arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2604.19795cs.AI
收藏

Prism:一种多智能体开放发现的进化记忆基质

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

AI Researcher(人工智能研究员);Basel, Switzerland(瑞士巴塞尔)

Suyash Mishra

AI总结:

Prism通过整合四种独立发展范式,提出一种基于决策理论框架的记忆基质,实现记忆分层、因果记忆图、信息价值检索、心跳驱动整合和复制衰减动态,提升多智能体开放发现性能。

摘要:

我们引入Prism(概率检索与信息分层记忆),一种为多智能体AI系统进行开放发现设计的进化记忆基质。Prism将四个独立发展的范式——分层文件持久化、向量增强语义记忆、图结构关系记忆和多智能体进化搜索——统一到一个决策理论框架中,包含八个相互连接的子系统。我们做出了五个贡献:(1)一种基于香农信息含量的熵门分层机制,将记忆分配到三元枢纽(技能/笔记/尝试);(2)一个具有干预边和智能体属性溯源的因果记忆图G=(V, E_r, E_c);(3)一个具有自进化策略选择的值信息检索策略;(4)一个通过最优停止理论检测停滞的心跳驱动整合控制器;(5)一个将记忆置信度解释为进化适应度的复制衰减动态框架,证明收敛到进化稳定记忆集(ESMS)。在LOCOMO基准测试中,Prism实现了88.1 LLM-as-a-Judge分数(比Mem0高31.2%)。在CORAL风格的进化优化任务中,4智能体Prism比单智能体基线提高了2.8倍。

英文摘要:

We introduce \prism{} (\textbf{P}robabilistic \textbf{R}etrieval with \textbf{I}nformation-\textbf{S}tratified \textbf{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 \emph{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 \emph{causal memory graph} $\mathcal{G} = (V, E_r, E_c)$ with interventional edges and agent-attributed provenance; (3)~a \emph{Value-of-Information retrieval} policy with self-evolving strategy selection; (4)~a \emph{heartbeat-driven consolidation} controller with stagnation detection via optimal stopping theory; and (5)~a \emph{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$\times$ higher improvement rate than single-agent baselines.%

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