EpiEvolve: Self-Evolving Agents for Streaming Pandemic Forecasting under Regime Shifts

Computer Science > Artificial Intelligence COVID-19 e-print Important: e-prints posted on arXiv are not peer-reviewed by arXiv; they should not be relied upon without context to guide clinical practice or health-related behavior and should not be reported in news media as established information without consulting multiple experts in the field. [Submitted on 3 Jun 2026] EpiEvolve: Self-Evolving Agents for Streaming Pandemic Forecasting under Regime Shifts Yiming Lu, Sihang Zeng, Zhengxu Tang, Max Lau, Fei Liu, Wei Jin Epidemic LLM forecasters are usually trained and evaluated as static supervised models, whereas operational pandemic forecasting is a streaming process in which labels arrive after predictions and disease regimes shift over time. We study this mismatch in weekly COVID-19 hospitalization trend forecasting across five variant regimes. We introduce EpiEvolve, a self-evolving agent that wraps an LLM forecaster trained on the warm-start period and keeps its weights fixed during streaming. EpiEvolve adapts by storing forecast outcomes in a hierarchical episodic memory, reflecting on delayed labels, retrieving cases relevant to the current regime, and distilling recurring errors into strategic rules. The resulting context lets the forecaster reuse its own past predictions and outcomes in later weeks while following a chronological protocol that prevents future leakage. On the streaming dataset, EpiEvolve reaches 0.629 average accuracy, compared with 0.561 for the static backbone and 0.325 for the external CDC ensemble, and reduces recovery lag after regime shifts from 5 to 2 weeks. Ablations show that reflection, strategic memory, and regime-aware retrieval each contribute to the gains. Subjects: Artificial Intelligence (cs.AI); Computation and Language (cs.CL) Cite as: arXiv:2606.05513 [cs.AI]   (or arXiv:2606.05513v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2606.05513 Focus to learn more Submission history From: Yiming Lu [view email] [v1] Wed, 3 Jun 2026 23:40:30 UTC (297 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-06 Change to browse by: cs cs.CL References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)