LLM Agents

LLM: Large Language Model

LLM agents combine language models with tools, memory, and execution environments to pursue goals through sequences of decisions rather than producing a single response. Common approaches include ReAct-style planning and tool use, retrieval and reusable skill libraries, reflection and verification, multi-agent coordination, and training with supervised trajectories or reinforcement learning; runtime harnesses also manage state, permissions, and model routing. They are tested on interactive web and coding tasks, tool-use and long-horizon benchmarks, domain workflows, and simulations of social or physical settings. A central challenge is making agents reliable and safe when tasks, instructions, and environments change while controlling cost and evaluating performance beyond narrow benchmark success.

Latest papers

711 papers129 papers in the last four weeks, up 59% on the four weeks before. 0.7% of all new papers.

An Empirical Study of Privacy Leakage Chains via Prompt Injection in Black-Box Chatbot Environments
May 18, 2026Hongjang Yang, Hyunsik Na, Daeseon ChoiData Leakage Privacy Leakage in Language Models
Department of Information Security Soongsil University Seoul, Korea · AI Safety Center Soongsil University Seoul, Korea · Department of AI Software Soongsil University Seoul, Korea
PPAI: Enabling Personalized LLM Agent Interoperability for Collaborative Edge Intelligence
May 18, 2026Zile Wang, Qianli Liu, Kaibin Guo +4Multi-Agent Collaboration LLM Agents
Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong · School of Software Engineering, Sun Yat-Sen University, China
ASPI: Seeking Ambiguity Clarification Amplifies Prompt Injection Vulnerability in LLM Agents
May 17, 2026Udari Madhushani Sehwag, Zhengyang Shan, Heming Liu +3LLM Agent Security AI Agent Security Benchmarks
Scale AI · 2Boston University · 4Human Frontier Collective +3
MetaCogAgent: A Metacognitive Multi-Agent LLM Framework with Self-Aware Task Delegation
May 17, 2026Chenyu Wang, Yang ShuLLM Agent Orchestration LLM Agent Evaluation
School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, China · Zhejiang University, Hangzhou, China
OpenJarvis: Personal AI, On Personal Devices
May 16, 2026Jon Saad-Falcon, Avanika Narayan, Robby Manihani +10On-Device Language Model Inference LLM Agents
Stanford University · Lambda Labs
Representation Signatures and Risk-Feedback Alignment in LLM Trading Agents
May 16, 2026Weicheng XueLLM Alignment LLM Auditing
Virginia Tech
Skills on the Fly: Test-Time Adaptive Skill Synthesis for LLM Agents
May 16, 2026Jingxing Wang, Chenyu Zhou, Zhihui Fu +4Test-Time Adaptation LLM Agent Skill Learning
1Shanghai Jiao Tong University · 2OPPO Research Institute
The Alpha Illusion: Reported Alpha from LLM Trading Agents Should Not Be Treated as Deployment Evidence
May 16, 2026Yuxuan Ye, Jun Han, Ao Hu +7LLM Agent Evaluation AI Agent Benchmarks
Fudan University · Shanghai University of Finance and Economics · Southwest University of Finance and Economics +3
Counterparty Modeling is Not Strategy: The Limits of LLM Negotiators
May 15, 2026Romain Cosentino, Sarath Shekkizhar, Adam Earle +1Multi-Agent Negotiation Automated Negotiation
Salesforce AI Research
Context, Reasoning, and Hierarchy: A Cost-Performance Study of Compound LLM Agent Design in an Adversarial POMDP
May 15, 2026Igor Bogdanov, Chung-Horng Lung, Thomas Kunz +3Multi-Agent LLM Systems LLM Agent Orchestration
Carleton University Ottawa, Ontario, Canada · Defence R&D Canada Ottawa, Ontario, Canada · Cistel Technology Ottawa, Ontario, Canada
paper.json: A Coordination Convention for LLM-Agent-Actionable Papers
May 15, 2026Arquimedes CanedoDocument Information Extraction LLM Agents
Look Before You Leap: Autonomous Exploration for LLM Agents
May 15, 2026Ziang Ye, Wentao Shi, Yuxin Liu +6RL Exploration LLM Agents
University of Science and Technology of China · Meituan
AInterviewer: A Platform for Designing and Conducting AI-led Qualitative Interviews
May 15, 2026Tobias Priesholm Gardhus, Nikolas Vitsakis, Fie Lejre Frederiksen +2LLM Agents
University of Copenhagen · IT University of Copenhagen
Latency-Quality Routing for Functionally Equivalent Tools in LLM Agents
May 14, 2026Kexin Chu, Dawei Xiang, Wei ZhangTool-Augmented Language Model Agents LLM Tool Use
University of Connecticut
How to Interpret Agent Behavior
May 13, 2026Jie Gao, Kaiser Sun, Jen-tse Huang +8Hierarchical Classification AI Agent Monitoring
1Johns Hopkins University · 2California Institute of Technology · 3Northeastern University +1
