Metraipolis › archive › dc_cee5a7d5e2bd

Agent Memory with Episodic Retrieval for Financial Decision-Making — arXiv:2609.28771

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.28771
License (as archived)
CC0-1.0
Archived
2026-10-08T04:25:41.506Z
SHA-256 of the archived text
a2a4f56dcf0c31a35da904e142ecfbac2226d4ce37446704c684a80aca1dc94d
Stable URL of this page
https://metraipolis.com/documento/dc_cee5a7d5e2bd

How to cite

Agent Memory with Episodic Retrieval for Financial Decision-Making — arXiv:2609.28771 — arXiv (en), https://arxiv.org/abs/2609.28771 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cee5a7d5e2bd (Metraipolis archive dc_cee5a7d5e2bd, sha256 a2a4f56dcf0c31a35da904e142ecfbac2226d4ce37446704c684a80aca1dc94d)
BibTeX
@misc{dccee5a7d5e2bd,
  title = {Agent Memory with Episodic Retrieval for Financial Decision-Making — arXiv:2609.28771},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.28771},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cee5a7d5e2bd; sha256 a2a4f56dcf0c31a35da904e142ecfbac2226d4ce37446704c684a80aca1dc94d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.28771. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models (LLMs) have demonstrated strong capabilities in financial analysis and reasoning, inspiring recent advances in agent-based trading frameworks. While these systems show promise, prior approaches either emphasize long-horizon forecasting or operate as stateless analyzers, limiting their applicability to the demands of trading in complicated settings. To address these gaps, we introduce META (Memory Enhanced Trading Agent), the first RAG-like episodic-memory-augmented multi-agent framework for financial decision making. META integrates a family of specialized indicator agents (e.g., Trend, MACD, Stochastic, RSI, SMA, AVWAP, Heikin-Ashi) with a Decision Agent that fuses their reports, and a Memory module that retrieves and updates past trading episodes encoded as market state embeddings with outcomes and reflections. By recalling relevant experiences and adaptively reweighting signals under similar market regimes, META achieves improved directional accuracy and robustness under short-horizon evaluation. Our results demonstrate that episodic memory provides a powerful mechanism for regime-aware, interpretable, and low-latency decision-making in trading and decision making. The code of this project is released on GitHub.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.28771 — 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 2026-10-08T03:50:57.674Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).