Semantic XPath: Structured Agentic Memory Access for Conversational AI
This addresses memory scaling issues for conversational AI systems, though it appears incremental as it builds on existing RAG methods by adding structure.
The paper tackles the problem of inefficient memory access in conversational AI by proposing Semantic XPath, a tree-structured memory module, which improves performance over flat-RAG baselines by 176.7% while using only 9.1% of the tokens required by in-context memory.
Conversational AI (ConvAI) agents increasingly maintain structured memory to support long-term, task-oriented interactions. In-context memory approaches append the growing history to the model input, which scales poorly under context-window limits. RAG-based methods retrieve request-relevant information, but most assume flat memory collections and ignore structure. We propose Semantic XPath, a tree-structured memory module to access and update structured conversational memory. Semantic XPath improves performance over flat-RAG baselines by 176.7% while using only 9.1% of the tokens required by in-context memory. We also introduce SemanticXPath Chat, an end-to-end ConvAI demo system that visualizes the structured memory and query execution details. Overall, this paper demonstrates a candidate for the next generation of long-term, task-oriented ConvAI systems built on structured memory.