Metraipolis › archive › dc_bd315a2bc997

Self-Evolving Time-Series Forecasting Agents with Episodic Memory and Online Policy Learning — arXiv:2609.32689

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.32689
License (as archived): CC0-1.0
Archived: 2026-10-07T22:36:46.182Z
SHA-256 of the archived text: d396e1c41a6e28986578146f253fb8499ce2e3ed876ce7e7eb157cd357dd627a
Stable URL of this page: https://metraipolis.com/documento/dc_bd315a2bc997

How to cite

Self-Evolving Time-Series Forecasting Agents with Episodic Memory and Online Policy Learning — arXiv:2609.32689 — arXiv (en), https://arxiv.org/abs/2609.32689 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bd315a2bc997 (Metraipolis archive dc_bd315a2bc997, sha256 d396e1c41a6e28986578146f253fb8499ce2e3ed876ce7e7eb157cd357dd627a)

BibTeX

@misc{dcbd315a2bc997,
  title = {Self-Evolving Time-Series Forecasting Agents with Episodic Memory and Online Policy Learning — arXiv:2609.32689},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.32689},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bd315a2bc997; sha256 d396e1c41a6e28986578146f253fb8499ce2e3ed876ce7e7eb157cd357dd627a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32689. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

LLM-based agents are increasingly used for time-series forecasting because they can organise contextual information, perform multi-step analysis, and guide the sequence of actions required to complete forecasting tasks. Most existing agents focus only on the current forecasting instance. However, in real-world deployments, forecasting commonly operates online, with new forecasts issued from the currently available history as the forecast origin advances and the ground-truth targets of earlier instances progressively become available. These targets provide feedback on the actions taken in earlier instances, yet existing agents generally do not preserve or utilise this information to adapt their subsequent actions. To address this limitation, we introduce FASE, a Feedback-Aware Self-Evolving forecasting agent that converts such feedback into task-specific experience for subsequent forecasting instances. FASE combines episodic memory, which retrieves relevant completed instances, with online policy learning, which summarises the feedback accumulated across instances into ranking guidance. The proposed framework is evaluated on 29 dataset configurations selected from the GIFT-Eval benchmark. Across these 29 configurations, FASE attains the strongest aggregate point forecasting performance among the evaluated methods and reduces the normalised MAE by 9.1% relative to the best individual foundation model baseline. The results further indicate that the cumulative advantage of FASE increases as delayed feedback accumulates. Together, these findings demonstrate that FASE can continually self-evolve through feedback from completed forecasting instances without updating the parameters of the LLM.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.32689 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T22:14:27.743Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).