mlsanityData to 7 Oct 2026

From Lossy to Verified: A Provenance-Aware Tiered Memory for Agents

arXiv 2602.17913 ↗First posted 20 Feb 2026cs.DB cs.AIcited by 16

Not on the map. Why?

Abstract (arXiv)

Long-horizon agents often compress interaction histories into write-time summaries. This creates a fundamental write-before-query barrier: compression decisions are made before the system knows what a future query will hinge on. As a result, summaries can cause unverifiable omissions -- decisive constraints (e.g., allergies) may be dropped, leaving the agent unable to justify an answer with traceable evidence. Retaining raw logs restores an authoritative source of truth, but grounding on raw logs by default is expensive: many queries are answerable from summaries, yet raw grounding still requires processing far longer contexts, inflating token consumption and latency. We propose TierMem, a provenance-linked framework that casts retrieval as an inference-time evidence allocation problem. TierMem uses a two-tier memory hierarchy to answer with the cheapest sufficient evidence: it queries a fast summary index by default, and a runtime sufficiency router Escalates to an immutable raw-log store only when summary evidence is insufficient. TierMem then writes back verified findings as new summary units linked to their raw sources. On LoCoMo, TierMem achieves 0.851 accuracy (vs.0.873 raw-only) while reducing input tokens by 54.1% and latency by 60.7%.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 12 of its 22 references that are in the map. First posted on arXiv 20 Feb 2026.

Builds on

12 of 22 references.

References · 12

  1. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  2. 2024Evaluating Very Long-Term Conversational Memory of LLM Agentscited by 800
  3. 2025Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memorycited by 722
  4. 2023Extending Context Window of Large Language Models via Positional Interpolationcited by 721
  5. 2024LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memorycited by 656
  6. 2025Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactionscited by 236
  7. 2023SCM: Enhancing Large Language Model with Self-Controlled Memory Frameworkcited by 98
  8. 2025O-Mem: Omni Memory System for Personalized, Long Horizon, Self-Evolving Agentscited by 30
  9. 2025MemR3: Memory Retrieval via Reflective Reasoning for LLM Agentscited by 17
  10. 2024Verifiable Generation with Subsentence-Level Fine-Grained Citationscited by 15
  11. 2025Fast or Better? Balancing Accuracy and Cost in Retrieval-Augmented Generation with Flexible User Controlcited by 6
  12. 2025Goal-Directed Search Outperforms Goal-Agnostic Memory Compression in Long-Context Memory Taskscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 16.

16 papers.

Sort:

By area:

  1. 2026MemMark: State-Evolution Attribution Watermarking for Agent Long-Term Memory Systemscited by 12
  2. 2026Your Agents Are Aging Too: Agent Lifespan Engineering for Deployed Systemscited by 7
  3. 2026Retrieval-Augmented LLM Agents: Learning to Learn from Experiencecited by 6
  4. 2026D-Mem: A Dual-Process Memory System for LLM Agentscited by 5
  5. 2026EMBER: Efficient Memory via Budgeted Evidence Retention for Long-Horizon Agentscited by 5
  6. 2026TRUSTMEM: Learning Trustworthy Memory Consolidation for LLM Agents with Long-Term Memorycited by 5
  7. 2026When Stale Constraints Go Unchecked: Budgeted Verification Failures in Inherited Agent Memorycited by 3
  8. 2026A Frozen 12B Beats Frontier Models on Verified Work: 100% Accuracy, 0 Tokens, Bit-Exact, Forevercited by 2
  9. 2026Retrieval-Driven Memory Reconsolidation for Long-Term LLM Agentscited by 2
  10. 2026MEMOREPAIR: Barrier-First Cascade Repair in Agentic Memorycited by 1
  11. 2026EA-Graph: Artifact-Anchored Verification Memory for Coding Agents under Upstream Driftcited by 1
  12. 2026Plan Pointers and Record-Directive Form in Budgeted Verification of Inherited Agent Memorycited by 0
4 more
  1. 2026Silence Is Endorsement: Verification-Status Laundering in LLM Agent Pipelinescited by 0
  2. 2026Memory as Middleware for Self-Improving AI Agentscited by 0
  3. 2026Vestrum: Improving Agent Harnesses by Adapting Their Verification, Structure and Memorycited by 0
  4. 2026FORGE: Form-Optimal Routing of Grounded Evidence for Frozen LLM Agentscited by 0