arXiv AI
GMTS: Gradient Magnitude-based Token Selection Improves RLVR Training for LLM Reasoning
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jul 1
Which Tokens Matter? Adaptive Token Selection for RLVR with the Relative Surprisal Index
arXiv:2606. 31575v1 Announce Type: new Abstract: Reinforcement learning (RL) has become a powerful tool for propelling Large Language Models (LLMs) beyond imitation-based training towards more robust reasoning capabilities.
Hugging Face Trending Papers
Jun 3
GRAIL: Gradient-Reweighted Advantages for Reinforcement Learning with Verifiable Rewards
Reinforcement learning with verifiable rewards (e. g.
arXiv Computation and Language
Aug 28
Boosting LLM Exploration via Weak-Model Guidance in RLVR
The paper introduces a method to enhance large language model (LLM) exploration in Reinforcement Learning with Verifiable Rewards (RLVR) by guiding the target model with partial reasoning trajectories from smaller, weaker language models. This weak-model guidance disrupts over‑confidence, preserves generative diversity, and mitigates entropy collapse without extra fine‑tuning or complex reward designs. Experiments on mathematical benchmarks show consistent improvements over vanilla RLVR, especially as the number of allowed attempts ($k$) increases, indicating broader reasoning coverage.
arXiv AI
Jun 6
InfoDensity: Rewarding Information-Dense Traces for Efficient Reasoning
arXiv:2603. 17310v2 Announce Type: replace Abstract: Large Language Models (LLMs) with extended reasoning capabilities often generate verbose and redundant reasoning traces, incurring unnecessary computational cost.
arXiv Machine Learning
Jun 9
ConSteer-RL: Steering Reasoning Capabilities in Large Language Models via Confidence-Aware Reinforcement Learning
arXiv:2606. 08088v1 Announce Type: new Abstract: Reinforcement Learning from Verifiable Rewards (RLVR) has recently become a key paradigm for improving the reasoning abilities of Large Language Models (LLMs), yet it remains limited by sparse binary rewards and its ignorance of model-internal uncertainty.
arXiv Machine Learning
3d ago
ERR+: Sequential Entropy Resolution for Efficient and Decisive LLM Reasoning
arXiv:2608.28771v1 Announce Type: new Abstract: Large reasoning models achieve strong performance on complex tasks by generating extended chain-of-thought (CoT) traces via reinforcement learning with...