超认知模式：一种用于智能体记忆的路由架构

中文摘要 AI 辅助

智能体记忆工作负载混合了直接事实查找、关系链和当前状态推理，以及对长期历史的广泛综合。我们描述了超认知模式（SCM），一种将显式或自动选择的每个查询模式映射到通过一个共享摄取底层进行检索和综合负载的架构。一个冻结的语义分类器和运行时门在融合的词汇和密集查找、图或迭代多跳处理以及分层长格式综合之间分配查询。底层结合了多粒度嵌入、提取的三元组、事实版本元数据和可选的异步增强。我们在三个基准上对部署的配置进行了表征：长期对话记忆（LoCoMo；n = 1,986）、记忆智能体基准（MAB；n = 3,671）和长记忆评估（n = 500）。参考运行在LoCoMo事实类别的记录为84.87%，在对抗性弃权上为68.61%，在MAB的两次重复中为61.49%，在长记忆评估上为86.00%。一个由存储库支持的复制品产生了类似的综合分数，并支持任务和模式条件下的故障分析。原始基线输出、LoCoMo和长记忆评估的端到端对齐时间以及完整的令牌账本不可用；存储的行也省略了一些最终运行时决策。结果表征了一种实现的路由配置及其诊断故障模式，而源代码检查验证了每个查询控制接口和共享底层设计。因果路由效应、效率提升和统计显著性仍在现有证据之外。

英文摘要

Agent-memory workloads mix direct factual lookup, relation-chain and current-state reasoning, and broad synthesis over long histories. We describe Supra Cognitive Modes (SCM), an architecture that maps explicit or automatically selected per-query modes to retrieval and synthesis payloads over one shared ingest substrate. A frozen semantic classifier and runtime gates dispatch queries among fused lexical and dense lookup, graph or iterative multi-hop handling, and stratified long-form synthesis. The substrate combines multi-granularity embeddings, extracted triples, fact-version metadata, and optional asynchronous enrichments. We characterize the deployed configuration on three benchmarks: Long-term Conversational Memory (LoCoMo; n = 1,986), MemoryAgentBench (MAB; n = 3,671), and LongMemEval (n = 500). The reference run records 84.87% on LoCoMo factoid categories and 68.61% on adversarial abstention, 61.49% on MAB across two repetitions, and 86.00% on LongMemEval. A repository-backed reproduction produces similar aggregate scores and supports task- and mode-conditioned failure analysis. Raw baseline outputs, aligned end-to-end timing for LoCoMo and LongMemEval, and complete token ledgers are unavailable; stored rows also omit some final runtime decisions. The results characterize one implemented routed configuration and its diagnostic failure patterns, while source inspection verifies the per-query control interface and shared-substrate design. Causal routing effects, efficiency gains, and statistical significance remain outside the available evidence.

发表机构

• Supra Research（超研）

机构由 AI 辅助整理，请以论文原文为准。