mlsanityData to 7 Oct 2026

ALIGN-HOLD: Experience Alignment for Real-Time Hold Control in Large-Scale Ride-Hailing Matching at DiDi

arXiv 2609.09685 ↗First posted 9 Sep 2026cs.LGcited by 0

On the map: LLM alignment / RLHF / preference optimisation → Reward modeling and RLHF

Abstract (arXiv)

Real-time hold control is a high-leverage mechanism in large-scale ride-hailing systems: by selectively deferring driver-order pairs, the platform can wait for better matching opportunities and improve end-to-end passenger-driver experience. Existing production systems such as EXHOLD learn bandit-based hold policies from handcrafted combinations of trip completion, cancellations, waiting time, and driver effort. However, designing such rewards becomes increasingly difficult as marketplace preferences are heterogeneous and observed passenger-driver behavior can be sparse, noisy, and affected by dynamic supply-demand conditions. We present ALIGN-HOLD, a production-scale experience alignment framework that learns hold policy from implicit marketplace preferences. ALIGN-HOLD constructs complementary preference pairs from order trajectories, driver trajectories, and contemporaneous local matching graphs, and trains an experience Reward Model (RM) using balanced multi-view sampling and model-adaptive hard preference sampling. During simulator-based policy learning, the frozen RM provides a dense, context-dependent reward and supports label-free filtering of low-identifiability interactions whose behavioral feedback is difficult to attribute to matching quality. We deploy ALIGN-HOLD on DiDi's ride-hailing platform and evaluate it in a 28-day randomized A/B experiment, covering approximately 100,000 passenger requests per day. Compared with the deployed production policy, ALIGN-HOLD achieves statistically significant improvements in trip completion rate and driver income, while significantly reducing passenger cancellations before and after driver acceptance. Complementary ablations, RM diagnostics, and behavioral analyses validate the contributions of the proposed components. ALIGN-HOLD has been fully ramped up and is currently serving DiDi's Brazil marketplace.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Reward modeling and RLHF, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 12 of its 36 references that are in the map. First posted on arXiv 9 Sep 2026.

Builds on

12 of 36 references.

Closest ancestors · 2

Same direction, newest first

  1. 2018Reward learning from human preferences and demonstrations in Atari15 Nov
  2. 2017Deep reinforcement learning from human preferences12 Jun

Other references · 10

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018Not All Samples Are Created Equal: Deep Learning with Importance Samplingcited by 323
  3. 2017Inverse Reward Designcited by 246
  4. 2018Batch Active Preference-Based Learning of Reward Functionscited by 87
  5. 2024RIME: Robust Preference-based Reinforcement Learning with Noisy Preferencescited by 37
  6. 2026MiniAppBench: Evaluating the Shift from Text to Interactive HTML Responses in LLM-Powered Assistantscited by 7
  7. 2024Hallucination Diversity-Aware Active Learning for Text Summarizationcited by 5
  8. 2023A Survey of Machine Learning-Based Ride-Hailing Planningcited by 3
  9. 2021Secure Your Ride: Real-time Matching Success Rate Prediction for Passenger-Driver Pairscited by 2
  10. 2026EXHOLD: Experience-Aware Real-Time Hold Control for Large-Scale Ride-Hailing Matching at DiDicited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025RAST-MoE-RL: A Regime-Aware Spatio-Temporal MoE Framework for Deep Reinforcement Learning in Ride-Hailing
  2. 2021Data-Driven Simulation of Ride-Hailing Services using Imitation and Reinforcement Learning
  3. 2019Optimal Passenger-Seeking Policies on E-hailing Platforms Using Markov Decision Process and Imitation Learning
  4. 2026D3-Subsidy: Online and Sequential Driver Subsidy Decision-Making for Large-Scale Ride-Hailing Market
  5. 2025TripScore: Aligning LLMs for Real-World Travel Planning via Expert-Calibrated Reward
  6. 2022Spatio-temporal Incentives Optimization for Ride-hailing Services with Offline Deep Reinforcement Learning
  7. 2026STAGE: Controlled Objective Admission for Multi-Preference LLM Alignment
  8. 2025One Step is Enough: Multi-Agent Reinforcement Learning based on One-Step Policy Optimization for Order Dispatch on Ride-Sharing Platforms