English
Related papers

Related papers: Behavioral Integrity Verification for AI Agent Ski…

200 papers

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 (LLMs) evolve from code generators into collaborative partners for software engineers, our methods for evaluation are lagging. Current benchmarks, focused on code correctness, fail to capture the nuanced,…

Software Engineering · Computer Science 2026-01-01 Tao Dong , Harini Sampath , Ja Young Lee , Sherry Y. Shi , Andrew Macvean

Existing agent safety benchmarks report binary accuracy, conflating early intervention with post-mortem analysis. A detector that flags a violation at step 8 enables intervention; one that reports it at step 48 provides only forensic value.…

As AI systems gain increasing autonomy and execution capability, the number of discovered security vulnerabilities continues to rise. However, many of these vulnerabilities are not fundamentally novel, but instead reflect recurring classes…

Cryptography and Security · Computer Science 2026-05-27 Kevin Eykholt , Dhilung Kirat , Xiaokui Shu , Jiyong Jang , Frederico Araujo , Ian Molloy

Agentic AI systems are entering software engineering workflows, yet empirical evidence on how industrial organizations actually adopt them remains sparse. We present a qualitative interview study with sixteen practitioners across twelve…

Software Engineering · Computer Science 2026-05-15 Spyridon Alvanakis Apostolou , Jan Bosch , Helena Holmström Olsson

AI coding agents increasingly act directly within software environments, yet existing analyses of their failures rely on benchmark trajectories that miss how developers actually experience misalignment. We present an observational study of…

Software Engineering · Computer Science 2026-05-29 Ningzhi Tang , Chaoran Chen , Gelei Xu , Yiyu Shi , Yu Huang , Collin McMillan , Tao Dong , Toby Jia-Jun Li

Artificial intelligence (AI) systems are increasingly adopted as tool-using agents that can plan, observe their environment, and take actions over extended time periods. This evolution challenges current evaluation practices where the AI…

Cryptography and Security · Computer Science 2026-03-17 Simone Aonzo , Merve Sahin , Aurélien Francillon , Daniele Perito

This paper systematically investigates the security, privacy, and ethical risks, as well as the traceability challenges of OpenClaw, a locally executable AI agent system for natural language interaction and real-world task completion. While…

Cryptography and Security · Computer Science 2026-05-25 Yutong Jin , Zelin Zhang , Zhijin Lyu , Jianbing Ni

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

Code-capable large language model (LLM) agents are increasingly embedded into software engineering workflows where they can read, write, and execute code, raising the stakes of safety-bypass ("jailbreak") attacks beyond text-only settings.…

Cryptography and Security · Computer Science 2025-10-03 Shoumik Saha , Jifan Chen , Sam Mayers , Sanjay Krishna Gouda , Zijian Wang , Varun Kumar

What should a developer inspect before deploying an LLM agent: the model, the tool code, the deployment configuration, or all three? In practice, many security failures in agent systems arise not from model weights alone, but from the…

Cryptography and Security · Computer Science 2026-03-25 Haiyue Zhang , Yi Nian , Yue Zhao

Modern AI agents execute real-world side effects through tool calls such as file operations, shell commands, HTTP requests, and database queries. A single unsafe action, including accidental deletion, credential exposure, or data…

Artificial Intelligence · Computer Science 2026-05-07 Chenglin Yang

Software security vulnerabilities allow attackers to perform malicious activities to disrupt software operations. Recent Transformer-based language models have significantly advanced vulnerability detection, surpassing the capabilities of…

Cryptography and Security · Computer Science 2024-06-11 Aidan Z. H. Yang , Haoye Tian , He Ye , Ruben Martins , Claire Le Goues

The rapid evolution of Large Multimodal Models (LMMs) has enabled agents to perform complex digital and physical tasks, yet their deployment as autonomous decision-makers introduces substantial unintentional behavioral safety risks.…

Artificial Intelligence · Computer Science 2026-03-30 Yuxuan Li , Yi Lin , Peng Wang , Shiming Liu , Xuetao Wei

Traditional software relies on contracts -- APIs, type systems, assertions -- to specify and enforce correct behavior. AI agents, by contrast, operate on prompts and natural language instructions with no formal behavioral specification.…

Artificial Intelligence · Computer Science 2026-02-27 Varun Pratap Bhardwaj

Artificial Intelligence (AI) is revolutionizing scientific research, yet its growing integration into laboratory environments presents critical safety challenges. Large language models (LLMs) and vision language models (VLMs) now assist in…

Skills are increasingly used to extend LLM agents by packaging prompts, code, and configurations into reusable modules. As public registries and marketplaces expand, they form an emerging agentic supply chain, but also introduce a new…

Cryptography and Security · Computer Science 2026-03-31 Shenao Wang , Junjie He , Yanjie Zhao , Yayi Wang , Kan Yu , Haoyu Wang

The acquisition of agentic capabilities has transformed LLMs from "knowledge providers" to "action executors", a trend that while expanding LLMs' capability boundaries, significantly increases their susceptibility to malicious use. Previous…

Cryptography and Security · Computer Science 2025-05-30 Jinchuan Zhang , Lu Yin , Yan Zhou , Songlin Hu

Large language models are increasingly deployed as autonomous agents for multi-step workflows in real-world software environments. However, existing agent benchmarks are limited by trajectory-opaque grading, underspecified safety and…

Artificial Intelligence · Computer Science 2026-05-08 Bowen Ye , Rang Li , Qibin Yang , Yuanxin Liu , Linli Yao , Hanglong Lv , Zhihui Xie , Chenxin An , Lei Li , Lingpeng Kong , Qi Liu , Zhifang Sui , Tong Yang

Anthropic proposes the concept of skills for LLM agents to tackle multi-step professional tasks that simple tool invocations cannot address. A tool is a single, self-contained function, whereas a skill is a structured bundle of…