The paper investigates whether tool‑calling large language model agents maintain consistent safety throughout a conversation. It finds that agents are most vulnerable at the very start of a session, with safety improving significantly after completing a few regular agentic tasks—a phenomenon termed the cold‑start safety gap. The authors introduce the Safety Over Depth for Agents (SODA) benchmark to systematically study this effect, evaluate multiple models, and demonstrate that warming up agents with regular tasks before deployment enhances safety while preserving utility.
By Chung-En Sun, Linbo Liu, Tsui-Wei Weng
arXiv:2606. 28739v1 Announce Type: new Abstract: Large language models increasingly act as agents: they call tools, move money, delete records, and send messages on a user's behalf.
By Shawn Li, Yue Zhao
arXiv:2606. 22686v2 Announce Type: replace-cross Abstract: Modern Large Language Models (LLMs) rely on extensive safety alignment, yet the mechanistic basis of refusal remains opaque.
By Shivam Ratnakar, Kartikeya Vats
arXiv:2607. 13596v1 Announce Type: cross Abstract: When cast as the protector of a vulnerable user yet given no explicit capability boundary, a large language model (LLM) may respond not by acknowledging its limits but by claiming to have taken -- or to be taking -- a real-world protective action it cannot perform, such as contacting emergency services or administering care.
By Eunna Lee, Jungpyo Nam, Sunjun Hwang
arXiv:2607. 07097v1 Announce Type: new Abstract: Safety evaluations of multi-agent LLM systems often compare a direct prompt with a planner-executor pipeline and report the difference as a single "pipeline effect.
By Lifei Liu, Haoran Yu, Xiaochong Jiang, Su Wang, Pin Qian, Yihang Chen
arXiv:2605.12015v3 Announce Type: replace-cross
Abstract: Reusable skills are becoming a common interface for extending large language model agents, packaging procedural guidance with access to files...
By Chang Jin, An Wang, Zeming Wei, Kai Wang, Biaojie Zeng, Qiaosheng Zhang, Chao Yang, Jingjing Qu, Xia Hu, Xingcheng Xu
arXiv:2603. 19423v2 Announce Type: replace-cross Abstract: Large language model (LLM) agents increasingly rely on external tools (file operations, API calls, database transactions) to autonomously complete complex multi-step tasks.
By Shawn Li, Yue Zhao
arXiv:2608. 02683v1 Announce Type: cross Abstract: Large Language Model (LLM) agents rely on multi-stage agentic workflows, with stages such as memory, planning, and tool execution, to accomplish complex tasks.
By Zibo Xiao, Haoyu Wang, Jun Sun
arXiv:2608. 10530v1 Announce Type: cross Abstract: Large Language Models (LLMs) have undergone a shift from stateless conversational interfaces to autonomous agents capable of multi-step planning, tool invocation, code execution, and maintaining persistent memory.
By Md Jafrin Hossain, Mohammad Arif Hossain, Nirwan Ansari
arXiv:2608. 09885v1 Announce Type: new Abstract: The safety of large language model (LLM) agents depends not only on model weights but also on the agent harness that manages context, memory, tools, permissions, and runtime control.
By Wanying Qu, Qinghua Mao, Yu Li, Jiyao Liu, Xin Zhang, Dadi Guo, Yanxu Zhu, Qingyu Liu, Leitao Yuan, Xi Lin, Shanfeng Zhu, Yanwei Fu, Jing Shao, Xia Hu, Dongrui Liu
Large language model agents coordinate tasks via multi‑role, multi‑stage workflows that transform upstream state into intermediate artifacts such as summaries and plans. The study shows that when these artifacts are transformed—through compression, plan assimilation, or other handoff methods—the strict action‑binding constraints on upstream state can be weakened, turning mandatory requirements into optional information. In 1,296 synthetic episodes, direct handoff preserved all safety blockers, whereas transformed handoffs frequently deactivated or forbidden actions, but restoring full state fields or applying downstream verification can recover preservation.
By Yiheng Sun, Huifei Wang, Yancheng Zhu, Zhenyu Li, Zebin Zhao, Yifan Yuan
arXiv:2608.29936v1 Announce Type: cross
Abstract: Safety alignment of large language models (LLMs) degrades across languages, yet the internal mechanism driving this asymmetry remains poorly understo...
By Apoorva Upadhyaya, Sandipan Sikdar