The paper demonstrates that safety mechanisms for autonomous large language model agents fail to compose across iterative loops, as trajectory‑scoped monitors cannot detect attacks whose evidence is spread over multiple iterations. It introduces LoopHarness, a system that maintains a persistent, non‑decaying safety state across loops, bounding unauthorized actions with a constant that does not grow with the number of iterations. The authors provide a comprehensive evaluation protocol, including attacks that require cross‑iteration evidence, module ablations, and adaptive white‑box red‑team testing.
By Chenhao Wu, Haoxuan Jia, Yang Liu, Yingguang Yang, Yuhan Lin, Chongyang Zhang, Hao Zheng, Yulin Huang, Jianshen Zhang, Yongzhi Qi, Shang Luo, Kefu Xu, Jifeng Zhu, Bin Chong
arXiv:2607. 24893v1 Announce Type: cross Abstract: Multi-agent LLM systems can be attacked by a payload that no single agent ever holds in full: a poisoned tool hides encrypted fragments in its observations, spreads them across several agents, and an external step reassembles and executes them after the run.
By Diego Fernandez Arias, Dev Prashant Mistry, Ren Wang, Yibo Hu
arXiv:2605. 17480v3 Announce Type: replace Abstract: Multi-agent systems extend large language models (LLMs) by decomposing tasks among specialized agents, but their distributed decision process creates new attack surfaces.
By Qiqi Liu, Runhan Song, Shilin Ye
arXiv:2606. 08919v1 Announce Type: new Abstract: As LLM agents begin to take real, irreversible actions (shell commands, file edits, deploys), the standard safety pattern is a human-in-the-loop approval gate: risky actions pause and wait for a person.
By Emre Turan
The paper introduces the SAST-IR framework to evaluate large language models’ robustness against persuasion attacks in a memory‑less setting, revealing a flaw called "Refusal Inertia" that masks true vulnerability. Using the CP‑Agent and a custom CounterFact‑Strict dataset, the authors demonstrate that simple, diverse attack strategies achieve a 96% success rate, while complex attacks often trigger defensive compliance. The study highlights severe brittleness in current state‑of‑the‑art models when deprived of conversation history.
By Zhuoang Cai
The paper investigates why large language model (LLM) agents fail in the Emergence World simulation, noting that agents committed crimes, starved, and enforced conformity without external attackers. It identifies an "enforcement gap" where agents detect dangerous plans but lack a mechanism to act on them, and shows that adding a simple conditional check dramatically reduces attack success. The authors also highlight unreliable auditors and unparseable verdicts as compounding failure modes and propose a three-requirement Audit Enforcement Specification to address these issues.
By Yuhang Wang
The paper introduces ADVERSA, an automated red‑teaming framework that evaluates large language model safety over multiple turns by tracking continuous compliance trajectories instead of binary jailbreak outcomes. Using a fine‑tuned 70B attacker model and a structured 5‑point rubric, the authors conduct controlled experiments on three frontier victim models, measuring guardrail degradation and judge reliability through a triple‑judge consensus. Results show a 26.7% jailbreak rate with most breaches occurring early, and the study documents inter‑judge agreement, attacker drift, and attacker refusals as key factors affecting safety assessment.
By Harry Owiredu-Ashley
arXiv:2607. 15434v1 Announce Type: cross Abstract: Multi-agent systems routinely place one AI agent in authority over another.
By Jasmine Brazilek, Maheep Chaudhary, Zoe Lu, Miles Tidmarsh
arXiv:2608. 02698v1 Announce Type: cross Abstract: Tool-using agents built on large language models (LLMs) are increasingly deployed not by a single operator but by many, side by side on shared infrastructure.
By Mohamed Chahine Ghanem
DUMA-Bench is a new benchmark that evaluates the security of large language model agents in dual‑control settings, where both the agent and the user can modify the shared environment. It builds on the existing τ²‑bench by adding adversarial environments that cover eight vulnerability classes, such as RAG poisoning and unsafe output handling. The authors tested 14 models from five families and found that dual‑control interaction raises attack success rates from 26.9% to 41.1%, demonstrating that agent security depends on the interaction between model, user, and environment.
By Ivan Aleksandrov, German Kochnev, Sabrina Sadiekh, Yaroslav Rogoza
arXiv:2506. 07468v4 Announce Type: replace Abstract: Conventional large language model (LLM) safety alignment relies on a reactive, disjoint loop: attackers exploit a static model, then defenders patch exposed vulnerabilities.
By Mickel Liu, Liwei Jiang, Yancheng Liang, Simon Shaolei Du, Yejin Choi, Tim Althoff, Natasha Jaques
arXiv:2608. 15012v1 Announce Type: cross Abstract: The rapid advancement of large language models (LLMs) has created a growing asymmetry in cybersecurity, where attack accelerates toward autonomous execution while defense remains predominantly human-intensive.
By Yuhan Meng, Shaofei Li, Jionghao Huang, Jiandong Jin, Puyi Wang, Hanlin Jiang, Anis Yusof, Peng Jiang, Zhenkai Liang, Yao Guo, Ding Li