Agent improves task success by proactively asking better questions
Asking for What Was Never Requested: Horizontal and Vertical Proactivity in Agents
Artificial IntelligenceComputation and Language
Summary
Sometimes, helpers like chatbots wait for what you ask, but solving your problem might need information you didn’t think to request. The authors studied how smart agents can not only act on their own but also figure out what questions to ask next to get missing info. They created a method called Q&D that trains an agent to ask questions that help gather important details efficiently, without relying on extra judgment tools. This approach helps agents complete tasks better by knowing what and when to ask, and it works well on customer service and retail scenarios.
What this means in practice
- •For customer service teams: Improve virtual agents to complete customer requests more effectively by asking fewer but more relevant follow-up questions.$Commercial implications: Enables better-performing interactive customer service chatbots that increase task completion and reduce customer effort.
- •For retail support developers: Develop retail AI systems that proactively gather overlooked but needed information to finalize sales or support efficiently.
Authors
Ido Levy, Asaf Yehudai, Segev Shlomov, Asaf Adi, Leshem Choshen
Abstract
An agent that uses tools typically responds to what the user explicitly asks, yet completing the task may require information the user never requested. Work on proactive agents mainly studies whether and when an agent should act on its own, not what information it should pursue. We study a distinct axis of proactivity: its content. Horizontal proactivity pursues unstated information that the current context already identifies, and vertical proactivity pursues needs that only earlier evidence reveals. A need graph, recovered from a benchmark's own decomposition, records which needs depend on which, so both forms, and whether the agent stops at the right time, can be scored from a transcript without a model judge. To learn this behavior, we propose Q&D (questioner and drafter), which trains a questioner to prefer the question whose continuation retrieves more of the required evidence, with no reward model or judge. On held-out splits of three multi-hop question-answering benchmarks, at equal retrieval spend, the trained questioner improves both forms of proactivity over the same model, prompted, and outperforms a prompted model $15\times$ larger in the same role on two of the three, and the gain persists after controlling for question volume and length. Without further training, we place the questioner in an interactive customer-service agent with a simulated customer, where it completes more tasks while asking fewer questions, and in retail it outperforms the $15\times$ larger model with fewer follow-up turns from the customer. These results show that proactivity depends not only on whether an agent acts without being asked, but also on what it chooses to pursue and when it stops.