LLM Agent Safety

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

24 papers in the last four weeks, up 50% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 193

All topics

Web Agents Should Adopt the Plan-Then-Execute Paradigm
May 14, 2026Julien Piet, Annabella Chow, Yiwei Hou +5LLM Agent Safety LLM Agent Planning
UC Berkeley
Auditing Agent Harness Safety
May 14, 2026Chengzhi Liu, Yichen Guo, Yepeng Liu +8AI Agent Auditing LLM Auditing
University of California, Santa Barbara · University of California, Berkeley · Microsoft Research +2
History Anchors: How Prior Behavior Steers LLM Decisions Toward Unsafe Actions
May 13, 2026Alberto G. Rodríguez SalgadoLLM Safety Evaluation AI Agent Safety Benchmarks
Independent Researcher
No Attack Required: Semantic Fuzzing for Specification Violations in Agent Skills
May 13, 2026Ying Li, Hongbo Wen, Yanju Chen +3LLM Guardrails LLM Agent Verification
University of California, Los Angeles · University of California, Santa Barbara · University of California, San Diego
Large Language Models for Agentic NetOps and AIOps: Architectures, Evaluation, and Safety
May 12, 2026Muhammad Bilal, Jon Crowcroft, Ruizhi Wang +2LLM Agent Evaluation AI Agent Security
School of Computing and Communications Lancaster University, United Kingdom · Department of Computer Science and Technology, University of Cambridge, United Kingdom · School of Software, Nanjing University of Information Science and Technology, China +1
No Action Without a NOD: A Heterogeneous Multi-Agent Architecture for Reliable Service Agents
May 12, 2026Zixu Yang, Hang Zheng, Nan Jiang +5AI Agent Reliability Multi-Agent LLM Systems
1X-LANCE Lab, School of Computer Science, Shanghai Jiao Tong University, Shanghai, China · 2Shanghai Innovation Institution, Shanghai, China · 3Jiangsu Key Lab of Language Computing, Suzhou, China
SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces
May 12, 2026Chang Jin, An Wang, Zeming Wei +7LLM Agent Security AI Agent Security Benchmarks
1Shanghai AI Laboratory · 2Peking University · 3East China Normal University
On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment
May 12, 2026Bo Yin, Qi Li, Xinchao WangAgentic RL LLM Safety Alignment
National University of Singapore
LITMUS: Benchmarking Behavioral Jailbreaks of LLM Agents in Real OS Environments
May 11, 2026Chiyu Zhang, Huiqin Yang, Bendong Jiang +8AI Agent Security Benchmarks LLM Jailbreak Attacks
Nanjing University of Aeronautics and Astronautics · Collaborative lnnovation Center of Novel Software Technology and Industrialization · Zhejiang University
Safe Multi-Agent Behavior Must Be Maintained, Not Merely Asserted: Constraint Drift in LLM-Based Multi-Agent Systems
May 11, 2026Tianxiao Li, Yixing Ma, Haiquan Wen +4Multi-Agent LLM Systems AI Agent Governance
University of Liverpool, UK · University of Nottingham, UK · University of Tokyo, Japan +1
NEXUS: Continual Learning of Symbolic Constraints for Safe and Robust Embodied Planning
May 10, 2026Tiehan Cui, Peipei Liu, Yanxu Mao +3Continual Learning for LLM Agents Large Language Model-Based Robot Planning
School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, China · School of Software, Henan University, China · Institute of Information Engineering, Chinese Academy of Sciences, China +2
AI-Care: A Conversational Agentic System for Task Coordination in Alzheimer's Disease Care
May 8, 2026Preyash Yadav, Michelle Cohn, Priyanka Koppolu +5Alzheimer's Disease Tool-Using Agents
Department of Computer Science University of California, Davis Davis, USA · Department of Linguistics University of California, Davis Davis, USA · Department of Neurology University of California, Davis Sacramento, USA +1
Safe, or Simply Incapable? Rethinking Safety Evaluation for Phone-Use Agents
May 8, 2026Zhengyang Tang, Yi Zhang, Chenxin Li +18Computer-Use Agents Agent Evaluation
1Tencent Hunyuan · 2The Chinese University of Hong Kong, Shenzhen · 3Tsinghua University
Why Does Agentic Safety Fail to Generalize Across Tasks?
May 7, 2026Yonatan Slutzky, Yotam Alexander, Tomer Slor +2AI Agent Safety LLM Agent Safety
Tel Aviv University
Designing Intelligent Enterprise Agents: A Capability-Aligned Multi-Agent Architecture
May 7, 2026John deVadossLLM Agents Multi-Agent Systems
InterWork Alliance Washington DC
Instrumental Choices: Measuring the Propensity of LLM Agents to Pursue Instrumental Behaviors
May 7, 2026Jonas Wiedermann-Möller, Leonard Dung, Maksym AndriushchenkoAI Agent Evaluation AI Agent Safety
Universität Bielefeld · Ruhr-Universität Bochum · ELLIS Institute Tübingen +2
TheraAgent: Self-Improving Therapeutic Agent for Precise and Comprehensive Treatment Planning
May 7, 2026Junkai Li, Yunghwei Lai, Tianyi Zhu +3LLM Self-Refinement Healthcare
1Dept. of Comp. Sci. & Tech., Institute for AI, Tsinghua University, Beijing, China · Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China · School of Computing, National University of Singapore, Singapore
SafeHarbor: Hierarchical Memory-Augmented Guardrail for LLM Agent Safety
May 7, 2026Zhe Liu, Zonghao Ying, Wenxin Zhang +5LLM Guardrails LLM Agent Security
School of Cyber Science and Technology, Beihang University, Beijing, China · Institute of Artificial Intelligence, Beihang University, Beijing, China · University of Chinese Academy of Sciences, Beijing, China +1
Enhancing Agent Safety Judgment: Controlled Benchmark Rewriting and Analogical Reasoning for Deceptive Out-of-Distribution Scenarios
May 5, 2026Zuoyu Zhang, Yancheng ZhuAI Agent Safety AI Agent Safety Benchmarks
Shenzhen University, Shenzhen, China.
Safeguarding LLM Agents from Misalignment through Provenance Analysis
May 1, 2026Yining She, Yiliang Liang, Eunsuk KangLLM Guardrails LLM Agent Safety
Carnegie Mellon University Pittsburgh, PA, USA
Benchmarking the Safety of Large Language Models for Robotic Health Attendant Control
Apr 29, 2026Mahiro Nakao, Kazuhiro TakemotoLanguage Model-Based Control Healthcare
Kyushu Institute of Technology Iizuka, Fukuoka, Japan
Think Before You Act -- A Neurocognitive Governance Model for Autonomous AI Agents
Apr 28, 2026Eranga Bandara, Ross Gore, Asanga Gunaratna +12Cognitive Architectures for AI Agents AI Agent Governance
Old Dominion University, Norfolk, VA, USA · AI Motion Labs, Melbourne, Australia · Florida International University, FL, USA +6
The Price of Agreement: Measuring LLM Sycophancy in Agentic Financial Applications
Apr 27, 2026Zhenyu Zhao, Aparna Balagopalan, Adi Agrawal +3Financial Services LLM Sycophancy
Writer, Inc.
The Interlocutor Effect: Why LLMs Leak More Personal Data to Agents Than Humans
Apr 26, 2026Faouzi El Yagoubi, Godwin Badu-Marfo, Ranwa Al MallahData Leakage Multi-Agent LLM Systems
Department of Computer and Software Engineering, Polytechnique Montréal, Montréal, Canada
Semantic Denial of Service in LLM-controlled robots
Apr 25, 2026Jonathan Steinberg, Oren GalLanguage Model Safety Evaluation Adversarial Attacks on LLMs
Swarms & AI Lab (SAIL) · University of Haifa
Discovering Agentic Safety Specifications from 1-Bit Danger Signals
Apr 25, 2026Víctor GallegoAgentic Reasoning LLM Safety Evaluation
Komorebi AI
LLM-Guided Safety Agent for Edge Robotics with an ISO-Compliant Perception-Compute-Control Architecture
Apr 22, 2026Xu Huang, Ruofan Zhang, Lu Cheng +9Robotics Robot Safety
Shanghai Jiao Tong University · SIMMIR Tech
Omission Constraints Decay While Commission Constraints Persist in Long-Context LLM Agents
Apr 22, 2026Yeran GamageAI Agent Monitoring LLM Security
University of South Florida · Independent AI Security Researcher
SafetyALFRED: Evaluating Safety-Conscious Planning of Multimodal Large Language Models
Apr 21, 2026Josue Torres-Fonseca, Naihao Deng, Yinpei Dai +5LLM Safety Benchmarks Large Language Model-Based Robot Planning
University of Michigan · Boise State University
Human-Guided Harm Recovery for Computer Use Agents
Apr 20, 2026Christy Li, Sky CH-Wang, Andi Peng +1Computer-Use Agents AI Agent Security Benchmarks
MIT CSAIL · Abridge · humans&

