Beyond expert users: agents should help users construct preferences, not just elicit them

• URL: http://arxiv.org/abs/2606.30863v2
• Date: Wed, 01 Jul 2026 01:04:18 GMT
• Title: Beyond expert users: agents should help users construct preferences, not just elicit them
• Abstract summary: We introduce CoPref, a model of how users construct preferences based on agent dialog actions.<n>In CoShop, an agent converses with and makes recommendations for a CoPref user.<n>We find that no agent exceeds 56% accuracy on CoShop despite five turns of interaction.
• Score: 31.382826707274685
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• AcCoRD: Evaluating User-Agent Collaboration Under Realistic User Preference Dynamics [13.692601337126462]
  Existing benchmarks for evaluating user-agent collaboration focus almost exclusively on resolving underspecified preferences.<n>We introduce AcCoRD, a user-agent collaboration benchmark requiring agents to handle diverse user preference dynamics in two domains: online shopping and travel planning.
  arXiv  Detail & Related papers  (2026-08-28T01:34:38Z)
• UserHarness: Harnessing User Minds for Stronger Agent Theory-of-Mind [51.47914365631888]
  UserHarness is a simple framework that reframes Theory-of-Mind (ToM) reasoning as explicit user-mind reconstruction.<n>It decomposes the user's mental state, its relation to the external environment, and the actions that follow from it, enabling agents to track what the user observes, believes, intends, and does.
  arXiv  Detail & Related papers  (2026-05-26T21:45:45Z)
• Turning Intent into Specifications: A Benchmark and an Interactive User-Assistant Agent [22.126763421836966]
  We introduce SpecBench, a new benchmark for evaluating an agent's ability to translate user intent into a structured, executable specification.<n>The agent is given access to past user conversations and may interact with the user for a fixed number of rounds to ask clarifying questions.
  arXiv  Detail & Related papers  (2026-05-13T16:07:43Z)
• KnowU-Bench: Towards Interactive, Proactive, and Personalized Mobile Agent Evaluation [72.01173512175531]
  KnowU-Bench is an online benchmark for personalized mobile agents.<n>It covers 42 general GUI tasks, 86 personalized tasks, and 64 proactive tasks.<n>Our experiments reveal a striking degradation: agents that excel at explicit task execution fall below 50% under vague instructions.
  arXiv  Detail & Related papers  (2026-04-09T16:50:50Z)
• Persona2Web: Benchmarking Personalized Web Agents for Contextual Reasoning with User History [8.085230376705887]
  Persona2Web is the first benchmark for evaluating personalized web agents on the real open web.<n>It consists of: (1) user histories that reveal preferences implicitly over long time spans, (2) ambiguous queries that require agents to infer implicit user preferences, and (3) a reasoning-aware evaluation framework that enables fine-grained assessment of personalization.
  arXiv  Detail & Related papers  (2026-02-19T01:54:26Z)
• Agentic Feedback Loop Modeling Improves Recommendation and User Simulation [55.857164472712455]
  We propose a novel framework that emphasizes the feedback loop process to facilitate the collaboration between the recommendation agent and the user agent.<n>This iterative process enhances the ability of both agents to infer user behaviors, enabling more effective item recommendations and more accurate user simulations.
  arXiv  Detail & Related papers  (2024-10-26T00:51:39Z)
• Apollonion: Profile-centric Dialog Agent [9.657755354649048]
  We propose a framework for dialog agent to incorporate user profiling (initialization, update): user's query and response is analyzed and organized into a structural user profile. We propose a series of evaluation protocols for personalization: to what extend the response is personal to the different users.
  arXiv  Detail & Related papers  (2024-04-10T03:32:41Z)
• Tell Me More! Towards Implicit User Intention Understanding of Language Model Driven Agents [110.25679611755962]
  Current language model-driven agents often lack mechanisms for effective user participation, which is crucial given the vagueness commonly found in user instructions. We introduce Intention-in-Interaction (IN3), a novel benchmark designed to inspect users' implicit intentions through explicit queries. We empirically train Mistral-Interact, a powerful model that proactively assesses task vagueness, inquires user intentions, and refines them into actionable goals.
  arXiv  Detail & Related papers  (2024-02-14T14:36:30Z)
• On Generative Agents in Recommendation [58.42840923200071]
  Agent4Rec is a user simulator in recommendation based on Large Language Models. Each agent interacts with personalized recommender models in a page-by-page manner.
  arXiv  Detail & Related papers  (2023-10-16T06:41:16Z)
• AgentCF: Collaborative Learning with Autonomous Language Agents for Recommender Systems [112.76941157194544]
  We propose AgentCF for simulating user-item interactions in recommender systems through agent-based collaborative filtering. We creatively consider not only users but also items as agents, and develop a collaborative learning approach that optimize both kinds of agents together. Overall, the optimized agents exhibit diverse interaction behaviors within our framework, including user-item, user-user, item-item, and collective interactions.
  arXiv  Detail & Related papers  (2023-10-13T16:37:14Z)
• Relative Behavioral Attributes: Filling the Gap between Symbolic Goal Specification and Reward Learning from Human Preferences [19.70421486855437]
  Non-expert users can express complex objectives by expressing preferences over short clips of agent behaviors. Relative Behavioral Attributes acts as a middle ground between exact goal specification and reward learning purely from preference labels. We propose two different parametric methods that can potentially encode any kind of behavioral attributes from ordered behavior clips.
  arXiv  Detail & Related papers  (2022-10-28T05:25:23Z)
• Towards customizable reinforcement learning agents: Enabling preference specification through online vocabulary expansion [25.053927377536905]
  We propose PRESCA, a system that allows users to specify their preferences in terms of concepts that they understand. We evaluate PRESCA by using it on a Minecraft environment and show that it can be effectively used to make the agent align with the user's preference.
  arXiv  Detail & Related papers  (2022-10-27T00:54:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.