User Preference Modeling for Conversational LLM Agents: Weak Rewards from Retrieval-Augmented Interaction

• URL: http://arxiv.org/abs/2603.20939v1
• Date: Sat, 21 Mar 2026 20:44:32 GMT
• Title: User Preference Modeling for Conversational LLM Agents: Weak Rewards from Retrieval-Augmented Interaction
• Abstract summary: We propose a pipeline-agnostic, frozen-backbone framework that represents each user with long-term and short-term vectors in a shared preference space.<n>The vectors are updated online from weak scalar rewards from users' feedback, enabling personalization without per-user fine-tuning.
• Score: 26.605145527804066
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Large language models are increasingly used as personal assistants, yet most lack a persistent user model, forcing users to repeatedly restate preferences across sessions. We propose Vector-Adapted Retrieval Scoring (VARS), a pipeline-agnostic, frozen-backbone framework that represents each user with long-term and short-term vectors in a shared preference space and uses these vectors to bias retrieval scoring over structured preference memory. The vectors are updated online from weak scalar rewards from users' feedback, enabling personalization without per-user fine-tuning. We evaluate on \textsc{MultiSessionCollab}, an online multi-session collaboration benchmark with rich user preference profiles, across math and code tasks. Under frozen backbones, the main benefit of user-aware retrieval is improved interaction efficiency rather than large gains in raw task accuracy: our full VARS agent achieves the strongest overall performance, matches a strong Reflection baseline in task success, and reduces timeout rate and user effort. The learned long-term vectors also align with cross-user preference overlap, while short-term vectors capture session-specific adaptation, supporting the interpretability of the dual-vector design. Code, model, and data are available at https://github.com/YurenHao0426/VARS.

Related papers

• SWE-Together: Evaluating Coding Agents in Interactive User Sessions [19.069719245971786]
  We introduce SWE-Together, a multi-turn benchmark reconstructed from real user-agent coding sessions.<n>We curate 109 repository-level tasks from 11,260 recorded sessions, selecting sessions with recoverable repository states, clear user goals, and observable outcomes.<n>We build a reactive LLM-based user simulator that preserves the original users' intents and provides feedback when the coding agent's progress requires it.
  arXiv  Detail & Related papers  (2026-06-29T08:35:15Z)
• PERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environments [72.02445514666428]
  We introduce PERMA, a benchmark designed to evaluate persona consistency over time beyond static preference recall.<n>PerMA consists of temporally ordered interaction events spanning multiple sessions and domains, with preference-related queries inserted over time.<n> Experiments demonstrate that by linking related interactions, advanced memory systems can extract more precise preferences and reduce token consumption.
  arXiv  Detail & Related papers  (2026-03-24T14:04:11Z)
• Temporal User Profiling with LLMs: Balancing Short-Term and Long-Term Preferences for Recommendations [3.719862246745416]
  We propose a novel method for user profiling that explicitly models short-term and long-term preferences.<n>LLM-TUP achieves substantial improvements over several baselines.
  arXiv  Detail & Related papers  (2025-08-11T20:28:24Z)
• Async Learned User Embeddings for Ads Delivery Optimization [24.104745716074262]
  In recommendation systems, high-quality user embeddings can capture subtle preferences, enable precise similarity calculations, and adapt to changing preferences over time to maintain relevance. We propose to asynchronously learn high fidelity user embeddings for billions of users each day from sequence based multimodal user activities through a Transformer-like large scale feature learning module.
  arXiv  Detail & Related papers  (2024-06-09T19:35:20Z)
• Latent User Intent Modeling for Sequential Recommenders [92.66888409973495]
  Sequential recommender models learn to predict the next items a user is likely to interact with based on his/her interaction history on the platform. Most sequential recommenders however lack a higher-level understanding of user intents, which often drive user behaviors online. Intent modeling is thus critical for understanding users and optimizing long-term user experience.
  arXiv  Detail & Related papers  (2022-11-17T19:00:24Z)
• Modeling Dynamic User Preference via Dictionary Learning for Sequential Recommendation [133.8758914874593]
  Capturing the dynamics in user preference is crucial to better predict user future behaviors because user preferences often drift over time. Many existing recommendation algorithms -- including both shallow and deep ones -- often model such dynamics independently. This paper considers the problem of embedding a user's sequential behavior into the latent space of user preferences.
  arXiv  Detail & Related papers  (2022-04-02T03:23:46Z)
• Sequential Search with Off-Policy Reinforcement Learning [48.88165680363482]
  We propose a highly scalable hybrid learning model that consists of an RNN learning framework and an attention model. As a novel optimization step, we fit multiple short user sequences in a single RNN pass within a training batch, by solving a greedy knapsack problem on the fly. We also explore the use of off-policy reinforcement learning in multi-session personalized search ranking.
  arXiv  Detail & Related papers  (2022-02-01T06:52:40Z)
• Empowering General-purpose User Representation with Full-life Cycle Behavior Modeling [11.698166058448555]
  We propose a novel framework called full- Life cycle User Representation Model (LURM) to tackle this challenge. LURM consists of two cascaded sub-models: (I) Bag-of-Interests (BoI) encodes user behaviors in any time period into a sparse vector with super-high dimension (e.g., 105) SMEN achieves almost dimensionality reduction, benefiting from a novel multi-anchor module which can learn different aspects of user interests.
  arXiv  Detail & Related papers  (2021-10-20T08:24:44Z)
• From Implicit to Explicit feedback: A deep neural network for modeling sequential behaviours and long-short term preferences of online users [3.464871689508835]
  Implicit and explicit feedback have different roles for a useful recommendation. We go from the hypothesis that a user's preference at a time is a combination of long-term and short-term interests.
  arXiv  Detail & Related papers  (2021-07-26T16:59:20Z)
• Dynamic Memory based Attention Network for Sequential Recommendation [79.5901228623551]
  We propose a novel long sequential recommendation model called Dynamic Memory-based Attention Network (DMAN) It segments the overall long behavior sequence into a series of sub-sequences, then trains the model and maintains a set of memory blocks to preserve long-term interests of users. Based on the dynamic memory, the user's short-term and long-term interests can be explicitly extracted and combined for efficient joint recommendation.
  arXiv  Detail & Related papers  (2021-02-18T11:08:54Z)
• Dynamic Embeddings for Interaction Prediction [2.5758502140236024]
  In recommender systems (RSs), predicting the next item that a user interacts with is critical for user retention. Recent studies have shown the effectiveness of modeling the mutual interactions between users and items using separate user and item embeddings. We propose a novel method called DeePRed that addresses some of their limitations.
  arXiv  Detail & Related papers  (2020-11-10T16:04:46Z)
• Sequential Recommender via Time-aware Attentive Memory Network [67.26862011527986]
  We propose a temporal gating methodology to improve attention mechanism and recurrent units. We also propose a Multi-hop Time-aware Attentive Memory network to integrate long-term and short-term preferences. Our approach is scalable for candidate retrieval tasks and can be viewed as a non-linear generalization of latent factorization for dot-product based Top-K recommendation.
  arXiv  Detail & Related papers  (2020-05-18T11:29:38Z)

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.