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

ICLR 2026 Conference Submission421 Authors

Keywords: Agent Memory, Memory System, Knowledge Representation

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 (\textit{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.
The source code of PISA and data of AggQA are available at \url{https://anonymous.4open.science/r/PISA-421/}

Primary Area: applications to neuroscience & cognitive science

Submission Number: 421