arXiv:2604. 02022v4 Announce Type: replace Abstract: 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.
arXiv:2605.27690v2 Announce Type: replace-cross Abstract: LLM agents increasingly operate through multi-turn tool use and environment interaction, where safety risks often emerge from intermediate st...
arXiv:2606. 09890v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as autonomous agents capable of executing multi-step action trajectories toward a given objective.
arXiv:2602.03100v2 Announce Type: replace Abstract: Large Language Models (LLMs) are increasingly deployed as agents that operate in real-world environments, introducing safety risks beyond linguisti...
arXiv:2606. 08531v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly evolving from simple text-based interaction systems into LLM agents that can maintain memory, use tools, access external environments, and execute tasks.
arXiv:2607. 29254v1 Announce Type: new Abstract: AI agents extend large language models (LLMs) with external tools, enabling them to perform complex tasks and translate model outputs into consequential real-world actions.
HINTBench is a new benchmark for evaluating agents’ intrinsic risk, comprising 596 trajectories (400 synthetic risky, 136 synthetic safe, 30 real risky, 30 real safe) with an average length of 24 steps. It supports three tasks—risk detection, risk-step localization, and intrinsic failure-type identification—using a unified five-constraint taxonomy. Experiments show a large performance gap: while large language models can detect risky trajectories, they score below 37 on strict-F1 for risk-step localization, and existing guard models transfer poorly to this setting.
arXiv:2606. 08531v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly evolving from simple text-based interaction systems into LLM agents that can maintain memory, use tools, access external environments, and execute tasks.
arXiv:2608. 05695v1 Announce Type: new Abstract: As large language model (LLM) agents increasingly invoke external tools and interact with real-world systems, unsafe actions may cause irreversible consequences on external states, user data, and downstream services.
The paper introduces a black-box framework for evaluating agentic AI systems, focusing on multi-step vulnerabilities that standard single-turn tests miss. It presents a seven-domain taxonomy linking observable behaviors to risk categories, an automated SAGE-RT red-teaming process generating 120 adversarial scenarios per domain, and a human-validated evaluation using LLM judges. Empirical tests on CrewAI and AutoGen agents show significant governance, privacy, and behavior risks, demonstrating the framework’s ability to uncover critical architectural weaknesses without privileged access.
LatentRiskBench is a new benchmark designed to evaluate state-dependent safety risks in enterprise agents, where the safety of an action depends on the workflow state rather than the action alone. It pairs risky trajectories with benign ones that share the same terminal action but differ in latent policy-relevant states, forcing models to reconstruct context instead of relying on action cues. The benchmark introduces residual risk metrics and demonstrates that state-level evaluation detects 96% of violations compared to only 9% for action-level methods, highlighting the inadequacy of existing guardrails.
LPS-Bench is a benchmark designed to evaluate the safety awareness of computer‑use agents (CUAs) in long‑horizon planning tasks that involve tool workflows. It uses a template‑guided multi‑agent pipeline to generate user instructions, simulated toolkits, and case‑specific safety criteria, followed by human review, allowing scalable expansion without building separate application environments. The benchmark includes 570 cases from 65 scenarios across seven task domains and nine planning‑risk types, and an LLM‑based evaluator assesses tool choices, arguments, and responses throughout execution. Evaluations of 13 LLM agents show persistent safety failures in both benign and adversarial settings, with prompt‑based interventions providing only model‑dependent improvements.