Episodic Memory in Agentic Frameworks: Suggesting Next Tasks
By: Sandro Rama Fiorini , Leonardo G. Azevedo , Raphael M. Thiago and more
Potential Business Impact:
Helps AI remember past work to suggest new ideas.
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.
Similar Papers
Narrative Memory in Machines: Multi-Agent Arc Extraction in Serialized TV
Multimedia
Helps computers understand TV show stories.
Beyond Task Completion: An Assessment Framework for Evaluating Agentic AI Systems
Multiagent Systems
Tests AI agents on how they work together.
Episodic Memories Generation and Evaluation Benchmark for Large Language Models
Computation and Language
Helps computers remember past events like people.