What are Key Factors for Updates in RL for LLM Reasoning?

arXiv:2606.22570 · cs.CL · Submitted 2026-06-21 · Read on arXiv

cs.CL

Submitted: 2026-06-21

Updated: 2026-09-19

Code: https://github.com/Control-derek/ACPO

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• GRPO — 24× in this paper · explained in 6 episodes
• Importance Sampling — 20× in this paper
• Reinforcement Learning — 20× in this paper · explained in 4 episodes
• Benchmark — 15× in this paper · explained in 2 episodes
• Alignment — 8× in this paper · explained in 1 episode
• Adaptive Clip Policy Optimization — 6× in this paper
• Aggregation — 6× in this paper · explained in 1 episode
• Ablation — 5× in this paper · explained in 1 episode
• Computational overhead — 5× in this paper · explained in 2 episodes
• Verifiable Rewards — 5× in this paper · explained in 2 episodes
• Calibration — 4× in this paper · explained in 7 episodes
• Accuracy — 3× in this paper · explained in 1 episode
• Adam — 3× in this paper · explained in 2 episodes
• Robustness — 3× in this paper · explained in 5 episodes
• Ablation study — 2× in this paper · explained in 1 episode
• Adaptive Mechanism — 2× in this paper · explained in 1 episode
• Advantage Reweighting — 2× in this paper
• Credit assignment — 2× in this paper · explained in 3 episodes
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Regularization — 2× in this paper · explained in 3 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Actor — 1× in this paper · explained in 3 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Entropy Collapse — 1× in this paper · explained in 2 episodes
• GRPO Objective — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Group Relative Policy Optimization — 1× in this paper
• Group Relative Policy Optimization (GRPO) — 1× in this paper · explained in 5 episodes
• KL Regularization — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Proximal Policy Optimization — 1× in this paper
• Sample Efficiency — 1× in this paper · explained in 4 episodes
• Singular Value Decomposition (SVD) — 1× in this paper · explained in 2 episodes
• Structured Reasoning — 1× in this paper · explained in 3 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Asymmetric REINFORCE for off-Policy Reinforcement Learning: Balancing positive and negative rewards
• MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention
• SEED-GRPO: Semantic Entropy Enhanced GRPO for Uncertainty-Aware Policy Optimization
• AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learning
• Reasoning with Exploration: An Entropy Perspective
• GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning
• The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models
• SRFT: A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for Reasoning
• One-shot Entropy Minimization
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language Models
• OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems
• Measuring Mathematical Problem Solving With the MATH Dataset
• Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model
• OpenAI o1 System Card
• Tulu 3: Pushing Frontiers in Open Language Model Post-Training
• Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning
• Learning What Reinforcement Learning Can't: Interleaved Online Fine-Tuning for Hardest Questions
• Tapered Off-Policy REINFORCE: Stable and efficient reinforcement learning for LLMs
• Proximal Policy Optimization Algorithms

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering