English
Related papers

Related papers: Policy-Invisible Violations in LLM-Based Agents

200 papers

Existing agent-safety evaluation has focused mainly on externally induced risks. Yet agents may still enter unsafe trajectories under benign conditions. We study this complementary but underexplored setting through the lens of…

Machine Learning · Computer Science 2026-04-16 Jiacheng Wang , Jinchang Hou , Fabian Wang , Ping Jian , Chenfu Bao , Zhonghou Lv

The robustness of LLMs to jailbreak attacks, where users design prompts to circumvent safety measures and misuse model capabilities, has been studied primarily for LLMs acting as simple chatbots. Meanwhile, LLM agents -- which use external…

Large Language Models (LLMs) exhibit substantial promise in enhancing task-planning capabilities within embodied agents due to their advanced reasoning and comprehension. However, the systemic safety of these agents remains an underexplored…

Artificial Intelligence · Computer Science 2025-04-22 Yuting Huang , Leilei Ding , Zhipeng Tang , Tianfu Wang , Xinrui Lin , Wuyang Zhang , Mingxiao Ma , Yanyong Zhang

Safe deployment of Large Language Model (LLM) agents in autonomous settings requires reliable oversight mechanisms. A central challenge is detecting scheming, where agents covertly pursue misaligned goals. One approach to mitigating such…

Computation and Language · Computer Science 2026-03-03 Simon Storf , Rich Barton-Cooper , James Peters-Gill , Marius Hobbhahn

Computer-using agents powered by Vision-Language Models (VLMs) have demonstrated human-like capabilities in operating digital environments like mobile platforms. While these agents hold great promise for advancing digital automation, their…

The rapid deployment of LLM-based autonomous agents has introduced safety risks that extend far beyond traditional LLM concerns, prompting a proliferation of safety benchmarks since late 2023. However, these benchmarks have developed…

Computers and Society · Computer Science 2026-05-19 Miles Q. Li , Benjamin C. M. Fung , Boyang Li , Heba Ismail , Farkhund Iqbal

Third-party skills are becoming the package ecosystem for LLM agents. They package natural-language instructions, helper scripts, templates, documents, and service configuration into reusable workflows. This makes skills useful, but it also…

Cryptography and Security · Computer Science 2026-05-15 Haomin Zhuang , Hanwen Xing , Yujun Zhou , Yuchen Ma , Yue Huang , Yili Shen , Yufei Han , Xiangliang Zhang

Large Language Models (LLMs) increasingly use persistent memory from past interactions to enhance personalization and task performance. However, this memory introduces critical risks when sensitive information is revealed in inappropriate…

As autonomous AI agents are increasingly deployed in high-stakes environments, ensuring their safety and alignment with human values is becoming a practical deployment concern. Current benchmarks for AI agents primarily evaluate refusal of…

Artificial Intelligence · Computer Science 2026-05-12 Miles Q. Li , Benjamin C. M. Fung , Martin Weiss , Pulei Xiong , Khalil Al-Hussaeni , Claude Fachkha

Large Language Model (LLM)-based agentic systems have shown growing promise in tackling complex, multi-step tasks through autonomous planning, reasoning, and interaction with external environments. However, the stochastic nature of LLM…

Human-Computer Interaction · Computer Science 2026-03-31 Shuo Yan , Xiaolin Wen , Shaolun Ruan , Yanjie Zhang , Jiaming Mi , Yushi Sun , Huamin Qu , Rui Sheng

Large language models (LLMs) are increasingly deployed as agents in various contexts by providing tools at their disposal. However, LLM agents can exhibit unpredictable behaviors, including taking undesirable and/or unsafe actions. In order…

Artificial Intelligence · Computer Science 2025-10-27 Ilija Lichkovski , Alexander Müller , Mariam Ibrahim , Tiwai Mhundwa

A common problem for agents operating in real-world environments is that the response of an environment to their actions may be non-deterministic and observed through noise. This renders environmental state and progress towards completing a…

Artificial Intelligence · Computer Science 2024-05-21 William E Bishop , Alice Li , Christopher Rawles , Oriana Riva

As organizations increasingly deploy LLMs in sensitive domains such as legal, financial, and medical settings, ensuring alignment with internal organizational policies has become a priority. Existing content moderation frameworks remain…

Machine Learning · Computer Science 2026-01-21 Oren Rachmil , Avishag Shapira , Roy Betser , Itay Gershon , Omer Hofman , Asaf Shabtai , Yuval Elovici , Roman Vainshtein

Cybersecurity post-incident reviews are essential for identifying control failures and improving organisational resilience, yet they remain labour-intensive, time-consuming, and heavily reliant on expert judgment. This paper investigates…

Cryptography and Security · Computer Science 2026-01-08 Huan Lin Oh , Jay Yong Jun Jie , Mandy Lee Ling Siu , Jonathan Pan

Organisations are starting to adopt LLM-based AI agents, with their deployments naturally evolving from single agents towards interconnected, multi-agent networks. Yet a collection of safe agents does not guarantee a safe collection of…

Multiagent Systems · Computer Science 2025-08-11 Alistair Reid , Simon O'Callaghan , Liam Carroll , Tiberio Caetano

As large language models are deployed in high-stakes enterprise applications, from healthcare to finance, ensuring adherence to organization-specific policies has become essential. Yet existing safety evaluations focus exclusively on…

Artificial Intelligence · Computer Science 2026-01-06 Dasol Choi , DongGeon Lee , Brigitta Jesica Kartono , Helena Berndt , Taeyoun Kwon , Joonwon Jang , Haon Park , Hwanjo Yu , Minsuk Kahng

Real-world requests to AI agents are fundamentally underspecified. Natural human communication relies on shared context and unstated constraints that speakers expect listeners to infer. Current agentic benchmarks test explicit…

Artificial Intelligence · Computer Science 2026-02-25 Ved Sirdeshmukh , Marc Wetter

LLM-based agents execute real-world workflows via tools and memory. These affordances enable ill-intended adversaries to also use these agents to carry out complex misuse scenarios. Existing agent misuse benchmarks largely test…

Computation and Language · Computer Science 2026-05-19 Nivya Talokar , Ayush K Tarun , Murari Mandal , Maksym Andriushchenko , Antoine Bosselut

Large Language Models (LLMs) are increasingly used for decision making in embodied agents, yet existing safety evaluations often rely on coarse success rates and domain-specific setups, making it difficult to diagnose why and where these…

Artificial Intelligence · Computer Science 2025-05-27 Yejin Son , Minseo Kim , Sungwoong Kim , Seungju Han , Jian Kim , Dongju Jang , Youngjae Yu , Chanyoung Park

Autonomous agent systems powered by Large Language Models (LLMs) have demonstrated promising capabilities in automating complex tasks. However, current evaluations largely rely on success rates without systematically analyzing the…

Artificial Intelligence · Computer Science 2025-08-19 Ruofan Lu , Yichen Li , Yintong Huo