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

arXiv: https://arxiv.org/abs/2604.19795 · HTML: https://mlsanity.com/paper/2604.19795/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Agent memory systems, one of 16 directions in LLM agents and tool use.
- Builds on 4 of its 20 references that are in the map.
- First posted on arXiv 8 Apr 2026.

## Placed in

- LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/)

## Builds on (most cited first, 4 of 4)

- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory](https://mlsanity.com/paper/2504.19413/) (2025)
- [CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery](https://mlsanity.com/paper/2604.01658/) (2026)

## Built on by (most cited first, 1 of 1)

- [SEDIMA: Cross-Run Hierarchical Insight Memory for Evolutionary Search Agents](https://mlsanity.com/paper/2610.02361/) (2026)

## Abstract (arXiv)

We introduce prism (Probabilistic Retrieval with Information-Stratified Memory), 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, Er, Ec) 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 2.8× higher improvement rate than single-agent baselines.%