Score: 1

Episodic Memory in Agentic Frameworks: Suggesting Next Tasks

Published: November 21, 2025 | arXiv ID: 2511.17775v1

By: Sandro Rama Fiorini , Leonardo G. Azevedo , Raphael M. Thiago and more

BigTech Affiliations: IBM

Potential Business Impact:

Helps AI remember past work to suggest new ideas.

Business Areas:
Artificial Intelligence Artificial Intelligence, Data and Analytics, Science and Engineering, Software

Agentic frameworks powered by Large Language Models (LLMs) can be useful tools in scientific workflows by enabling human-AI co-creation. A key challenge is recommending the next steps during workflow creation without relying solely on LLMs, which risk hallucination and require fine-tuning with scarce proprietary data. We propose an episodic memory architecture that stores and retrieves past workflows to guide agents in suggesting plausible next tasks. By matching current workflows with historical sequences, agents can recommend steps based on prior patterns.

Country of Origin
🇺🇸 United States

Page Count
6 pages

Category
Computer Science:
Multiagent Systems