arXiv Machine Learning
Learning from the Gap Between Pass@K and Pass@1
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Jun 18
REVES: REvision and VErification--Augmented Training for Test-Time Scaling
arXiv:2606. 18910v1 Announce Type: new Abstract: Test-time scaling via sequential revision has emerged as a powerful paradigm for enhancing Large Language Model (LLM) reasoning.
arXiv Computation and Language
Sep 2
From Base Rollouts to RL Reasoning: A Budgeted Search Perspective
arXiv:2609.01274v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) improves language-model reasoning, but how these gains relate to inference-time decoding and sear...
arXiv Machine Learning
Jun 11
Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling
arXiv:2606. 12370v1 Announce Type: new Abstract: Reinforcement learning (RL) has become a key component in modern large language models, yet the rollout stage remains the key bottleneck in RL training pipelines.
arXiv AI
Jun 3
Exploiting Verification-Generation Gap: Test-Time Reinforcement Learning with Confidence-Conditioned Verification
arXiv:2606. 03608v1 Announce Type: cross Abstract: Test-time reinforcement learning has emerged as a promising paradigm for enhancing the complex reasoning abilities of large language models in a completely label-free manner.
Hugging Face Trending Papers
Jun 10
Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling
Reinforcement learning (RL) has become a key component in modern large language models, yet the rollout stage remains the key bottleneck in RL training pipelines. Although Multi-Token Prediction (MTP) offers a natural solution to accelerate rollouts through speculative decoding, many studies have observed that MTP acceptance rates degrade significantly during RL training, leading to limited speedup performance.
arXiv AI
Jun 19
Think Again or Think Longer? Selective Verification for Budget-Aware Reasoning
arXiv:2606. 19808v1 Announce Type: new Abstract: Test-time reasoning is increasingly used as a serving-time control knob, but extra reasoning is not uniformly valuable: it can repair failed attempts, waste compute on already-correct answers, or introduce harmful answer changes.