Asking for What Was Never Requested: Horizontal and Vertical Proactivity in Agents

2026-09-29

AI Summary

This study addresses the challenge of agents proactively acquiring information that is essential for task completion but not explicitly requested by users. To this end, it proposes the Q&D framework, which introduces novel dimensions of horizontal and vertical proactivity alongside a requirement graph for evaluating information-seeking behavior. Without relying on reward models, the framework trains questioners to learn proactive questioning strategies through preference optimization in simulated interactions. Experimental results demonstrate significant improvements in proactivity across three multi-hop question-answering benchmarks, outperforming large language models with fifteen times more parameters. Furthermore, in customer service scenarios, the approach achieves higher task completion rates while requiring fewer questions, establishing an efficient new paradigm for proactive agent interaction.

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.

Problem

• proactive agents
• horizontal proactivity
• vertical proactivity
• multi-hop question answering
• tool-use

Innovation

• Proactive Agents
• Horizontal and Vertical Proactivity
• Need Graph
• Q&D Training
• Multi-hop Question Answering