PISA: A Pragmatic Psych-Inspired Unified Memory System for Enhanced AI Agency
This work addresses the problem of inflexible memory systems for AI agents, offering a novel approach that enhances adaptability and knowledge retention, though it appears incremental in building on existing cognitive theories and benchmarks.
The paper tackles the lack of adaptability and task-oriented focus in AI agent memory systems by proposing PISA, a psych-inspired unified memory system that introduces a trimodal adaptation mechanism and hybrid memory access architecture, achieving new state-of-the-art results on benchmarks like LOCOMO and AggQA.
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.