BMAM: Brain-inspired Multi-Agent Memory Framework

ACL ARR 2026 January Submission4297 Authors

Keywords: long-term memory, brain-inspired architecture, multi-agent systems, temporal reasoning, memory consolidation

Abstract: Language-model-based agents operating over extended interaction horizons face persistent challenges in preserving temporally grounded information and maintaining behavioral consistency across sessions, a failure mode we term "soul erosion." We present BMAM (Brain-inspired Multi-Agent Memory), a general-purpose memory architecture that models agent memory as a set of functionally specialized subsystems rather than a single unstructured store. Inspired by cognitive memory systems, BMAM decomposes memory into episodic, semantic, salience-aware, and control-oriented components that operate at complementary time scales. To support long-horizon reasoning, BMAM organizes episodic memories along explicit timelines and retrieves evidence by fusing multiple complementary signals. Experiments on the LoCoMo benchmark show that BMAM achieves 78.45% accuracy under the standard long-horizon evaluation setting, and ablation analyses confirm that the hippocampus-inspired episodic memory subsystem plays a critical role in temporal reasoning.

Paper Type: Long

Research Area: AI/LLM Agents

Research Area Keywords: Dialogue and Interactive Systems, NLP Applications,

Contribution Types: NLP engineering experiment

Languages Studied: English

Submission Number: 4297