interaction trajectories using a teacher LLM, then fine‑tunes the agent with supervised learning and group relative policy optimization, guided by rewards for accuracy and temporal structure. Experiments across several datasets show that Cast‑R1 effectively equips smaller language models with tool‑augmented, multi‑turn forecasting capabilities within structured workflows.

By Xiaoyu Tao, Mingyue Cheng, Yaguo Liu, Xingpeng Gao, Qingsong Wen, Shijin Wang, Enhong chen
llmsagentsreinforcement-learningfine-tuningefficiency
More like this →
arXiv AI
Aug 5

CastFSR: A Fast--Slow--Reflect Agentic Reasoning Framework for Context-Aware Time Series Forecasting

arXiv:2608. 03031v1 Announce Type: new Abstract: Time series forecasting is fundamental to decision-making in complex systems, where future dynamics are influenced not only by historical observations but also by evolving contextual features.

By Xiaoyu Tao, Mingyue Cheng, Bokai Pan, Chuang Jiang, Huanjian Zhang, Tian Gao, Yaguo Liu, Qi Liu, Enhong Chen
llmsagentsreinforcement-learningfine-tuning
More like this →
arXiv Machine Learning
Oct 5

MACTS-EM: Multi-Agent Collaborative Time Series Forecasting with Emergent Memory

MACTS-EM is a new multi‑agent framework for time series forecasting that combines domain‑specialised agents, a meta‑cognitive allocation layer, emergent memory for cross‑domain transfer, multimodal context integration, and adversarial robustness. The authors evaluate the system on financial, climate, energy, and pandemic data, reporting 8‑12% higher accuracy, 22‑27% better zero‑shot transfer, 16‑21% greater resilience to regime shifts, and 15‑18% faster recovery from distribution changes compared to existing methods. These results suggest that collaborative, agent‑based approaches can outperform traditional architectures in complex, real‑world forecasting tasks.

By Ahmad Shahi, Mamehgol Yousefi
agentsmultimodalsafety
More like this →
arXiv AI
Oct 19

CastFlow: Bridging Evidence Acquisition and Accurate Prediction in Agentic Time Series Forecasting

CastFlow is a role‑specialized agentic forecasting framework that combines general‑purpose tool reasoning with specialized temporal forecasting. It uses an Experience Memory to guide a frozen LLM in acquiring evidence via a multi‑view toolkit, then a lightweight specialized LLM refines predictions through evidence‑grounded reasoning. The two‑stage training strategy—supervised fine‑tuning followed by reinforcement learning with verifiable rewards—optimizes the specialized model based on final forecasting outcomes, achieving superior performance on nine out of ten real‑world benchmarks.

By Bokai Pan, Mingyue Cheng, Xiaoyu Tao, Zhiding Liu, Shuo Yu, Yuchong Wu, Qi Liu, Defu Lian, Enhong Chen
llmsagentsreinforcement-learningfine-tuningbenchmarks
More like this →
arXiv AI
Aug 18

ReasonCast: Agentic Demand Forecasting with Selective Semantic Reasoning

arXiv:2608. 15291v1 Announce Type: new Abstract: Demand forecasting increasingly requires combining two complementary sources of information: historical sales reveal recurring numerical dynamics, while future promotions, holidays, price changes, and platform interventions provide forward-looking knowledge.

By Ziyue Yang, Chaolin Xu, Yijing Wang, Tiankai Gu, Hui Yang, Yanhong Lin, Kaiyuan Liu, Fei Xiao
agentsreinforcement-learningfine-tuning
More like this →