# Mitigating Provenance-Role Collapse in Long-Term Agents via Typed Memory Representation

arXiv: https://arxiv.org/abs/2605.25869 · HTML: https://mlsanity.com/paper/2605.25869/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Agent memory systems, one of 16 directions in LLM agents and tool use.
- Builds on 22 of its 95 references that are in the map.
- First posted on arXiv 25 May 2026.

## Placed in

- LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/)

## Builds on (most cited first, 22 of 22)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [Zep: A Temporal Knowledge Graph Architecture for Agent Memory](https://mlsanity.com/paper/2501.13956/) (2025)
- [Titans: Learning to Memorize at Test Time](https://mlsanity.com/paper/2501.00663/) (2024)
- [Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions](https://mlsanity.com/paper/2507.05257/) (2025)
- [LightMem: Lightweight and Efficient Memory-Augmented Generation](https://mlsanity.com/paper/2510.18866/) (2025)
- [SimpleMem: Efficient Lifelong Memory for LLM Agents](https://mlsanity.com/paper/2601.02553/) (2026)
- [A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts](https://mlsanity.com/paper/2402.09727/) (2024)
- [ChatDB: Augmenting LLMs with Databases as Their Symbolic Memory](https://mlsanity.com/paper/2306.03901/) (2023)
- [Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agents](https://mlsanity.com/paper/2507.22925/) (2025)
- [Beyond a Million Tokens: Benchmarking and Enhancing Long-Term Memory in LLMs](https://mlsanity.com/paper/2510.27246/) (2025)
- [What Deserves Memory: Adaptive Memory Distillation for LLM Agents](https://mlsanity.com/paper/2508.03341/) (2025)
- [O-Mem: Omni Memory System for Personalized, Long Horizon, Self-Evolving Agents](https://mlsanity.com/paper/2511.13593/) (2025)
- [Beyond Static Summarization: Proactive Memory Extraction for LLM Agents](https://mlsanity.com/paper/2601.04463/) (2026)
- [HiMem: Hierarchical Long-Term Memory for LLM Long-Horizon Agents](https://mlsanity.com/paper/2601.06377/) (2026)
- [Active Context Compression: Autonomous Memory Management in LLM Agents](https://mlsanity.com/paper/2601.07190/) (2026)
- [TeleMem: Building Long-Term and Multimodal Memory for Agentic AI](https://mlsanity.com/paper/2601.06037/) (2025)
- [SwiftMem: Fast Agentic Memory via Query-aware Indexing](https://mlsanity.com/paper/2601.08160/) (2026)
- [Aeon: High-Performance Neuro-Symbolic Memory Management for Long-Horizon LLM Agents](https://mlsanity.com/paper/2601.15311/) (2026)

## Built on by (most cited first, 5 of 5)

- [When Memory Becomes Authority: Benchmarking Authority Collapse at the Memory Consolidation Boundary](https://mlsanity.com/paper/2608.01679/) (2026)
- [Stored Is Not Supported: Typed Provenance and Assertion Guardrails for Persistent AI Agents](https://mlsanity.com/paper/2609.02127/) (2026)
- [Silence Is Endorsement: Verification-Status Laundering in LLM Agent Pipelines](https://mlsanity.com/paper/2609.20211/) (2026)
- [Governed Persistent Memory: Source-Bound State Semantics and Fail-Closed Release for Long-Horizon Agents](https://mlsanity.com/paper/2608.12476/) (2026)
- [Memory Is a Derivation: The Distributed-Evidence Paradox in Long-Term Agents](https://mlsanity.com/paper/2609.36130/) (2026)

## Abstract (arXiv)

Long-term memory is essential for persistent LLM agents, yet prevailing architectures store historical interactions as unstructured, flat text. This unconstrained storage induces provenance-role collapse, a critical failure mode where agents suffer from source-monitoring errors. To resolve this cognitive vulnerability at the architectural level, we propose MemIR, a typed Memory Intermediate Representation that operationalizes source monitoring as a structural constraint. MemIR writes long-term memory into grounded atoms that separate raw evidence, retrieval cues, and truth-bearing claims, with factual authorization restricted to supported claim atoms. It then applies multi-route atomic projection and provenance-scoped utilization to transform heterogeneous retrieval hits into claim-centered candidate bundles and a normalized fact interface for answer generation. Experiments on LoCoMo and BEAM-100K demonstrate that MemIR consistently outperforms existing memory baselines, especially on tasks requiring source tracking, temporal grounding, and aggregation of fragmented evidence.