Bridging Reflective and Semantic Memory for Lifelong Learning in LLM-based Agents

AAMAS 2026 Workshop EMAS Submission28 Authors

Keywords: LLM agent, Memory-Augmented LLMs, Bidirectional Memory Interaction, Memory Pruning and Refinement

TL;DR: This article introduces a unified memory architecture for LLM agents in which reflection and semantic memories co-evolve to improve agents' lifelong learning capabilities.

Abstract: Large Language Model (LLM) agents increasingly rely on external memory to support long-term reasoning, adaptation, and generalization. While prior work has explored reflective memory for self-evaluation and semantic memory for storing abstract knowledge, the interaction between them remains underexplored. This article introduces a unified memory architecture in which reflection and semantic memory co-evolve to support lifelong learning. Reflection is used to evaluate and refine semantic memory through selective strengthening, stabilization, refinement, and forgetting, while semantic memory enriches the reflection process by grounding self-critique in accumulated knowledge. This bidirectional coupling enables more effective use of past experience and improves downstream decision-making. Experiments on the ARC Challenge dataset with the Phi-2 model show consistent improvements over baselines using isolated or loosely coupled memory mechanisms. Overall, our proposed approach advances the design of adaptive LLM-based agents capable of robust, long-horizon reasoning through tightly integrated, heterogeneous memory systems.

Paper Type: Regular paper

Demo: No, we do not plan to present a demo.

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 28