English
Related papers

Related papers: Toward a Principled Framework for Agent Safety Mea…

200 papers

The rapid proliferation of large language models (LLMs) has intensified the requirement for reliable safety evaluation to uncover model vulnerabilities. To this end, numerous LLM safety evaluation benchmarks are proposed. However, existing…

Computation and Language · Computer Science 2025-08-22 Xiangyang Zhu , Yuan Tian , Chunyi Li , Kaiwei Zhang , Wei Sun , Guangtao Zhai

The integration of tool use into large language models (LLMs) enables agentic systems with real-world impact. In the meantime, unlike standalone LLMs, compromised agents can execute malicious workflows with more consequential impact,…

Cryptography and Security · Computer Science 2025-02-17 Jizhou Chen , Samuel Lee Cong

Evaluating the safety of LLM-based agents is increasingly important because risks in realistic deployments often emerge over multi-step interactions rather than isolated prompts or final responses. Existing trajectory-level benchmarks…

Artificial Intelligence · Computer Science 2026-05-14 Yu Li , Haoyu Luo , Yuejin Xie , Yuqian Fu , Zhonghao Yang , Shuai Shao , Qihan Ren , Wanying Qu , Yanwei Fu , Yujiu Yang , Jing Shao , Xia Hu , Dongrui Liu

Behavioral studies of LLM-based software engineering agents extract operational rules about which trajectory shapes correlate with higher resolution rates: that a test step follows a code modification, that error cascades are short, or that…

Software Engineering · Computer Science 2026-05-19 Wei Ma , Zhi Chen , Jingxu Gu , Tianling Li , Shangqing Liu , Lingxiao Jiang

Test-time scaling has become a dominant paradigm for improving LLM agent reliability, yet current approaches treat compute as an abundant resource, allowing agents to exhaust token and tool budgets on redundant steps or dead-end…

Machine Learning · Computer Science 2026-03-16 Yushu Li , Wenlong Deng , Jiajin Li , Xiaoxiao Li

Modern LLM based agents are no longer passive text generators. They read repositories, call tools, browse the web, execute code, maintain memory, communicate with other agents, and act through long horizon workflows. This shift moves the…

Multiagent Systems · Computer Science 2026-05-12 Tianxiao Li , Yixing Ma , Haiquan Wen , Zhenglin Huang , Qianyu Zhou , Zeyu Fu , Guangliang Cheng

Large language models deployed as agents increasingly interact with external systems through tool calls--actions with real-world consequences that text outputs alone do not carry. Safety evaluations, however, overwhelmingly measure…

Artificial Intelligence · Computer Science 2026-02-20 Arnold Cartagena , Ariane Teixeira

The integration of vision-language models (VLMs) is driving a new generation of embodied agents capable of operating in human-centered environments. However, as deployment expands, these systems face growing safety risks, particularly when…

Cryptography and Security · Computer Science 2025-10-21 Zonghao Ying , Le Wang , Yisong Xiao , Jiakai Wang , Yuqing Ma , Jinyang Guo , Zhenfei Yin , Mingchuan Zhang , Aishan Liu , Xianglong Liu

LLM-based coding agents are rapidly being deployed in software development, yet their safety implications remain poorly understood. These agents, while capable of accelerating software development, may exhibit unsafe behaviors during normal…

Artificial Intelligence · Computer Science 2025-08-26 Matous Kozak , Roshanak Zilouchian Moghaddam , Siva Sivaraman

Autonomous agents based on Large Language Models (LLMs) are increasingly being utilized in complex software systems. However, reliability remains a significant challenge due to unpredictable failures such as hallucinations, execution…

Software Engineering · Computer Science 2026-05-11 Cheonsu Jeong , Younggun Shin

The scarcity of data depicting dangerous situations presents a major obstacle to training AI systems for safety-critical applications, such as construction safety, where ethical and logistical barriers hinder real-world data collection.…

Artificial Intelligence · Computer Science 2025-05-21 Vu Dinh Xuan , Hao Vo , David Murphy , Hoang D. Nguyen

Proactive large language model (LLM) agents aim to actively plan, query, and interact over multiple turns, enabling efficient task completion beyond passive instruction following and making them essential for real-world, user-centric…

Artificial Intelligence · Computer Science 2026-02-13 Yihang Yao , Zhepeng Cen , Haohong Lin , Shiqi Liu , Zuxin Liu , Jiacheng Zhu , Zhang-Wei Hong , Laixi Shi , Ding Zhao

This paper introduces a novel framework for simulating and analyzing how uncooperative behaviors can destabilize or collapse LLM-based multi-agent systems. Our framework includes two key components: (1) a game theory-based taxonomy of…

Multiagent Systems · Computer Science 2026-01-13 Devang Kulshreshtha , Wanyu Du , Raghav Jain , Srikanth Doss , Hang Su , Sandesh Swamy , Yanjun Qi

The popularity of large language models (LLMs) continues to grow, and LLM-based assistants have become ubiquitous. Information security awareness (ISA) is an important yet underexplored area of LLM safety. ISA encompasses LLMs' security…

Cryptography and Security · Computer Science 2026-03-23 Ofir Cohen , Gil Ari Agmon , Asaf Shabtai , Rami Puzis

The rapid adoption of LLMs in both research and industry highlights the challenges of deploying them safely and reveals a gap in the systematic evaluation of toxicity benchmarks. As organizations increasingly rely on these benchmarks to…

Artificial Intelligence · Computer Science 2026-05-12 Regina Gugg , Selina Niederländer , Andreas Stöckl , Martin Flechl

As LLM agents grow more capable of causing harm autonomously, AI developers will rely on increasingly sophisticated control measures to prevent possibly misaligned agents from causing harm. AI developers could demonstrate that their control…

Artificial Intelligence · Computer Science 2025-04-08 Tomek Korbak , Mikita Balesni , Buck Shlegeris , Geoffrey Irving

Large Language Model (LLM)-based agents are increasingly adopted in high-stakes settings, but current benchmarks evaluate mainly whether a task was completed, not how. We introduce Procedure-Aware Evaluation (PAE), a framework that…

Artificial Intelligence · Computer Science 2026-03-04 Hongliu Cao , Ilias Driouich , Eoin Thomas

Large Language Model (LLM)-based agents are increasingly deployed in real-world applications such as "digital assistants, autonomous customer service, and decision-support systems", where their ability to "interact in multi-turn,…

Artificial Intelligence · Computer Science 2025-07-21 Xueyang Zhou , Weidong Wang , Lin Lu , Jiawen Shi , Guiyao Tie , Yongtian Xu , Lixing Chen , Pan Zhou , Neil Zhenqiang Gong , Lichao Sun

Recent studies on the safety alignment of large language models (LLMs) have revealed that existing approaches often operate superficially, leaving models vulnerable to various adversarial attacks. Despite their significance, these studies…

Cryptography and Security · Computer Science 2025-06-02 Jianwei Li , Jung-Eun Kim

LLM agents increasingly run inside execution harnesses that dispatch tools, allocate resources, and route messages between specialized components. However, a harness can return a correct, benign answer over a trajectory that accesses…

Computation and Language · Computer Science 2026-05-19 Chengzhi Liu , Yichen Guo , Yepeng Liu , Yuzhe Yang , Qianqi Yan , Xuandong Zhao , Wenyue Hua , Sheng Liu , Sharon Li , Yuheng Bu , Xin Eric Wang