General ML · reinforcement learning papers, 2023–2026

Key findings

• General ML · reinforcement learning went from 287 papers in 2023 to 575 in 2026, roughly 2.0x in three years.
• ICLR publishes the most General ML · reinforcement learning work: 847 papers from 2023 to 2026, 51% of the four-venue total.
• The fastest-growing overlap is with Diffusion Models: papers tagged with both rose from 2 in 2023 to 34 in 2026.
• Among the 6 topics under General Machine Learning, it ranks #2 by 2026 paper count; the fastest grower in the group, General ML · evaluation, is up 4.3x versus 2.0x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026The Sample Complexity of Multiple Change Point Identification under Bandit Feedback
• ICML 2026De-attribute to Forget for LLM Unlearning
• ICLR 2026AbstRaL: Augmenting LLMs' Reasoning by Reinforcing Abstract Thinking
• CVPR 2026Dynamic Important Example Mining for Reinforcement Finetuning
• NeurIPS 2025RULE: Reinforcement UnLEarning Achieves Forget-retain Pareto Optimality
• ICML 2025The Number of Trials Matters in Infinite-Horizon General-Utility Markov Decision Processes
• ICLR 2025A General Framework for Off-Policy Learning with Partially-Observed Reward
• CVPR 2025Automated Proof of Polynomial Inequalities via Reinforcement Learning
• NeurIPS 2024Learning General Parameterized Policies for Infinite Horizon Average Reward Constrained MDPs via Primal-Dual Policy Gradient Algorithm
• ICML 2024Provable Risk-Sensitive Distributional Reinforcement Learning with General Function Approximation
• ICLR 2024Bandits with Replenishable Knapsacks: the Best of both Worlds
• CVPR 2024Improving Unsupervised Hierarchical Representation with Reinforcement Learning
• NeurIPS 2023General Munchausen Reinforcement Learning with Tsallis Kullback-Leibler Divergence
• ICML 2023Non-stationary Reinforcement Learning under General Function Approximation
• ICLR 2023A General Framework for Sample-Efficient Function Approximation in Reinforcement Learning
• CVPR 2023Frustratingly Easy Regularization on Representation Can Boost Deep Reinforcement Learning
• NeurIPS 2026Learning When to Stop: Selective Imitation Learning Under Arbitrary Dynamics Shift
• ICML 2026Fox in the Henhouse: Supply-Chain Backdoor Attacks Against Reinforcement Learning
• ICLR 2026APPLE: Toward General Active Perception via Reinforcement Learning
• CVPR 2026Reinforcement-Guided Synthetic Data Generation for Privacy-Sensitive Identity Recognition

