Provably Efficient Personalized Multi-Objective Bandits with Proactive Conversational Queries

• URL: http://arxiv.org/abs/2606.08410v1
• Date: Sun, 07 Jun 2026 02:19:59 GMT
• Title: Provably Efficient Personalized Multi-Objective Bandits with Proactive Conversational Queries
• Abstract summary: We formalize a proactive query-based framework in which user queries provide structured preference signals.<n>We prove that proactive queries accelerate preference estimation and yield improved regret scaling over prior preference-aware MO-MAB methods.
• Score: 24.496126767935937
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Personalized decision-making in multi-objective bandits requires learning user-specific trade-offs among competing objectives. Since arm utility depends on both unknown rewards and unknown preferences, existing methods infer preferences only from utility feedback, entangling preference learning with reward exploration. In practice, however, users often reveal their priorities through proactive conversational queries (e.g., "cheap and clean hotel"), yet this structured signal is not leveraged. We formalize a proactive query-based framework in which user queries provide structured preference signals. Modeling these signals via a Plackett-Luce subset choice model, we show that query-only learning is insufficient due to a fundamental shift-invariance barrier. To resolve this, we introduce MO-PQUCB, a hybrid algorithm that integrates query-based preference anchoring with bandit feedback through shift-invariant regularization and dual-exploration UCB. We prove that proactive queries accelerate preference estimation and yield improved regret scaling over prior preference-aware MO-MAB methods. Under corrupted queries, we further characterize statistical limits and design a robust estimator achieving near-optimal performance when the corruption is sparse. Experiments validate both theoretical and practical gains.

Related papers

• Tabular Foundation Models for Discrete Choice Estimation [8.167439804974467]
  Tabular foundation models (TFMs) generate predictions on structured data via in-context learning, without task-specific estimation.<n>We ask whether TFMs can be effectively applied to discrete choice, a central demand estimation framework in marketing and operations.<n>We propose a reformulation that encodes both choice-set dependence and individual heterogeneity within a row-based learning framework.
  arXiv  Detail & Related papers  (2026-07-14T22:34:00Z)
• Before Thinking, Learn to Decide: Proactive Routing for Efficient Visual Reasoning [87.18590662029432]
  We propose PRP, a Proactive Routing Paradigm that enables early decision-making by jointly evaluating the competence of both the draft and target models.<n>Our draft Rating Learning (DRL) equips the draft model with an internal confidence estimator, while Joint Rating Learning (JRL) predicts how well the target model can handle a given query.<n>These ratings enable fine-grained, instance-level textbfProactive Routing and substantially accelerate inference without compromising overall performance.
  arXiv  Detail & Related papers  (2026-06-29T12:30:24Z)
• Selective Ensemble Based on Preference-Directed Multi-Objective Bandits [90.75513823660775]
  We formalize a sequential decision problem under partially specified linear preferences.<n>We then propose a preference-directed upper confidence bound (PrefUCB) algorithm.<n> Experiments on large pre-trained model selective ensemble tasks and online asset allocation under institutional mandates validate our method.
  arXiv  Detail & Related papers  (2026-06-20T07:52:46Z)
• RecThinker: An Agentic Framework for Tool-Augmented Reasoning in Recommendation [63.74915464611075]
  RecThinker is an agentic framework for tool-augmented reasoning in recommendation.<n>We develop a suite of specialized tools for RecThinker, enabling the model to acquire user item-side and collaborative information.
  arXiv  Detail & Related papers  (2026-03-10T16:07:17Z)
• Verifiable Reasoning for LLM-based Generative Recommendation [106.7765000777685]
  Reasoning in Large Language Models (LLMs) has recently shown strong potential in enhancing generative recommendation.<n>We propose a novel textbftextitreason-verify-recommend paradigm, which interleaves reasoning with verification to provide reliable feedback.<n>Experiments on four real-world datasets demonstrate that VRec substantially enhances recommendation effectiveness and scalability without compromising efficiency.
  arXiv  Detail & Related papers  (2026-03-08T16:55:45Z)
• Are LLMs Vulnerable to Preference-Undermining Attacks (PUA)? A Factorial Analysis Methodology for Diagnosing the Trade-off between Preference Alignment and Real-World Validity [45.92643973404507]
  We investigate whether aligned models are vulnerable to Preference-Undermining Attacks (PUA), a class of manipulative prompting strategies.<n>Surprisingly, more advanced models are sometimes more susceptible to manipulative prompts.
  arXiv  Detail & Related papers  (2026-01-10T15:16:23Z)
• Robust Preference Alignment via Directional Neighborhood Consensus [13.313830197011983]
  We introduce Robust Preference Selection (RPS), a post-hoc, training-free method by leveraging directional neighborhood consensus.<n>RPS samples multiple responses from a local neighborhood of related preferences to create a superior candidate pool.<n>Our work presents a practical, theoretically-grounded solution for enhancing the reliability of preference-aligned models.
  arXiv  Detail & Related papers  (2025-10-23T12:39:20Z)
• STARec: An Efficient Agent Framework for Recommender Systems via Autonomous Deliberate Reasoning [54.28691219536054]
  We introduce STARec, a slow-thinking augmented agent framework that endows recommender systems with autonomous deliberative reasoning capabilities.<n>We develop anchored reinforcement training - a two-stage paradigm combining structured knowledge distillation from advanced reasoning models with preference-aligned reward shaping.<n>Experiments on MovieLens 1M and Amazon CDs benchmarks demonstrate that STARec achieves substantial performance gains compared with state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-08-26T08:47:58Z)
• Online Clustering of Dueling Bandits [59.09590979404303]
  We introduce the first "clustering of dueling bandit algorithms" to enable collaborative decision-making based on preference feedback.<n>We propose two novel algorithms: (1) Clustering of Linear Dueling Bandits (COLDB) which models the user reward functions as linear functions of the context vectors, and (2) Clustering of Neural Dueling Bandits (CONDB) which uses a neural network to model complex, non-linear user reward functions.
  arXiv  Detail & Related papers  (2025-02-04T07:55:41Z)
• Cost-Effective Proxy Reward Model Construction with On-Policy and Active Learning [70.22819290458581]
  Reinforcement learning with human feedback (RLHF) is a widely adopted approach in current large language model pipelines. Our approach introduces two key innovations: (1) on-policy query to avoid OOD and imbalance issues in seed data, and (2) active learning to select the most informative data for preference queries.
  arXiv  Detail & Related papers  (2024-07-02T10:09:19Z)
• Estimating Treatment Effects under Recommender Interference: A Structured Neural Networks Approach [32.55211271796683]
  We show that commonly adopted difference-in-means estimators can lead to severely biased estimates due to recommender interference.<n>We propose a recommender choice model'' that explicitly represents the interference pathway.<n>We validate our method with a large-scale field experiment on Weixin short-video platform.
  arXiv  Detail & Related papers  (2024-06-20T14:53:26Z)
• Active recursive Bayesian inference using R\'enyi information measures [11.1748531496641]
  We propose an active Bayesian inference framework with unified inference and query selection steps. We analytically demonstrate that the proposed approach outperforms conventional methods such as mutual information. We present empirical and experimental performance evaluations on two applications: restaurant recommendation and brain-computer interface (BCI) typing systems.
  arXiv  Detail & Related papers  (2020-04-07T05:52:58Z)

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.