让智能体按需切换记忆模式，提升长时记忆问答准确率。
Supra Cognitive Modes: A Routed Architecture for Agent Memory
- 通过路由机制动态选择查询处理模式，统一管理多种记忆任务。
- 在三个基准上最高达86%准确率，对抗性拒绝任务也表现良好。
- 适合研究长期记忆、多跳推理或智能体架构的开发者参考。
智能体记忆任务包含直接事实查找、关系链推理和长期历史综合等不同需求。本文提出超认知模式（Supra Cognitive Modes, SCM）架构，将每条查询的处理模式（显式指定或自动选择）路由至共享的摄入底座上的检索与合成任务。该底座融合多粒度嵌入、抽取三元组、事实版本元数据及可选异步增强。通过运行时门控机制，查询被分发至融合词汇与密集检索、图结构或多跳处理、分层长文本生成等路径。在三个基准测试中验证：Long-term Conversational Memory（LoCoMo；n=1,986）、MemoryAgentBench（MAB；n=3,671）和LongMemEval（n=500）。参考运行结果在LoCoMo事实类别中达84.87%，对抗性拒绝任务为68.61%；MAB两次重复平均61.49%；LongMemEval达86.00%。代码仓库支持任务与模式相关的失败分析，但原始输出、端到端耗时及完整令牌日志未公开，部分运行决策记录缺失。结果呈现一种已实现的路由配置及其诊断性失败模式，源码验证了每查询控制接口与共享底座设计。因果路由效果、效率提升及统计显著性尚无证据支持。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。