All General ML · reinforcement learning papers

108 papers, page 2 of 3

51. NeurIPS 2025Learning to Clean: Reinforcement Learning for Noisy Label Correction
52. NeurIPS 2025Measure gradients, not activations! Enhancing neuronal activity in deep reinforcement learning
53. NeurIPS 2025Meta-learning how to Share Credit among Macro-Actions
54. NeurIPS 2025Mind the GAP! The Challenges of Scale in Pixel-based Deep Reinforcement Learning
55. NeurIPS 2025Mixture-of-Experts Meets In-Context Reinforcement Learning
56. NeurIPS 2025Novel Exploration via Orthogonality
57. NeurIPS 2025Offline Actor-Critic for Average Reward MDPs
58. NeurIPS 2025Offline Goal-conditioned Reinforcement Learning with Quasimetric Representations
59. NeurIPS 2025Offline imitation learning in $Q^\pi$-realizable MDPs without expert realizability
60. NeurIPS 2025Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration
61. NeurIPS 2025On the Global Optimality of Policy Gradient Methods in General Utility Reinforcement Learning
62. NeurIPS 2025On the Sample Complexity Bounds of Bilevel Reinforcement Learning
63. NeurIPS 2025Optimal Dynamic Regret by Transformers for Non-Stationary Reinforcement Learning
64. NeurIPS 2025Optimal Regret Bounds via Low-Rank Structured Variation in Non-Stationary Reinforcement Learning
65. NeurIPS 2025Option-aware Temporally Abstracted Value for Offline Goal-Conditioned Reinforcement Learning
66. NeurIPS 2025Perception-R1: Pioneering Perception Policy with Reinforcement Learning
67. NeurIPS 2025Preference Distillation via Value based Reinforcement Learning
68. NeurIPS 2025Preference-based Reinforcement Learning beyond Pairwise Comparisons: Benefits of Multiple Options
69. NeurIPS 2025Pretraining a Shared Q-Network for Data-Efficient Offline Reinforcement Learning
70. NeurIPS 2025Progress Reward Model for Reinforcement Learning via Large Language Models
71. NeurIPS 2025Quantization-Free Autoregressive Action Transformer
72. NeurIPS 2025Real-World Reinforcement Learning of Active Perception Behaviors
73. NeurIPS 2025REINFORCE Converges to Optimal Policies with Any Learning Rate
74. NeurIPS 2025Reinforcement Learning Finetunes Small Subnetworks in Large Language Models
75. NeurIPS 2025Reinforcement Learning with Backtracking Feedback
76. NeurIPS 2025Reinforcement Learning with Imperfect Transition Predictions: A Bellman-Jensen Approach
77. NeurIPS 2025Reward-Aware Proto-Representations in Reinforcement Learning
78. NeurIPS 2025Risk-Averse Constrained Reinforcement Learning with Optimized Certainty Equivalents
79. NeurIPS 2025Risk-Averse Total-Reward Reinforcement Learning
80. NeurIPS 2025RLVR-World: Training World Models with Reinforcement Learning
81. NeurIPS 2025RULE: Reinforcement UnLEarning Achieves Forget-retain Pareto Optimality
82. NeurIPS 2025Sample Complexity of Distributionally Robust Average-Reward Reinforcement Learning
83. NeurIPS 2025SeRL: Self-play Reinforcement Learning for Large Language Models with Limited Data
84. NeurIPS 2025Shift Before You Learn: Enabling Low-Rank Representations in Reinforcement Learning
85. NeurIPS 2025ShiQ: Bringing back Bellman to LLMs
86. NeurIPS 2025Skill-Driven Neurosymbolic State Abstractions
87. NeurIPS 2025Solving Continuous Mean Field Games: Deep Reinforcement Learning for Non-Stationary Dynamics
88. NeurIPS 2025Stable Gradients for Stable Learning at Scale in Deep Reinforcement Learning
89. NeurIPS 2025Staggered Environment Resets Improve Massively Parallel On-Policy Reinforcement Learning
90. NeurIPS 2025STAIR: Addressing Stage Misalignment through Temporal-Aligned Preference Reinforcement Learning
91. NeurIPS 2025STAR: Efficient Preference-based Reinforcement Learning via Dual Regularization
92. NeurIPS 2025State Entropy Regularization for Robust Reinforcement Learning
93. NeurIPS 2025Structured Reinforcement Learning for Combinatorial Decision-Making
94. NeurIPS 2025Tackling Continual Offline RL through Selective Weights Activation on Aligned Spaces
95. NeurIPS 2025The World Is Bigger: A Computationally-Embedded Perspective on the Big World Hypothesis
96. NeurIPS 2025Time Reversal Symmetry for Efficient Robotic Manipulations in Deep Reinforcement Learning
97. NeurIPS 2025To Think or Not To Think: A Study of Thinking in Rule-Based Visual Reinforcement Fine-Tuning
98. NeurIPS 2025Towards Large-Scale In-Context Reinforcement Learning by Meta-Training in Randomized Worlds
99. NeurIPS 2025Towards Provable Emergence of In-Context Reinforcement Learning
100. NeurIPS 2025Trajectory Graph Learning: Aligning with Long Trajectories in Reinforcement Learning Without Reward Design

FAQ

How many General ML · reinforcement learning papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

1,676 in total: 287 in 2023, 403 in 2024, 411 in 2025, 575 in 2026.

How many General ML · reinforcement learning papers are at NeurIPS 2026?

NeurIPS 2026 has 113 General ML · reinforcement learning papers, versus 108 the year before.

How many General ML · reinforcement learning papers are at ICLR 2026?

ICLR 2026 has 335 General ML · reinforcement learning papers, versus 230 the year before.

How many General ML · reinforcement learning papers are at ICML 2026?

ICML 2026 has 113 General ML · reinforcement learning papers, versus 71 the year before.

How many General ML · reinforcement learning papers are at CVPR 2026?

CVPR 2026 has 14 General ML · reinforcement learning papers, versus 2 the year before.

Which conference publishes the most General ML · reinforcement learning papers?

ICLR, with 847 papers from 2023 to 2026.