arXiv AI June 17, 2026 By Ziliang Wang, Kang An, Faqiang Qian, Jialu Cai, Cijun Ouyang, Yuhang Wang, Qibing Ren, Yichao Wu

Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs

Read the original on arXiv AI →

arXiv:2606. 17735v1 Announce Type: new Abstract: Although reinforcement learning (RL) has expanded the cognitive boundaries of large language models (LLMs), it often remains vulnerable to the autoregressive curse in long-horizon logical reasoning: small epistemic perturbations introduced early in generation can propagate irreversibly along the Markov decision process flow, triggering cascading failures that drive the reasoning trajectory toward collapse.

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

arXiv AI

Aug 7

DASH: Divergence-Adaptive Supervision Horizons for On-Policy Self-Distillation of Reasoning Models

arXiv:2608. 06243v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) improves the reasoning capabilities of large language models using automatically verifiable outcome signals, but these signals are typically sparse and at the sequence-level.

By ZhiYan Hou, Xinyu Tang, Hongyan An, Jianjin Zhang, Weizhen Wang, Yunyun Han, Gengsheng Li, Xiangzhao Hao, Haiyun Guo, Wenbin Hu, Jinqiao Wang, Yafeng Deng

llms reinforcement-learning efficiency benchmarks

arXiv Machine Learning

Jun 2

Internalize the Temperature: On-Policy Self-Distillation as Policy Reheater for Reinforcement Learning

arXiv:2606. 00755v1 Announce Type: cross Abstract: Reinforcement learning from verifiable rewards improves the reasoning ability of large language models, but often suffers from entropy collapse, in which increasingly concentrated policies reduce rollout diversity and useful learning signals.

By Xuewei Yang, Jiachen Yu, Jie Wu, Shaoning Sun, Junjie Wang, Yujiu Yang

llms reinforcement-learning efficiency

arXiv AI

Jun 19

Beyond Reasoning Gains: Mitigating General-Capability Forgetting in Large Reasoning Models

arXiv:2510. 21978v2 Announce Type: replace-cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has delivered impressive gains in mathematical and multimodal reasoning and has become a standard post-training paradigm for contemporary language and vision-language models.

By Hoang Phan, Xianjun Yang, Yuanshun Yao, Jingyu Zhang, Shengjie Bi, Xiaocheng Tang, Madian Khabsa, Lijuan Liu, Deren Lei

llms reinforcement-learning multimodal benchmarks

arXiv AI

Jul 14

Depth-Entropy Guided Sampling for Training-Free LLM Reasoning

arXiv:2607. 09693v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become the dominant paradigm for improving the reasoning capabilities of large language models, but it requires expensive training, curated data, and reward signals.

By Zibin Meng, Peng Xie, Kani Chen

llms reinforcement-learning benchmarks

arXiv AI

Jun 18

Sparsity Curse: Understanding RLVR Model Parameter Space from Model Merging

arXiv:2606. 18521v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Reward (RLVR) has emerged as a powerful post-training paradigm that surpasses Supervised Fine-Tuning (SFT) in eliciting reasoning intelligence and resisting catastrophic forgetting.

By Chenrui Wu, Zexi Li, Jiajun Bu, Jiangchuan Liu, Haishuai Wang

reinforcement-learning fine-tuning efficiency benchmarks

arXiv AI

Aug 11

How Much Backtracking is Enough? Exploring the Interplay of SFT and RL in Enhancing LLM Reasoning

arXiv:2505. 24273v2 Announce Type: replace Abstract: Recent advancements in large language models (LLMs) suggest that reinforcement learning (RL) effectively internalizes search strategies, yielding significant improvements on challenging reasoning tasks through extended chains of thought.

By Hongyi James Cai, Junlin Wang, Xiaoyin Chen, Bhuwan Dhingra

llms reinforcement-learning fine-tuning

Related stories

DASH: Divergence-Adaptive Supervision Horizons for On-Policy Self-Distillation of Reasoning Models

Internalize the Temperature: On-Policy Self-Distillation as Policy Reheater for Reinforcement Learning

Beyond Reasoning Gains: Mitigating General-Capability Forgetting in Large Reasoning Models

Depth-Entropy Guided Sampling for Training-Free LLM Reasoning

Sparsity Curse: Understanding RLVR Model Parameter Space from Model Merging

How Much Backtracking is Enough? Exploring the Interplay of SFT and RL in Enhancing LLM Reasoning