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:2608.22444v1 Announce Type: new
Abstract: The unit of AI safety evaluation is still the individual model, yet language-model agents are increasingly deployed in interacting populations that rea...
By Isotta Magistrali, Chen Shani
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
arXiv:2606. 28710v1 Announce Type: new Abstract: We ask under what conditions an agent with a harm-minimizing policy can displace an approval-seeking (RLHF) agent in a competitive market, and when that policy is sufficient to prevent community harm.
By Darrell Lewis-Sandy
The paper introduces a provenance‑aware execution graph for long‑horizon LLM agents, defining influence distance (DI) as the shortest structural path from an untrusted source to a sensitive action. Compared to the traditional sequence distance (DT), DI is always less than or equal to DT, revealing a median gap of nine hops in 454 injection–sink pairs across multiple models and datasets. The study shows that most pairs exhibit a non‑zero gap, and a deterministic DI‑based gate can block attacks missed by a sequence‑only gate without extra benign blocking.
By Md Jafrin Hossain, Nur Al Hasan Haldar
arXiv:2606. 14923v1 Announce Type: new Abstract: As language-model agents increasingly work in teams, each agent must decide how much to trust its teammates.
By Yujiao Chen
arXiv:2608. 11274v1 Announce Type: cross Abstract: The dominant paradigm treats AI safety as a property to be instilled during model training via RLHF, DPO, or Constitutional AI.
By Albus W. Ng, Yi Han, Jusheng Zhang, Wenhao Wang
arXiv:2607. 10814v1 Announce Type: cross Abstract: Evaluating LLM agents in hidden-information multi-agent settings is hard: final outcomes are high-variance and rarely reveal why an agent decided as it did.
By Yuan Gao, Jiangyi Yang, Yao Zhao, Yichi Zhang
arXiv:2606. 19356v1 Announce Type: cross Abstract: When multi-agent LLM systems produce bad answers, not all failures are equal: some answers are grounded in the right material but incomplete, while others are simply ungrounded and should be stopped.
By Anantha Sharma
arXiv:2607. 07695v1 Announce Type: new Abstract: We introduce institutional red-teaming, an evaluation methodology for testing deployment rules in multi-agent AI: hold the agents, objectives, and task state fixed, vary only one rule, and attribute the resulting change in collective behavior to that rule.
By Yujiao Chen
The study investigates how limited reading capacity and claim wording influence consensus outcomes in language‑model networks. By modeling message capacity as the number of messages an agent reads, the authors show that when agents read fewer than about 6.4 messages on average, a wrong consensus becomes unreachable. However, the wording of a claim—its inherent threshold—can override this effect, leading to incorrect consensus even when most agents start correct.
By Makoto Fukushima
arXiv:2607. 07368v1 Announce Type: cross Abstract: AI control is a family of techniques to prevent an AI with malicious goals from subverting its operator's intent.
By Oliver Makins, Orazio Angelini, Zohreh Shams, Mary Phuong