Prism: An Evolutionary Memory Substrate for Multi-Agent Open-Ended Discovery

arXiv:2604.19795v1 Announce Type: new Abstract: We introduce prism{} (extbf{P}robabilistic extbf{R}etrieval with extbf{I}nformation-extbf{S}tratified extbf{M}emory), an evolutionary memory substrate for multi-agent AI systems engaged in open-ended discovery. prism{} unifies four independently developed paradigms -- layered file-based persistence, vector-augmented semantic memory, graph-structured relational memory, and multi-agent evolutionary search -- under a single decision-theoretic framework with eight interconnected subsystems. We make five contributions: (1)~an entropy-gated stratification mechanism that assigns memories to a tri-partite hub (skills/notes/attempts) based on Shannon information content, with formal context-window utilization bounds; (2)~a causal memory graph G = (V, E_r, E_c) with interventional edges and agent-attributed provenance; (3)~a Value-of-Information retrieval policy with self-evolving strategy selection; (4)~a heartbeat-driven consolidation controller with stagnation detection via optimal stopping theory; and (5)~a replicator-decay dynamics framework that interprets memory confidence as evolutionary fitness, proving convergence to an Evolutionary Stable Memory Set (ESMS). On the LOCOMO benchmark, prism{} achieves 88.1 LLM-as-a-Judge score (31.2% over Mem0). On CORAL-style evolutionary optimization tasks, 4-agent prism{} achieves 2.8imes higher improvement rate than single-agent baselines.%

Related

• AEL: Agent Evolving Learning for Open-Ended Environments
• LSTM-MAS: A Long Short-Term Memory Inspired Multi-Agent System for Long-Context Understanding
• CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification
• Learning to Communicate: Toward End-to-End Optimization of Multi-Agent Language Systems

Source: arXiv cs.AI | 2026-04-23