# AgentMemGate: Addressing Speculation Contamination in Conversational Assistant Memory

arXiv: https://arxiv.org/abs/2610.07707 · HTML: https://mlsanity.com/paper/2610.07707/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 28 references that are in the map.
- First posted on arXiv 6 Oct 2026.

## Builds on (most cited first, 24 of 24)

- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [Evaluating Very Long-Term Conversational Memory of LLM Agents](https://mlsanity.com/paper/2402.17753/) (2024)
- [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)
- [Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scale](https://mlsanity.com/paper/2504.14225/) (2025)
- [In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents](https://mlsanity.com/paper/2503.08026/) (2025)
- [How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behavior](https://mlsanity.com/paper/2505.16067/) (2025)
- [Keep Me Updated! Memory Management in Long-term Conversations](https://mlsanity.com/paper/2210.08750/) (2022)
- [HaluMem: Evaluating Hallucinations in Memory Systems of Agents](https://mlsanity.com/paper/2511.03506/) (2025)
- [STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?](https://mlsanity.com/paper/2605.06527/) (2026)
- [REALTALK: A 21-Day Real-World Dataset for Long-Term Conversation](https://mlsanity.com/paper/2502.13270/) (2025)
- [From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM Agents](https://mlsanity.com/paper/2606.04329/) (2026)
- [TiMem: Temporal-Hierarchical Memory Consolidation for Long-Horizon Conversational Agents](https://mlsanity.com/paper/2601.02845/) (2026)
- [Evaluating Long-Horizon Memory for Multi-Party Collaborative Dialogues](https://mlsanity.com/paper/2602.01313/) (2026)
- [Cordon: Semantic Transactions for Tool-Using LLM Agents](https://mlsanity.com/paper/2606.17573/) (2026)
- [Supersede: Diagnosing and Training the Memory-Update Gap in LLM Agents](https://mlsanity.com/paper/2606.27472/) (2026)
- [HorizonBench: Long-Horizon Personalization with Evolving Preferences](https://mlsanity.com/paper/2604.17283/) (2026)
- [ES-MemEval: Benchmarking Conversational Agents on Personalized Long-Term Emotional Support](https://mlsanity.com/paper/2602.01885/) (2026)
- [Chronos: Temporal-Aware Conversational Agents with Structured Event Retrieval for Long-Term Memory](https://mlsanity.com/paper/2603.16862/) (2026)
- [Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents](https://mlsanity.com/paper/2605.17830/) (2026)
- [ConsistencyGate: Preventing Memory Contamination in LLM Agents via Self-Consistency Admission Control](https://mlsanity.com/paper/2607.22962/) (2026)
- [TriggerBench: Investigating Prospective Memory for Large Language Models](https://mlsanity.com/paper/2606.23459/) (2026)
- [MemRouter: Memory-as-Embedding Routing for Long-Term Conversational Agents](https://mlsanity.com/paper/2605.00356/) (2026)

## Abstract (arXiv)

Conversational AI assistants with long-term memory extract facts from user messages into a store consulted in later conversations. A stated plan can enter that store as fact: a user who might move to Seattle may be recorded as already living there. We call this speculation contamination. Final-state memory benchmarks miss this error because they do not probe intermediate state and include few unresolved speculations. We present AgentMemGate, a write-time gate for profile-store memory that classifies extracted statements as speculation, completed event, correction, or other. Speculations remain outside memory, with conditions governing later promotion or deletion. We also contribute a dataset of multi-session conversations in which plans are confirmed, abandoned, or left unresolved. On our 147-conversation held-out set, Mem0 and Graphiti assert unresolved plans as current state for 35.2% and 27.3% of pending plans. On the core benchmark, AgentMemGate eliminates all observed contamination relative to the identical ungated pipeline (87.5% to zero for the most exposed extraction style) and raises task accuracy from 65% to 95%. On the harder held-out set, gated contamination is 3.4% to 5.7% and task accuracy rises by 9 to 13 percentage points. Our analysis identifies field matching as the main remaining bottleneck: realistic speculations often match no profile field and never reach the gate. We release our datasets, prompts, and evaluation code.