AI Agent · China · Decrypt
AI Agents Are Learning to Predict What Users Want—Before They Ask for It
Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.
★ Tier-1 Source
Researchers at Shanghai Jiao Tong University and Chinese technology conglomerate Tencent claim to have built an AI agent that uses the quiet time between conversations to predict what users may ask next—and prepare answers before they ask.
Key facts
- According to the researchers, ProAct was tested in 200 simulations across 40 domains, including financial planning, software release management, and cybersecurity
- According to the paper, the system reduced conversation turns by 14.8% and cut follow-up requests by 11.7%
- Researchers acknowledged that the ProAct study had several limitations, including that in 3% of cases, the system made responses worse by bringing up irrelevant information
- The research comes as autonomous AI agents spread across the tech industry, with projects such as OpenClaw and Hermes Agent delivering persistent AI assistants that can handle longer, more
Summary
Researchers at Shanghai Jiao Tong University and Tencent developed ProAct, an AI agent designed to predict likely user needs before users ask. The system uses downtime between messages to review past conversations and prepare information in advance. Researchers said ProAct performed better than earlier proactive AI systems in benchmark testing, though the experiments did not involve real users. The system, called ProAct, works differently from most AI agents that wait for users to ask a question before responding.