Reimagining service delivery in the agentic era with Google Public Sector
cloud.google.com·21h ago
AI Research
arXiv CS.AI·May 25·8 min read
OnePred: Next-Query Prediction via Recursive Intent Memory in Multi-Turn Conversations
TL;DR
Conversational AI systems respond reactively to user queries but cannot anticipate what users will ask next. OnePred predicts the next user query by maintaining a compressed memory of the user's evolving intent rather than storing full dialogue history, reducing token consumption 22× while improving prediction accuracy.
✦ Why It Matters
Engineers can build more efficient conversational systems that anticipate user needs while reducing computational costs and token consumption.
Key Takeaways
- Utilize OnePred for proactive user query prediction.
- Adopt recursive intent memory to manage dialogue context efficiently.
- Leverage NQP-Bench for benchmarking conversational models.
- Reduce token consumption significantly in multi-turn dialogues.
How It Works
OnePred maintains a recursively updated memory that captures the user's intent trajectory, allowing it to predict future queries without needing to process the entire dialogue history. This approach focuses on unresolved needs and shifts in user interest, enabling efficient and accurate predictions.