Consistent Conversational State for Virtual Agents: Slot-Based Memory for Accurate Fact Retrieval
TL;DR
This work investigates whether memory interference originates mainly from memory retrieval or from the accumulation of competing fact versions added during memory updates, and evaluates how memory-write policies influence memory retrieval behavior later on.
Abstract
Long-term conversational agents rely on memory databases to ensure consistent user state across multiple interactions. Although prior work has analyzed retrieval-augmented generation and persistent memory for conversational agents, few studies have evaluated how memory-write policies influence memory retrieval behavior later on. We investigate whether memory interference originates mainly from memory retrieval or from the accumulation of competing fact versions added during memory updates. Three memory-write policies were evaluated in a controlled virtual patient dialogue environment. Append-only retrieval (NAIVE-SLOT), append-only retrieval with recency ranking (RECENT-SLOT), and slot-overwrite memory (SMART-SLOT) which maintains a single canonical value for each fact. Three clinical scenarios were implemented, consisting of 4,320 recall observations and 1,080 adversarial trap probes. SMART-SLOT achieved the highest recall accuracy, cross-session consistency, and demonstrated the greatest resistance to stale-fact prompts while with insignificant additional latency.