The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
TimeRSI is a self‑improving deployment system for time‑series foundation models that automates the creation and refinement of forecasting pipelines. A coding agent translates task descriptions into executable changes, tests each revision on historical data, and uses error feedback to guide further revisions. During live deployment, an adaptive selector chooses the best pipeline based on completed forecasts under similar conditions, achieving superior performance on 198 tasks compared to all other submissions.
arXiv:2610.19725v1 Announce Type: new Abstract: Time-series foundation models provide strong zero-shot forecast, but deployment for real- world applications still requires task-specific designs for m...
Real-world time-series forecasting is rarely a one-shot model invocation: practitioners must formulate tasks, connect data and models, incorporate domain expertise, assess prediction plausibility, and...
MetaCaster is a meta-harness-optimized multi-agent framework that enables few-shot learning for lightweight time series forecasters. It uses agentic data generation to automatically train specialized forecasters from only a few examples and textual contexts, positioning agents as intermediary engineers rather than direct forecasters. Experiments on 18 datasets and 23 lightweight forecasters show that MetaCaster achieves data and computational efficiency while maintaining high forecasting quality.
Agentic time series forecasting concerns systems whose underlying mechanisms evolve, making the relative effectiveness of numerical models, reasoning strategies, and intervention rules inherently time...
arXiv:2609.24862v1 Announce Type: new Abstract: Agentic time series forecasting concerns systems whose underlying mechanisms evolve, making the relative effectiveness of numerical models, reasoning s...