arXiv Machine Learning
When Tomorrow Becomes Today: Self-Evolving Policies for Agentic Time-Series Forecasting
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Jun 2
Bridging the Last Mile of Time Series Forecasting with LLM Agents
arXiv:2606. 02497v1 Announce Type: new Abstract: Time series forecasting has advanced rapidly, especially with the emergence of foundation models that show strong zero-shot performance on numerical extrapolation.
arXiv AI
2d ago
When Should Forecasting Agents Reason? Behavioral Stress Tests for Reliability Routing
The paper investigates when forecasting agents should employ different behaviors—retrieval, reasoning, deferring to market priors, or using historical analogs—on binary forecasting tasks. It finds that the optimal mechanism depends on the data source, with structured analogs excelling for some processes and market or conservative baselines for others. The authors propose ReliabilityRoute, a rule‑based system that steers agent behavior using reliability features, achieving competitive performance across multiple LLM versions while highlighting that more reasoning is not always better.
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.
arXiv AI
Aug 5
Traceable Multi-Agent System for Knowledge-Based Forecasting
arXiv:2608. 03339v1 Announce Type: new Abstract: Enterprise forecasting increasingly relies on autonomous agents that interpret documents, search for data, generate code, and revise models.
arXiv AI
2d ago
Forecast-Dojo: Replayable Environments for Benchmarking and Training LLM Forecasting Agents
Forecast-Dojo is a replayable environment designed to benchmark and train large language model (LLM) forecasting agents. It integrates resolved prediction‑market questions with dated news, enabling agents to research events and revisit predictions at successive historical dates. The platform includes 1,568 Polymarket events, 18.8 million dated news articles, and supports repeated evaluation, training interactions, and outcome feedback, with evidence that research tools lower Brier scores across 12 tested models, though all models still lag behind historical market forecasts.
arXiv AI
Jun 30
Self-Evolving World Models for LLM Agent Planning
arXiv:2606. 30639v1 Announce Type: new Abstract: World models offer a principled way to equip long-horizon LLM agents with foresight: predictions of action consequences before execution.