arXiv AI
DCRL: Decoupling and Coupling Reinforcement Learning via Policy-Reward Manifold Alignment
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jul 7
A Technical Survey of Reinforcement Learning Techniques for Large Language Models
arXiv:2507. 04136v2 Announce Type: replace Abstract: This survey offers a comprehensive foundation on the integration of RL with language models, highlighting prominent algorithms such as Proximal Policy Optimization (PPO), Q-Learning, and Actor-Critic methods.
arXiv Machine Learning
Sep 4
Gradients Know What Outcomes Don't: Unlocking Reinforcement Learning for LLM Reasoning with Gradient-Aligned Rewards
The paper introduces Gradient-Aligned Reward (GAR), a reinforcement learning technique that uses truncated backpropagation to generate a compact gradient vector for each rollout and compares it to an expert-anchor gradient via cosine similarity. This dense, reasoning-aware reward improves large language model chain-of-thought reasoning on math benchmarks and transfers to other tasks without domain‑specific data, while adding less than 9% computational overhead. GAR outperforms existing baselines such as GRPO on Qwen3-4B and Qwen3-8B models.
arXiv AI
Aug 19
Co-RL: Unsupervised Reasoning Emerges from Diverse Cohort in Multi-agent RL
Co‑RL is a multi‑agent reinforcement learning framework that trains several decoupled models without shared parameters, using rewards generated by their peers. By increasing cohort diversity—through heterogeneous model families, varying sizes, and rephrased training samples—Co‑RL reduces self‑reinforcing feedback loops, preserves behavioral diversity, and prevents training collapse. Across both text‑only and multimodal benchmarks, Co‑RL outperforms base models and prior label‑free methods, achieving gains of 3.0‑8.6% on seven text benchmarks and 2.3‑7.2% on four multimodal benchmarks, while matching or surpassing supervised approaches without any ground‑truth labels.
arXiv Machine Learning
Aug 12
Reinforcement Learning-based Semi-supervised Knowledge Distillation with LLM-as-a-Judge
arXiv:2604. 02621v2 Announce Type: replace-cross Abstract: Reinforcement Learning (RL) substantially improves the reasoning capabilities of language models, but most existing RL fine-tuning approaches rely entirely on ground-truth verifiable rewards and thus labeled datasets with verifiable answers.
arXiv AI
Aug 3
Don't Mix Rewards, Mix Policies: Policy Decomposition and Optimization for Multi-Reward RL
arXiv:2607. 29246v1 Announce Type: new Abstract: Modern large language models (LLMs) are expected not just to answer correctly, but to adapt their behavior to different human values and use cases.
arXiv Machine Learning
Jun 30
Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation
arXiv:2602. 09305v2 Announce Type: replace Abstract: Large Language Models (LLMs) demonstrate transformative potential, yet their reasoning remains inconsistent and unreliable.