# Stale, Misattributed, or Late: Where Personal Memory Fails Before Generation

arXiv: https://arxiv.org/abs/2610.10265 · HTML: https://mlsanity.com/paper/2610.10265/

## Key facts

- No citing papers in the map yet (data through 7 Oct 2026).
- Builds on 12 of its 28 references that are in the map.
- First posted on arXiv 7 Oct 2026.

## Builds on (most cited first, 12 of 12)

- [Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory](https://mlsanity.com/paper/2504.19413/) (2025)
- [LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory](https://mlsanity.com/paper/2410.10813/) (2024)
- [Zep: A Temporal Knowledge Graph Architecture for Agent Memory](https://mlsanity.com/paper/2501.13956/) (2025)
- [STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?](https://mlsanity.com/paper/2605.06527/) (2026)
- [Beyond Dialogue Time: Temporal Semantic Memory for Personalized LLM Agents](https://mlsanity.com/paper/2601.07468/) (2026)
- [Are We Ready For An Agent-Native Memory System?](https://mlsanity.com/paper/2606.24775/) (2026)
- [Temporal Validity in Retrieval Memory: Eliminating Stale-Fact Errors for AI Agents over Evolving Knowledge](https://mlsanity.com/paper/2606.26511/) (2026)
- [MemConflict: Evaluating Long-Term Memory Systems Under Memory Conflicts](https://mlsanity.com/paper/2605.20926/) (2026)
- [TOKI: A Bitemporal Operator Algebra for Contradiction Resolution in LLM-Agent Persistent Memory](https://mlsanity.com/paper/2606.06240/) (2026)
- [MemTrace: Probing What Final Accuracy Misses in Long-Term Memory](https://mlsanity.com/paper/2606.17328/) (2026)
- [AgentIR: A Workload-Adaptive Cascade Retrieval Substrate for Long-Term Conversational Memory](https://mlsanity.com/paper/2605.25092/) (2026)
- [MUSE: A Heterogeneity-Aware Multimedia Search Engine for Mobile SoCs](https://mlsanity.com/paper/2511.19192/) (2025)

## Abstract (arXiv)

Personal memory for language agents is usually judged by whether the final an- swer is correct. That score hides errors that arise before generation: the memory block may contain an obsolete value, a fact about the wrong person, or no use- ful fact before the serving deadline. We measure these failures directly. Using Personal Fact Memory (PFM) as a reference layer, we find that temporal validity is primarily a property of memory construction in our setting. On a controlled revision benchmark, serving only the active value of each correctly keyed slot eliminates observed stale exposure; without update resolution, 70.3% of prompts expose a superseded value. Once retrievers share the same active store and par- ticipant information, participant-aware BM25 is equivalent to the reference ranker within a prespecified 0.02 margin. The harder problem is assigning revisions to the right slot. Missed merges leave stale values active, whereas false merges silently remove current values; four LLM key assigners achieve higher key re- call than a rule extractor yet produce lower clean-retrieval rates, and open-domain merge recall on LongMemEval never exceeds 0.062. Misattribution survives va- lidity filtering: an entity posterior reduces same-name exposure on controlled data but cannot distinguish identically named speakers in LoCoMo. Two frozen lan- guage models reproduce prompt errors in generated text. Retrieval latency varies across rankers, but prompt prefill dominates turn-level latency on our hardware. These results argue for evaluating agent memory before generation, separating stored-state validity, identity resolution, abstention, and serving latency.