May 14, 2026, cs.CRJ/K move · Enter open · S save

Web Agents Should Adopt the Plan-Then-Execute Paradigm

Julien Piet, Annabella Chow, Yiwei Hou, Muxi Lyu+4

UC Berkeley

LLM Agent Safety LLM Agent Planning Web Agents

Open paper AskPDF arXiv

ReAct has become the default architecture across LLM agents, and many existing web agents follow this paradigm. We argue that it is the wrong default for web agents. Instead, web agents should default to plan-then-execute: commit to a task-specific program before observing runtime web content, then execute it. The reason is that web content mixes inputs from many parties. An e-commerce product page may combine a seller's listing, customer reviews and sponsored advertisements. Under ReAct, all of this content flows into the model when deciding on the next action, creating a direct path for prompt injections to steer the agent's control flow. Plan-then-execute changes this boundary: untrusted data may influence values or branches inside a predefined execution graph, but it cannot redefine the user task or cause the model to synthesize new actions at runtime. We analyze WebArena, a popular web agent benchmark, and find that all tasks are compatible with plan-then-execute, while 80% can be completed with a purely programmatic plan, without any runtime LLM subroutine. We identify the main barrier to adopting plan-then-execute on the web: For it to work well, tools must map cleanly to semantic actions, with effects known before execution, so agents have enough information to plan. The web does not naturally expose that interface. Browser tools such as click, type, and scroll have page-dependent meanings. Planning at this layer is near-sighted: the agent can only see actions on the current page, and later actions appear only after it acts. Closing this gap requires typed interfaces that turn website interactions from clicks and keystrokes to task-level operations. This is an infrastructure problem, not a modeling problem. Web tasks do not need reactivity by default; they need typed, complete, auditable website APIs.

Momentum

Related topics

Latest papers 193