PersonalAI 2.0: Enhancing knowledge graph traversal/retrieval with planning mechanism for Personalized LLM Agents
May 13, 2026Mikhail Menschikov, Matvey Iskornev, Alexander Kharitonov +8Multi-Hop QA Graph Retrieval-Augmented Generation
Skoltech, Moscow, Russia · SberAI, Moscow, Russia · Huawei, Moscow, Russia +4
Speculative Interaction Agents: Building Real-Time Agents with Asynchronous I/O and Speculative Tool Calling
May 13, 2026Coleman Hooper, Minwoo Kang, Suhong Moon +7Tool-Using Agents LLM Agents
University of California, Berkeley · ICSI · LBNL
IfcLLM: Natural Language Querying of IFC Models through Complementary Relational and Graph Representations
May 13, 2026Rabindra Lamsal, Sisi Zlatanova, Haowen Xu +2Building Information Modeling LLM Agents
GRID Lab, School of Built Environment, The University of New South Wales, Sydney, Australia · School of Civil and Environmental Engineering, The University of New South Wales, Sydney, Australia
SHM-Agents: A Generalist-Specialist Integrated Agent System for Structural Health Monitoring
May 13, 2026Yuequan Bao, Xing Li, Huabin Sun +3LLM Agent Orchestration LLM Agents
Key Lab of Smart Prevention and Mitigation of Civil Engineering Disasters of the Ministry of Industry and Information Technology, Harbin Institute of Technology, Harbin · Key Lab of Structures Dynamic Behavior and Control of the Ministry of Education, Harbin Institute of Technology, Harbin · School of Civil Engineering, Harbin Institute of Technology, Harbin
Multi-Stream LLMs: Unblocking Language Models with Parallel Streams of Thoughts, Inputs and Outputs
May 12, 2026Guinan Su, Yanwu Yang, Xueyan Li +1LLM Agents Instruction Tuning
Max Planck Institute for Intelligent Systems · University Hospital Tübingen · University of Tübingen +3
Predicting Decisions of AI Agents from Limited Interaction through Text-Tabular Modeling
May 12, 2026Eilam Shapira, Moshe Tennenholtz, Roi ReichartNext-Action Prediction LLM Agents
Faculty of Data and Decision Sciences Technion – Israel Institute of Technology Haifa, Israel
SkillSmith: Compiling Agent Skills into Boundary-Guided Runtime Interfaces
May 12, 2026Duling Xu, Zheng Chen, Zaifeng Pan +4LLM Agent Workflow Optimization LLM Agent Skill Retrieval
AetherHeart Tech Co., Ltd., Shanghai, China · Renmin University of China, Beijing, China · University of California San Diego, CA, USA
Deep Reasoning in General Purpose Agents via Structured Meta-Cognition
May 12, 2026Dean Light, Michael Theologitis, Kshitish Ghate +7Structured Reasoning Agentic Reasoning
University of Washington Seattle, WA, USA
NanoResearch: Co-Evolving Skills, Memory, and Policy for Personalized Research Automation
May 11, 2026Jinhang Xu, Qiyuan Zhu, Yujun Wu +11Multi-Agent LLM Systems LLM Agent Skill Learning
1Shanghai Artificial Intelligence Laboratory · 2The Hong Kong University of Science and Technology · 3Peking University +4
An agentic framework for gravitational-wave counterpart association in the multi-messenger era
May 11, 2026Yiming Dong, Yacheng Kang, Junjie Zhao +3AI Agents for Scientific Discovery Gravitational-Wave Astronomy
Department of Astronomy, School of Physics, Peking University, No. 5 Yiheyuan Road, Beijing, 100871, Beijing, China. · Kavli Institute for Astronomy and Astrophysics, Peking University, No. 5 Yiheyuan Road, Beijing, 100871, Beijing, China. · Institute for Gravitational Wave Astronomy, Henan Academy of Sciences, No. 228 Chongshili Road, Zhengzhou, 450046, Henan, China. +2
Argumentation-Based Person-Tailored Storytelling for Older Adults: A Reflective Hybrid AI Architecture
May 11, 2026Jayalakshmi Baskar, Vera C. Kaelin, Kaan Kilic +1Argument Mining LLM Agent Evaluation
Umeå University, Department of Computing Science, Sweden
Agent-X: Full Pipeline Acceleration of On-device AI Agents
May 11, 2026Jinha Chung, Byeongjun Shin, Jiin Kim +1LLM Inference Efficiency On-Device Language Model Inference
KAIST Republic of Korea, Daejeon
SkillRAE: Agent Skill-Based Context Compilation for Retrieval-Augmented Execution
May 11, 2026Xiangcheng Meng, Shu Wang, Yixiang FangAgentic Retrieval LLM Agent Skill Retrieval
The Chinese University of Hong Kong, Shenzhen
Strategic Exploitation in LLM Agent Markets: A Simulation Framework for E-Commerce Trust
May 11, 2026Shijun Lei, Quang Nguyen, Swapneel S Mehta +7Human Behavior Simulation Agent-Based Modeling
Northwestern Polytechnical University · Boston University · Fudan University +3
Sequential Behavioral Watermarking for LLM Agents
May 11, 2026Hyeseon An, Shinwoo Park, Dongsu Kim +1LLM Watermarking LLM Agents
Department of Computer Science, Yonsei University, Seoul, South Korea

