Beyond expert users: agents should help users construct preferences, not just elicit them
Quick Answer
The study critiques the assumption that users have well-defined preferences, proposing CoPref and CoShop to help users construct preferences through agent interactions.
Quick Take
The study critiques the assumption that users have well-defined preferences, proposing CoPref and CoShop to help users construct preferences through agent interactions. Despite evaluating five models, none achieved over 56% accuracy, highlighting the need for agents to enhance user knowledge rather than just retrieve items.
Key Points
- CoPref model helps users construct preferences through agent dialog actions.
- CoShop benchmark evaluates agent performance in user interactions.
- No agent exceeded 56% accuracy in CoShop after five interaction turns.
- Failures are due to limited user knowledge rather than item retrieval.
- Study emphasizes the importance of educating users in preference formation.
Paper Resources
Article Content
From source RSS / original summaryarXiv:2606. 30863v1 Announce Type: new Abstract: Agents typically assume an expert user -- one with well-formed preferences about what they want -- and default to clarifying questions whenever the task is underspecified. We argue this assumption is unrealistic.
Users often lack the domain knowledge to have completely specified preferences; if asked about their preference on some feature, the user may be unable to answer without the agent helping the user to learn some domain knowledge needed to form a preference for that feature, e. g. , via examples or explanations. To formalize these principles, we draw on the Search-Experience-Credence framework from Information Economics to introduce CoPref, a model of how users construct preferences based on agent dialog actions.
We then study these ideas concretely in agentic recommender systems, proposing CoShop, an interactive benchmark. In CoShop, an agent converses with and makes recommendations for a CoPref user. The agent's performance depends on whether it can help the user gain the knowledge needed to specify the task well. Evaluating five frontier models, we find that no agent exceeds 56% accuracy on CoShop despite five turns of interaction.
Failures stem not from agents' ability to find items, but from how little the interaction expands what users know about what they want.
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →The Verification Horizon: No Silver Bullet for Coding Agent Rewards
As coding agents evolve, verifying solutions becomes more challenging than generating them, necessitating a focus on scalable, faithful, and robust verification methods. The study reveals that no fixed reward function can sustain effectiveness as model capabilities advance, emphasizing the need for verification to evolve alongside solution generation.