arXiv Machine Learning July 7, 2026 By Mickel Liu, Liwei Jiang, Yancheng Liang, Simon Shaolei Du, Yejin Choi, Tim Althoff, Natasha Jaques

Chasing Moving Targets with Online Self-Play Reinforcement Learning for Safer Language Models

Read the original on arXiv Machine Learning →

arXiv:2506. 07468v4 Announce Type: replace Abstract: Conventional large language model (LLM) safety alignment relies on a reactive, disjoint loop: attackers exploit a static model, then defenders patch exposed vulnerabilities.

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

arXiv AI

Jun 2

Safety Alignment of LMs via Non-cooperative Games

arXiv:2512. 20806v3 Announce Type: replace Abstract: Ensuring the safety of language models (LMs) while maintaining their usefulness remains a critical challenge in AI alignment.

By Anselm Paulus, Ilia Kulikov, Brandon Amos, R\'emi Munos, Ivan Evtimov, Kamalika Chaudhuri, Arman Zharmagambetov

llms agents reinforcement-learning fine-tuning safety

arXiv Machine Learning

Jun 5

Alignment Risks from Capability-Seeking RL Training

arXiv:2602. 12124v2 Announce Type: replace Abstract: While most AI alignment research focuses on preventing models from generating explicitly harmful content, a more subtle risk arises from capability-seeking RL training in vulnerable environments.

By Yujun Zhou, Yue Huang, Han Bao, Kehan Guo, Zhenwen Liang, Pin-Yu Chen, Tian Gao, Werner Geyer, Nuno Moniz, Nitesh V Chawla, Xiangliang Zhang

llms reinforcement-learning fine-tuning safety

arXiv AI

Aug 6

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic)

arXiv:2608. 04317v1 Announce Type: cross Abstract: Autonomous cyber defense systems based on Deep Reinforcement Learning (DRL) have attracted significant research attention, yet remain evaluated almost exclusively against static, heuristic red agents, leaving their robustness against adaptive threats critically understudied.

By Ryozo Masukawa, Ian Bryant, Armita Kazeminajafabadi, Sanggeon Yun, Hyunwoo Oh, SungHeon Jeong, Nathaniel D. Bastian, Mahdi Imani, Mohsen Imani

llms agents reinforcement-learning benchmarks

arXiv AI

Jun 16

Reward Hacking in Language Model Agents: Revisiting AI Safety Gridworlds

arXiv:2606. 15385v1 Announce Type: new Abstract: Reward hacking, where AI systems exploit misspecified objectives to achieve high reward without satisfying intended goals, remains a central challenge in AI safety.

By \"Omer Veysel \c{C}a\u{g}atan, Xuandong Zhao

llms agents reinforcement-learning safety

Hugging Face Trending Papers

Aug 5

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic)

Autonomous cyber defense systems based on Deep Reinforcement Learning (DRL) have attracted significant research attention, yet remain evaluated almost exclusively against static, heuristic red agents, leaving their robustness against adaptive threats critically understudied. Meanwhile, recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) have improved LLM reasoning, but their integration into cybersecurity remains elusive due to the absence of suitable benchmark environments and interaction datasets.

llms agents reinforcement-learning benchmarks

arXiv Machine Learning

Jul 1

Addressing Over-Refusal in LLMs with Competing Rewards

arXiv:2606. 31748v1 Announce Type: new Abstract: Safety training on language models often induces over-refusal: improved safety on harmful prompts at the cost of increased refusal on harmless ones.

By Taeyoun Kim, Aviral Kumar

llms reinforcement-learning safety

Related stories

Safety Alignment of LMs via Non-cooperative Games

Alignment Risks from Capability-Seeking RL Training

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic)

Reward Hacking in Language Model Agents: Revisiting AI Safety Gridworlds

Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic)

Addressing Over-Refusal in LLMs with Competing Rewards