PISA: A Pragmatic Psych-Inspired Unified Memory System for Enhanced AI Agency

2025-10-12

AI Summary

Existing AI agent memory systems lack task adaptability and overlook the constructive, goal-directed nature of human memory. To address this, we propose a psychology-inspired unified memory architecture grounded in Piaget’s schema theory, featuring a schema-driven memory structure. We design a tri-modal adaptation mechanism—update, evolve, and create—to enable dynamic, context-sensitive memory evolution. Furthermore, we introduce a hybrid access paradigm that synergistically integrates symbolic reasoning with neural retrieval, supporting both structured inference and flexible similarity-based recall. The architecture natively incorporates continual learning, balancing memory organization consistency with retrieval flexibility. Evaluated on the LOCOMO benchmark and a newly introduced AggQA benchmark, our system achieves state-of-the-art performance, demonstrating significant improvements in memory adaptability, cross-task generalization, long-term knowledge retention, and retrieval efficiency.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Agent/AI Theories and Architectures
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Psychology-informed user models and recommender systems

Abstract

Memory systems are fundamental to AI agents, yet existing work often lacks adaptability to diverse tasks and overlooks the constructive and task-oriented role of AI agent memory. Drawing from Piaget's theory of cognitive development, we propose PISA, a pragmatic, psych-inspired unified memory system that addresses these limitations by treating memory as a constructive and adaptive process. To enable continuous learning and adaptability, PISA introduces a trimodal adaptation mechanism (i.e., schema updation, schema evolution, and schema creation) that preserves coherent organization while supporting flexible memory updates. Building on these schema-grounded structures, we further design a hybrid memory access architecture that seamlessly integrates symbolic reasoning with neural retrieval, significantly improving retrieval accuracy and efficiency. Our empirical evaluation, conducted on the existing LOCOMO benchmark and our newly proposed AggQA benchmark for data analysis tasks, confirms that PISA sets a new state-of-the-art by significantly enhancing adaptability and long-term knowledge retention.

Problem

• Enhancing AI agent adaptability across diverse tasks
• Addressing limitations in constructive task-oriented memory systems
• Improving memory retrieval accuracy and efficiency through hybrid architecture

Innovation

• Trimodal adaptation mechanism for continuous learning
• Hybrid memory architecture combining symbolic and neural retrieval
• Schema-grounded structures enabling flexible memory updates