ProfiLLM: Utility-Aligned Agentic User Profiling for Industrial Ride-Hailing Dispatch
Quick Answer
ProfiLLM enhances industrial ride-hailing dispatch by utilizing LLMs for user profiling, achieving up to 6.14% AUC improvement and 4.35% GMV gain in simulations.
Quick Take
Deployed on DiDi's platform, it addresses challenges of user data sparsity and context limitations through innovative profiling techniques.
Key Points
- ProfiLLM uses to create adaptive user profiles for ride-hailing dispatch.
- Achieved a 6.14% relative AUC improvement in outcome prediction.
- Generated a 4.35% GMV gain in dispatching simulations.
- Implemented on DiDi's production dispatcher with positive A/B test results.
- Addresses user data sparsity and context limitations in profiling.
Paper Resources
📖 Reader Mode
~2 min readAbstract: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.
| Subjects: | Artificial Intelligence (cs.AI); Computers and Society (cs.CY) |
| Cite as: | arXiv:2606.18803 [cs.AI] |
| (or arXiv:2606.18803v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2606.18803 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Tengfei Lyu [view email]
[v1]
Wed, 17 Jun 2026 08:15:07 UTC (11,200 KB)
— Originally published at arxiv.org
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 →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.