ProfiLLM: Utility-Aligned Agentic User Profiling for Industrial Ride-Hailing Dispatch

• URL: http://arxiv.org/abs/2606.18803v1
• Date: Wed, 17 Jun 2026 08:15:07 GMT
• Title: ProfiLLM: Utility-Aligned Agentic User Profiling for Industrial Ride-Hailing Dispatch
• Abstract summary: ProfiLLM operationalizes utility-aligned user profiling for production matching systems through two modules.<n>It produces reusable global knowledge, adaptive user clustering rules, and region-level supply-demand priors.<n>It achieves up to +6.14% relative AUC improvement in outcome prediction, up to +4.35% GMV gain in dispatching simulation.
• Score: 20.2442673472594
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Bringing Large Language Models (LLMs) into industrial ride-hailing dispatch as semantic feature extractors over platform-scale behavioral logs is a compelling but under-explored data systems problem. Production matching pipelines remain dominated by structured numerical features, yet decisive behavioral signals (e.g., a driver's habitual aversion to certain regions) are inherently contextual and naturally expressible as LLM-generated user profiles. However, scaling such profiling to a live, millisecond-latency dispatcher faces three intertwined constraints rarely addressed together: on a platform with millions of daily orders, logs exceed any LLM's context window by orders of magnitude; most users are long-tail, with too few interactions for per-user profiling; and surface-fluent profiles do not necessarily improve downstream prediction utility. We present ProfiLLM, an agentic LLM data pipeline that operationalizes utility-aligned user profiling for production matching systems through two modules. (1) Tool-Augmented Global Knowledge Mining equips an LLM agent with 27 analytical tools to mine platform-scale data, producing reusable global knowledge, adaptive user clustering rules, and region-level supply-demand priors. (2) Utility-Aligned Profile Exploration generates multiple candidate profiles per cluster, evaluates them via a lightweight downstream utility proxy, iteratively refines the best candidates and constructs preference pairs for DPO fine-tuning. Deployed on DiDi's production dispatcher, ProfiLLM achieves up to +6.14% relative AUC improvement in outcome prediction, up to +4.35% GMV gain in dispatching simulation, and consistent improvements in a 14-day online A/B test including +0.47% GMV, +0.33% Completion Rate, and -0.82% Cancel-Before-Accept rate.

Related papers

• Generate to Explore, Select to Exploit: Aligning LLM-based Headline Generation with Personalized Recommendation [6.094273771485958]
  In industrial recommendation feeds, presenting a static headline for an item often fails to satisfy the diverse, multimodal interests of the user population.<n>We introduce GESE, a framework that decouples personalization into generative exploration and selective exploitation.<n>Extensive deployment on a commercial platform with over 100 million daily active users demonstrates that GESE significantly outperforms state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-09-14T06:14:38Z)
• Task-Aware Automated User Profile Generation for Recommendation Simulation Using Large Language Models [8.706093337738869]
  This work proposes an Automated Profile Generation Framework for Recommendation Simulation, APG4RecSim.<n>APG4RecSim constructs realistic, coherent, and robust user profiles with minimal supervision.<n>Our results show that profiles generated by APG4RecSim are resilient to popularity- and position-induced biases.
  arXiv  Detail & Related papers  (2026-05-13T13:20:39Z)
• Chimera: Latency- and Performance-Aware Multi-agent Serving for Heterogeneous LLMs [62.17306142810532]
  We present Chimera, a predictive scheduling system for multi-agent workflow serving on heterogeneous LLM clusters.<n>Chime traces the best latency, reducing end-to-end latency by 1.2--2.4$times$ and improving task performance by 8.0-9.5 percentage points on average over competitive baselines.
  arXiv  Detail & Related papers  (2026-03-23T17:01:42Z)
• FedPDPO: Federated Personalized Direct Preference Optimization for Large Language Model Alignment [55.97027207627]
  Fed PDPO (Federated Personalized Direct Preference Optimization) is a personalized framework for preference alignment of large language models (LLMs)<n>It adopts a parameter-efficient fine-tuning architecture where each client maintains a frozen pretrained LLM backbone augmented with a Low-Rank Adaptation (LoRA) adapter, enabling communication-efficient aggregation.<n>Experiments on multiple preference datasets demonstrate state-of-the-art performance, achieving up to 4.80% average accuracy improvements in federated intra-domain and cross-domain settings.
  arXiv  Detail & Related papers  (2026-03-20T08:24:49Z)
• Synthetic Interaction Data for Scalable Personalization in Large Language Models [67.31884245564086]
  We introduce a high-fidelity synthetic data generation framework called PersonaGym.<n>Unlike prior work that treats personalization as static persona-preference pairs, PersonaGym models a dynamic preference process.<n>We release PersonaAtlas, a large-scale, high-quality, and diverse synthetic dataset of high-fidelity multi-turn personalized interaction trajectories.
  arXiv  Detail & Related papers  (2026-02-12T20:41:22Z)
• Diagnostic-Guided Dynamic Profile Optimization for LLM-based User Simulators in Sequential Recommendation [15.61963892566877]
  DGDPO is a novel framework that constructs user profile through a dynamic and iterative optimization process.<n>Unlike existing LLM-based user simulators that are limited to single-round interactions, we are the first to integrate DGDPO with sequential recommenders.
  arXiv  Detail & Related papers  (2025-08-18T06:17:59Z)
• PROMPTEVALS: A Dataset of Assertions and Guardrails for Custom Production Large Language Model Pipelines [0.8148009849453334]
  Large language models (LLMs) are increasingly deployed in specialized production data processing pipelines across diverse domains.<n>To improve reliability in these applications, creating assertions or guardrails for LLM outputs to run alongside the pipelines is essential.<n>In this paper, we introduce PROMPTEVALS, a dataset of 2087 pipeline prompts with 12623 corresponding assertion criteria.
  arXiv  Detail & Related papers  (2025-04-20T21:04:23Z)
• Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scale [53.059480071818136]
  Large Language Models (LLMs) have emerged as personalized assistants for users across a wide range of tasks.<n> PERSONAMEM features curated user profiles with over 180 simulated user-LLM interaction histories.<n>We evaluate LLM chatbots' ability to identify the most suitable response according to the current state of the user's profile.
  arXiv  Detail & Related papers  (2025-04-19T08:16:10Z)
• PersonaX: A Recommendation Agent Oriented User Modeling Framework for Long Behavior Sequence [8.557534799079956]
  PersonaX is an agent-agnostic LLM-UM framework to address these challenges.<n>It augments downstream recommendation agents to achieve better recommendation performance and inference efficiency.
  arXiv  Detail & Related papers  (2025-03-04T08:41:40Z)
• Prompt Tuning as User Inherent Profile Inference Machine [68.16976932088708]
  We propose UserIP-Tuning, which uses prompt-tuning to infer user profiles.<n>UserIP-Tuning outperforms state-of-the-art recommendation algorithms.<n>The presented solution has been deployed in Huawei AppGallery's Explore page since May 2025.
  arXiv  Detail & Related papers  (2024-08-13T02:25:46Z)
• Self-Augmented Preference Optimization: Off-Policy Paradigms for Language Model Alignment [104.18002641195442]
  We introduce Self-Augmented Preference Optimization (SAPO), an effective and scalable training paradigm that does not require existing paired data. Building on the self-play concept, which autonomously generates negative responses, we further incorporate an off-policy learning pipeline to enhance data exploration and exploitation.
  arXiv  Detail & Related papers  (2024-05-31T14:21:04Z)

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.