mlsanityData to 14 Oct 2026

Ranking-aware Reinforcement Learning for Ordinal Ranking

arXiv 2601.20585 ↗First posted 28 Jan 2026cs.LG cs.AIcited by 1

On the map: Deep reinforcement learning methods → RL training of language and agent models

Abstract (arXiv)

Ordinal regression and ranking are challenging due to inherent ordinal dependencies that conventional methods struggle to model. We propose Ranking-Aware Reinforcement Learning (RARL), a novel RL framework that explicitly learns these relationships. At its core, RARL features a unified objective that synergistically integrates regression and Learning-to-Rank (L2R), enabling mutual improvement between the two tasks. This is driven by a ranking-aware verifiable reward that jointly assesses regression precision and ranking accuracy, facilitating direct model updates via policy optimization. To further enhance training, we introduce Response Mutation Operations (RMO), which inject controlled noise to improve exploration and prevent stagnation at saddle points. The effectiveness of RARL is validated through extensive experiments on three distinct benchmarks.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in RL training of language and agent models, one of 15 directions in Deep reinforcement learning methods. Builds on 15 of its 22 references that are in the map. First posted on arXiv 28 Jan 2026.

Builds on

15 of 22 references.

References · 15

  1. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  2. 2025Qwen2.5-VL Technical Reportcited by 5,587
  3. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,810
  4. 2025Understanding R1-Zero-Like Training: A Critical Perspectivecited by 1,345
  5. 2025Kimi k1.5: Scaling Reinforcement Learning with LLMscited by 1,210
  6. 2017Age Progression/Regression by Conditional Adversarial Autoencodercited by 429
  7. 2025GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoningcited by 150
  8. 2016Photo Aesthetics Ranking Network with Attributes and Content Adaptationcited by 125
  9. 2017Label Distribution Learning Forestscited by 25
  10. 2024Benchmarking Object Detectors with COCO: A New Path Forwardcited by 23
  11. 2023Learning-to-Rank Meets Language: Boosting Language-Driven Ordering Alignment for Ordinal Classificationcited by 21
  12. 2024CLIP-DR: Textual Knowledge-Guided Diabetic Retinopathy Grading with Ranking-aware Promptingcited by 18
3 more
  1. 2023Semi-Supervised Deep Regression with Uncertainty Consistency and Variational Model Ensembling via Bayesian Neural Networkscited by 16
  2. 2019Aesthetic Image Captioning From Weakly-Labelled Photographscited by 12
  3. 2023Robust Image Ordinal Regression with Controllable Image Generationcited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026RISE: Reliable Improvement in Self-Evolving Vision-Language Modelscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2026Structure-aware Relative Policy Optimization for Ranking
  2. 2026ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking
  3. 2026Reward Learning through Ranking Mean Squared Error
  4. 2026RRC: Unlocking Generative Reward Models in LLM Reinforcement Learning via Ranking-Based Reward Construction
  5. 2024ELO-Rated Sequence Rewards: Advancing Reinforcement Learning Models
  6. 2026RankBuffer: Efficient Ranking-Based Rewards for Open-Ended Generation
  7. 2023Unified Off-Policy Learning to Rank: a Reinforcement Learning Perspective
  8. 2026RLVR2: Reinforcement Learning with Verifiable Rubric-based Ranking