arXiv AI June 2, 2026 By Mingyi Wang, Zhuoer Shen, Yuheng Bu, Shaofeng Zou

Detector-Evasive LLM Paraphrasing via Constrained Policy Optimization

arXiv:2606. 00392v1 Announce Type: cross Abstract: AI-text detectors are vulnerable to paraphrasing and detector-guided paraphrasing attacks, but existing detector-evasion methods often lack precise control over semantic preservation.

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

Oct 26

StealthRL: Reinforcement Learning Paraphrase Attacks for Multi-Detector Evasion of AI-Text Detectors

arXiv:2602.08934v3 Announce Type: replace-cross Abstract: AI-text detectors are increasingly used in high-stakes settings, but their robustness to meaning-preserving adversarial rewriting remains unc...

By Suraj Ranganath, Atharv Ramesh

reinforcement-learning safety

arXiv Computation and Language

Sep 22

Team DArgk at the 2026 ELOQUENT lab for evaluating generative language model quality: Residuals of Humanity: AI Detection Evasion via GRPO Fine-Tuning

arXiv:2609.22221v1 Announce Type: new Abstract: Large language models (LLMs) can generate fluent and coherent text that is increasingly difficult to distinguish from human writing, motivating the dev...

By Antonela Tommasel, Juan Manuel Rodriguez

llms reinforcement-learning fine-tuning safety

arXiv AI

Jul 23

Co-Evolving LLM Evaluators and Policies via DynamicRubric

arXiv:2607. 20083v1 Announce Type: cross Abstract: Post-training with evaluator feedback on policy-induced samples serves as a major mechanism for improving large language models.

By Beining Wang, Weihang Su, Hongtao Tian, Hao Kong, Tao Yang, Ting Yao, Qingyi Pan, Yueyue Wu, Qingyao Ai, Min Zhang, Yiqun Liu

llms reinforcement-learning

arXiv Computer Vision

Oct 16

SCOPE: Semantic Bounded Credit Optimization for Prompt Engineering in Text-to-image Generation

SCOPE introduces a reinforcement learning approach for text‑to‑image prompt engineering that respects semantic spans such as objects, counts, attributes, and relations. By pooling policy log‑probability shifts within each semantic span, the method assigns a shared coefficient to token losses while using a single advantage per completion, eliminating the need for separate span rewards or extra image renders. Experiments on Qwen‑Image, SD3, and FLUX.1‑dev show average relative gains of 9.48% on GeneVal and 7.62% on T2I‑CompBench compared to vanilla GRPO, with ablation studies confirming the benefit of semantic boundaries and pooling.

By Yufei Jiao, Jinfa Huang, Zeyue Xue, Tianyu Xie, Yuexiao Ma, Rongrong Ji, Xiawu Zheng, Jiebo Luo

llms diffusion reinforcement-learning benchmarks safety

arXiv Machine Learning

Jun 2

Advantage Collapse in Group Relative Policy Optimization: Diagnosis and Mitigation

arXiv:2605. 21125v2 Announce Type: replace Abstract: Group Relative Policy Optimization (GRPO), a prominent algorithm within the Reinforcement Learning from Verifiable Rewards (RLVR) framework, has achieved strong results in improving the reasoning capabilities of large language models (LLMs).

By Xixiang He, Qiyao Sun, Ao Cheng, Xingming Li, Xuanyu Ji, Hailun Lu, Runke Huang, Qingyong Hu

llms reinforcement-learning benchmarks

arXiv AI

Jun 2

Boosting RL-Based Visual Reasoning with Selective Adversarial Entropy Intervention

arXiv:2512. 10414v2 Announce Type: replace Abstract: Recently, reinforcement learning (RL) has become a common choice in enhancing the reasoning capabilities of vision-language models (VLMs).

By Yang Yu, Zhuangzhuang Chen, Lanqing Li, Xiaomeng Li

llms reinforcement-learning fine-tuning multimodal safety

One email a morning, machine-written

Related stories

StealthRL: Reinforcement Learning Paraphrase Attacks for Multi-Detector Evasion of AI-Text Detectors

Team DArgk at the 2026 ELOQUENT lab for evaluating generative language model quality: Residuals of Humanity: AI Detection Evasion via GRPO Fine-Tuning

Co-Evolving LLM Evaluators and Policies via DynamicRubric

SCOPE: Semantic Bounded Credit Optimization for Prompt Engineering in Text-to-image Generation

Advantage Collapse in Group Relative Policy Optimization: Diagnosis and Mitigation

Boosting RL-Based Visual Reasoning with Selective Adversarial Entropy Intervention