arXiv Machine Learning July 28, 2026 By Zhibin Kang, Hanmo You, Dong Wang, Haiming Zheng, Junjie Chen

Evaluating Fuzz Testing for Reinforcement Learning Agents

Read the original on arXiv Machine Learning →

arXiv:2607. 24577v1 Announce Type: new Abstract: Reinforcement Learning (RL) agents are increasingly deployed in safety-critical domains such as robotics, autonomous driving, and drone control, where unexpected behaviors may lead to severe real-world consequences.

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

arXiv AI

Jul 3

Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification

arXiv:2607. 01793v1 Announce Type: new Abstract: LLM agents increasingly perform autonomous actions through external tools, leading to complex and evolving safety risks.

By Yunhao Feng, Ruixiao Lin, Ming Wen, Qinqin He, Yanming Guo, Yifan Ding, Yutao Wu, Jialuo Chen, Yunhao Chen, Xiaohu Du, Jianan Ma, Zixing Chen, Zhuoer Xu, Xingjun Ma, Xinhao Deng

llms agents safety

arXiv AI

1d ago

AeroCopilotBench: A Two-Tier Benchmark for Evaluating LLM Agents as Aviation Copilots in an Interactive Virtual Cockpit Environment

arXiv:2608. 16349v1 Announce Type: new Abstract: Large language model (LLM) agents may assist flight crews with complex decisions and task execution, but existing aviation evaluations centered on static knowledge do not support systematic testing of procedural execution and safety compliance in interactive environments.

By Yuchen Yuan, Zhenghuang Wu, Yuangan Li, Liang Ma, Ke Li

llms agents benchmarks safety

arXiv AI

Jul 9

Gimitest: A Comprehensive Tool for Testing Reinforcement Learning Policies

arXiv:2607. 07029v1 Announce Type: cross Abstract: Reinforcement learning (RL) policies can be unsafe and vulnerable to attacks.

By Dennis Gross, Quentin Mazouni, Helge Spieker, Arnaud Gotlieb

agents reinforcement-learning

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

Aug 11

AIVV: Neuro-Symbolic LLM Agent-Integrated Verification and Validation for Trustworthy Autonomous Systems

arXiv:2604. 02478v2 Announce Type: replace Abstract: Deep learning models excel at detecting anomaly patterns in normal data.

By Jiyong Kwon, Ujin Jeon, Sooji Lee, Guang Lin

llms agents

arXiv AI

Jun 2

Before the Model Learns the Bug:Fuzzing RLVR Verifiers

arXiv:2606. 01066v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) replaces human preference labels with executable reward functions such as math answer checkers, JSON tool-call validators, and code unit-test harnesses.

By Jaideep Ray

reinforcement-learning safety

Related stories

Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification

AeroCopilotBench: A Two-Tier Benchmark for Evaluating LLM Agents as Aviation Copilots in an Interactive Virtual Cockpit Environment

Gimitest: A Comprehensive Tool for Testing Reinforcement Learning Policies

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

AIVV: Neuro-Symbolic LLM Agent-Integrated Verification and Validation for Trustworthy Autonomous Systems

Before the Model Learns the Bug:Fuzzing RLVR Verifiers