arXiv Machine Learning June 15, 2026 By Hen Davidov, Nachshon Cohen, Oren Kalinsky, Yaron Fairstein, Guy Kushilevitz, Ram Yazdi, Patrick Rebeschini

Knowing When to Quit: A Principled Framework for Dynamic Abstention in LLM Reasoning

Read the original on arXiv Machine Learning →

arXiv:2604. 18419v5 Announce Type: replace Abstract: LLMs utilizing chain-of-thought reasoning often waste substantial compute by producing long, incorrect responses.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI

Aug 11

Understanding and Mitigating Premature Confidence for Better LLM Reasoning

arXiv:2605. 24396v2 Announce Type: replace Abstract: Long chains of thought (CoT) from current language models frequently contain logical gaps and unjustified leaps, limiting the gains from additional test-time compute.

By Jingchu Gai, Guanning Zeng, Christina Baek, Chen Wu, J. Zico Kolter, Andrej Risteski, Aditi Raghunathan

llms reinforcement-learning benchmarks safety

arXiv AI

Jun 2

Process Reward Agents for Steering Knowledge-Intensive Reasoning

arXiv:2604. 09482v2 Announce Type: replace Abstract: Reasoning in knowledge-intensive domains remains challenging as intermediate steps are often not locally verifiable: unlike math or code, evaluating step correctness may require synthesizing clues across large external knowledge sources.

By Jiwoong Sohn, Tomasz Sternal, Kenneth Styppa, Torsten Hoefler, Michael Moor

rag agents benchmarks

arXiv AI

Jul 28

Not All LLM Reasoning is Visible in the Chain-of-Thought

arXiv:2607. 22925v1 Announce Type: cross Abstract: A key question for AI safety is whether a language model expresses all of its reasoning in its output tokens.

By Vatsal Baherwani, Tom Goldstein, Ashwinee Panda

llms reinforcement-learning fine-tuning safety

arXiv AI

Jul 7

rePIRL: Learn PRM with Inverse RL for LLM Reasoning

arXiv:2602. 07832v3 Announce Type: replace-cross Abstract: Process rewards have been widely used in deep reinforcement learning to improve training efficiency, reduce variance, and prevent reward hacking.

By Xian Wu, Kaijie Zhu, Ying Zhang, Lun Wang, Wenbo Guo

llms reinforcement-learning benchmarks

arXiv AI

1d ago

Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability

arXiv:2604. 06628v2 Announce Type: replace Abstract: A prevailing narrative in LLM post-training holds that supervised finetuning (SFT) memorizes while reinforcement learning (RL) generalizes.

By Qihan Ren, Peng Wang, Ruikun Cai, Shuai Shao, Dadi Guo, Yuejin Xie, Yafu Li, Quanshi Zhang, Xia Hu, Jing Shao, Dongrui Liu

llms reinforcement-learning fine-tuning safety data-engineering

arXiv Machine Learning

Jun 16

ExpRL: Exploratory RL for LLM Mid-Training

arXiv:2606. 17024v1 Announce Type: new Abstract: Sparse reward reinforcement learning (RL) has become a standard tool for improving LLM reasoning, but its success depends critically on the coverage present in the base model.

By Violet Xiang, Amrith Setlur, Chase Blagden, Nick Haber, Aviral Kumar

llms reinforcement-learning fine-tuning efficiency

Related stories

Understanding and Mitigating Premature Confidence for Better LLM Reasoning

Process Reward Agents for Steering Knowledge-Intensive Reasoning

Not All LLM Reasoning is Visible in the Chain-of-Thought

rePIRL: Learn PRM with Inverse RL for LLM Reasoning

Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability

ExpRL: Exploratory RL for LLM Mid-Training