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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

4d ago

Self-discovering RL in the Era of Experience: Is Learning History an Asset or a Burden?

arXiv:2609.35897v1 Announce Type: new Abstract: The pursuit of recursive self-improvement (RSI) toward general intelligence is divided between macro-level language model scaling and the interaction-d...

By Haomin Luo (University of Cambridge, Models2 AI)

llms reinforcement-learning benchmarks

arXiv Machine Learning

Sep 1

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...

By Xin Jiang, Minhao Wang, Wen Wu, Zhentao Xie, Shangheng Du, Jinxin Shi, Jiabao Zhao

llms reinforcement-learning

arXiv AI

2d ago

Does Scaling Reinforcement Learning Really Require More Training?

arXiv:2610.01133v1 Announce Type: cross Abstract: Scaling reasoning typically spends more compute on reinforcement learning (RL) or on inference. We show that a completed RL training history can yiel...

By Bangji Yang, Jiajun Fan, Hongba Ma, Ruihan Guo, Ge Liu

reinforcement-learning benchmarks

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 AI

Sep 1

Locked at the Entrance, Open Inside: Where RLVR Narrows the Solution Space

The paper investigates why reinforcement learning with verifiable rewards (RLVR) reduces the diversity of solutions in reasoning tasks. By analyzing the Countdown task, the authors show that RLVR contracts the solution space mainly at the entrance—before the first arithmetic operation—causing a 67% drop in solution coverage. They demonstrate that providing an unselected entrance prefix or applying entrance‑targeted interventions can restore or even improve coverage without harming accuracy.

By Qiancheng Zhou, Ruizhe Li

llms reinforcement-learning fine-tuning 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

One email a morning, machine-written

Related stories

Self-discovering RL in the Era of Experience: Is Learning History an Asset or a Burden?

ERR+: Sequential Entropy Resolution for Efficient and Decisive LLM Reasoning

Does Scaling Reinforcement Learning Really Require More Training?

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

Locked at the Entrance, Open Inside: Where RLVR Narrows the Solution Space

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