mlsanityData to 7 Oct 2026

Supra Cognitive Modes: A Routed Architecture for Agent Memory

arXiv 2607.19096 ↗First posted 21 Jul 2026cs.AI cs.CLcited by 1

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 30 of its 36 references that are in the map. First posted on arXiv 21 Jul 2026.

Builds on

30 of 36 references.

References · 30

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  3. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  4. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  5. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  6. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  7. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  8. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,411
  9. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,295
  10. 2025A-MEM: Agentic Memory for LLM Agentscited by 1,000
  11. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 911
  12. 2024Evaluating Very Long-Term Conversational Memory of LLM Agentscited by 800
18 more
  1. 2023FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performancecited by 791
  2. 2025Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memorycited by 722
  3. 2024LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memorycited by 656
  4. 2024RouteLLM: Learning to Route LLMs with Preference Datacited by 633
  5. 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrievalcited by 519
  6. 2023Active Retrieval Augmented Generationcited by 506
  7. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 437
  8. 2023Cognitive Architectures for Language Agentscited by 422
  9. 2025Zep: A Temporal Knowledge Graph Architecture for Agent Memorycited by 372
  10. 2025Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactionscited by 236
  11. 2025LightMem: Lightweight and Efficient Memory-Augmented Generationcited by 163
  12. 2025MIRIX: Multi-Agent Memory System for LLM-Based Agentscited by 160
  13. 2025MemOS: A Memory OS for AI Systemcited by 129
  14. 2025MemBench: Towards More Comprehensive Evaluation on the Memory of LLM-based Agentscited by 82
  15. 2022Temporal Knowledge Graph Completion: A Surveycited by 61
  16. 2025Beyond a Million Tokens: Benchmarking and Enhancing Long-Term Memory in LLMscited by 52
  17. 2026AMA-Bench: Evaluating Long-Horizon Memory for Agentic Applicationscited by 46
  18. 2026LongMemEval-V2: Evaluating Long-Term Agent Memory Toward Experienced Colleaguescited by 17

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Contract Memory Compiler: Resolve, Then Traversecited by 0