Abstract
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.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Sharma, C., Fowlersmith, B., & Maamari, K. (2026). AgentMemGate: Addressing Speculation Contamination in Conversational Assistant Memory. https://omanscience.com/en/articles/agentmemgate-addressing-speculation-contamination-in-conversational-assistant-memory
MLA 9
Sharma, Chirag, et al. "AgentMemGate: Addressing Speculation Contamination in Conversational Assistant Memory." https://omanscience.com/en/articles/agentmemgate-addressing-speculation-contamination-in-conversational-assistant-memory.
Chicago (author–date)
Sharma, Chirag, Benjamin Fowlersmith, and Karime Maamari. 2026. "AgentMemGate: Addressing Speculation Contamination in Conversational Assistant Memory." https://omanscience.com/en/articles/agentmemgate-addressing-speculation-contamination-in-conversational-assistant-memory.
Harvard
Sharma, C., Fowlersmith, B. and Maamari, K. (2026) 'AgentMemGate: Addressing Speculation Contamination in Conversational Assistant Memory', Available at: https://omanscience.com/en/articles/agentmemgate-addressing-speculation-contamination-in-conversational-assistant-memory.
Vancouver
Sharma C, Fowlersmith B, Maamari K. AgentMemGate: Addressing Speculation Contamination in Conversational Assistant Memory. https://omanscience.com/en/articles/agentmemgate-addressing-speculation-contamination-in-conversational-assistant-memory
IEEE
C. Sharma, B. Fowlersmith, and K. Maamari, "AgentMemGate: Addressing Speculation Contamination in Conversational Assistant Memory," https://omanscience.com/en/articles/agentmemgate-addressing-speculation-contamination-in-conversational-assistant-memory.