ForecastCompass: Guiding Agentic Forecasting with Adaptive Factor Memory

2026-05-29 · Yurui Chang, Yongkang Du, Yuanpu Cao, Jinghui Chen, Lu Lin arxiv

Agentic forecasting is important for decision-making in dynamic environments, but it remains challenging because agents must reason from incomplete, time-limited evidence and produce calibrated probabilities before outcomes are resolved. Memory provides a natural mechanism for transferring experience from resolved forecasts to future prediction tasks. However, existing agent-memory methods are not tailored to forecasting, as they typically store past interactions, reflections, or factual associations without explicitly representing reusable predictive factors or calibration knowledge. We propose ForecastCompass (FoCo), an adaptive factor-based memory framework for agentic forecasting. FoCo organizes forecasting experience with a hierarchical forecasting-task taxonomy, enabling retrieval task-relevant forecasting knowledge. It maintains two complementary memory components: factor memory, which captures reusable predictive dimensions, and reasoning memory, which encodes probability updating, uncertainty handling, and calibration principles. Using retrospective analyses as learning signals, FoCo iteratively revises memory through a verbalized memory-revision procedure, enabling the agent to accumulate transferable forecasting knowledge over time. Experiments on Prophet Arena and FutureX with GPT-5-mini and Gemini-2.5-Flash show that FoCo improves both probabilistic accuracy and calibration.

📄 PDF Abstract BibTeX arXiv:2605.30858

Code (0)

등록된 구현이 없습니다.

Position: Beyond Model-Centric Prediction -- Agentic Time Series Forecasting

2026-02-02 · Mingyue Cheng, Xiaoyu Tao, Qi Liu, Ze Guo 외 arxiv

Time series forecasting has traditionally been formulated as a model-centric, static, and single-pass prediction problem that maps historical observations to future values. While this paradigm has driven substantial prog…

Time Series Forecasting Reinforcement Learning

CastFlow: Learning Role-Specialized Agentic Workflows for Time Series Forecasting

2026-04-30 · Bokai Pan, Mingyue Cheng, Zhiding Liu, Shuo Yu 외 arxiv

Recently, large language models (LLMs) have shown great promise in time series forecasting. However, most existing LLM-based forecasting methods still follow a static generative paradigm that directly maps historical obs…

Time Series Forecasting Reinforcement Learning

Adaptive tumor growth forecasting via neural & universal ODEs

2025-11-27 · Kavya Subramanian, Prathamesh Dinesh Joshi, Raj Abhijit Dandekar, Rajat Dandekar 외 arxiv

Forecasting tumor growth is critical for optimizing treatment. Classical growth models such as the Gompertz and Bertalanffy equations capture general tumor dynamics but may fail to adapt to patient-specific variability, …

FLAIRR-TS -- Forecasting LLM-Agents with Iterative Refinement and Retrieval for Time Series

2025-08-24 · Gunjan Jalori, Preetika Verma, Sercan Ö Arık arxiv

Time series Forecasting with large languagemodels (LLMs) requires bridging numericalpatterns and natural language. Effective fore-casting on LLM often relies on extensive pre-processing and fine-tuning.Recent studiesshow…

Time Series Forecasting Code Generation

From Failure Modes to Reliability Awareness in Generative and Agentic AI System

2025-10-24 · Janet, Lin, Liangwei Zhang arxiv

This chapter bridges technical analysis and organizational preparedness by tracing the path from layered failure modes to reliability awareness in generative and agentic AI systems. We first introduce an 11-layer failure…