LLM Digest

Story

arxiv_cs_lg · Sep 21, 2026 · paper

Source brief

When Tomorrow Becomes Today: Self-Evolving Policies for Agentic Time-Series Forecasting

arxiv.orgSep 21, 2026
original source linked

In brief

Agentic time series forecasting concerns systems whose underlying mechanisms evolve, making the relative effectiveness of numerical models, reasoning strategies, and intervention rules inherently time-varying. Consequ...

Feed lens

agenticeval

Read the original at arxiv.org →Open in live feed Read that day’s brief

When Tomorrow Becomes Today: Self-Evolving Policies for Agentic Time-Series Forecasting

Earlier in this thread 4 items

RATL: Learning from Retrieved Residuals for Robust Multivariate Time-Series Forecasting

When Does Online Adaptation Pay on the Edge? A Leakage-Free Evaluation of Warmup, Learning-Rate Selection, and Resource Trade-offs for Time-Series Forecasting

VISA: Agentic Self-Evolving Data Synthesis for Multimodal Instruction Following

EvoTS-Agent: A Self-Evolving LLM Agent for Financial Time Series Change Point Detection