arXiv AI August 5, 2026 By Saqib Shouqi, Abdullah Nazly, Januki Wanniarachchi, Ravisha De Alwis

Adversarial Stress Testing of Role-Playing Language Agents using Multi-Agent Evaluation

arXiv:2608. 03166v1 Announce Type: new Abstract: Role-Playing Language Agents (RPLAs) are increasingly deployed in high-stakes applications such as healthcare assistance, customer support, and education, where maintaining consistent personas, ethical constraints, and behavioral coherence under adversarial pressure is critical.

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

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

Jul 31

Adversarial Pragmatics for AI Safety Evaluation: A Diagnostic Framework and Seed Benchmark for Language-Mediated Control

arXiv:2607. 01153v3 Announce Type: replace-cross Abstract: Safety evaluations for language models increasingly depend on judgments about ambiguous natural-language behaviour: whether a model followed an instruction, refused appropriately, complied with a policy, or misreported progress in an agentic task.

By Brett Reynolds

llms agents benchmarks safety

arXiv AI

Jun 19

The Autonomy Tax: Defense Training Breaks LLM Agents

arXiv:2603. 19423v2 Announce Type: replace-cross Abstract: Large language model (LLM) agents increasingly rely on external tools (file operations, API calls, database transactions) to autonomously complete complex multi-step tasks.

By Shawn Li, Yue Zhao

llms agents benchmarks safety

arXiv AI

Jun 12

ERTS: Adversarial Robustness Testing of Ethical AI via Semantic Perturbation in a Bounded Consequence Space

arXiv:2606. 13282v1 Announce Type: new Abstract: As AI systems are deployed in high-stakes ethical contexts such as healthcare triage, autonomous vehicle control, and employment screening, formal methods for evaluating their robustness against adversarial manipulation of ethical reasoning remain underdeveloped.

By Pratyush Chaudhari

llms agents robotics safety

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 AI

Jul 22

A Red Teaming Framework for Large Language Models: A Case Study on Faithfulness Evaluation

arXiv:2606. 25476v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have demonstrated remarkable performance across natural language processing tasks, yet their deployment in high-stakes applications raises critical concerns regarding reliability, safety, and trustworthiness.

By Abrar Alotaibi, Raed Mughus, Moataz Ahmed

llms nlp safety

Related stories

Alignment Risks from Capability-Seeking RL Training

Adversarial Pragmatics for AI Safety Evaluation: A Diagnostic Framework and Seed Benchmark for Language-Mediated Control

The Autonomy Tax: Defense Training Breaks LLM Agents

ERTS: Adversarial Robustness Testing of Ethical AI via Semantic Perturbation in a Bounded Consequence Space

Safety Alignment of LMs via Non-cooperative Games

A Red Teaming Framework for Large Language Models: A Case Study on Faithfulness Evaluation