May 18, 2026J/K move · Enter open · S save

An Empirical Study of Privacy Leakage Chains via Prompt Injection in Black-Box Chatbot Environments

Hongjang Yang, Hyunsik Na, Daeseon Choi

Department of Information Security Soongsil University Seoul, Korea · AI Safety Center Soongsil University Seoul, Korea · Department of AI Software Soongsil University Seoul, Korea

Data Leakage Privacy Leakage in Language Models Indirect Prompt Injection Prompt Injection Attacks LLM Agents Black-Box Adversarial Attacks

Open paper AskPDF arXiv

LLM-based chatbot agents increasingly process user requests by combining natural-language reasoning with external tools such as web browsing. These capabilities improve usability, but they also create attack surfaces when untrusted external content is processed as part of a user' s task. This paper studies a privacy-leakage attack chain based on indirect prompt injection in black-box chatbot environments, where the attacker has no access to model weights, system prompts, or agent implementation details including how a trajectory is actually managed during its processing for a query. We first analyze how an attacker can hijack an agent' s intended task by crafting external content that appears benign to the victim while inducing the agent to execute an attacker-defined objective. We then evaluate a new prompt-injection technique, called exemplification, which uses a bridge in the external content to reframe the user prompt and the benign beginning of the retrieved page as few-shot examples before appending the attacker' s objective. We compare its attack success rate with a prior fake-completion technique. Finally, we demonstrate a proof-of-concept data-exfiltration chain using fictitious personal information in a controlled setting. Our results suggest that prompt injection, jailbreak-style instruction steering, and web-tool invocation can be combined into a feasible privacy-leakage path in deployed chatbot agents.