AI Agent Monitoring

Follow this topic Ask about this topic

AI agent monitoring studies how to observe and assess agents while they use tools, pursue long-running tasks, and interact with other agents, so problems can be detected before they cause harm or waste. Common approaches include trajectory classifiers and LLM judges, early-warning models over trace prefixes, formal runtime checks and action gates, and telemetry or provenance systems that record what happened and why. Some work also uses internal activations, human-facing dashboards, and recovery or intervention mechanisms to complement external observation. A central challenge is making monitors timely and reliable across long contexts and adaptive attacks without excessive false alarms, cost, or loss of useful autonomy.

Latest papers

285 papers51 papers in the last four weeks, up 55% on the four weeks before. 0.3% of all new papers.

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
Runtime Monitoring of Perception-Based Autonomous Systems via Embedding Temporal Logic
May 12, 2026Parv Kapoor, Abigail Hammer, Ashish Kapoor +2Signal Temporal Logic AI Agent Monitoring
Software and Societal Systems Department Carnegie Mellon University · General Robotics · Aeronautics and Astronautics Department University of Washington
Classifier Context Rot: Monitor Performance Degrades with Context Length
May 12, 2026Sam Martin, Fabien RogerLong-Context Modeling Long-Context Language Model Evaluation
Anthropic Fellows Program · Anthropic
Attacks and Mitigations for Distributed Governance of Agentic AI under Byzantine Adversaries
May 12, 2026Matthew D. Laws, Alina Oprea, Cristina Nita-RotaruAI Agent Security AI Agent Monitoring
Northeastern University
Property-Level Reconstructability of Agent Decisions: An Anchor-Level Pilot Across Vendor SDK Adapter Regimes
May 12, 2026Oleg SolozobovAI Agent Auditing Agent Evaluation
Independent Researcher (Global)
Mobius Injection: From One-Shot Prompt Injection to Sustained Resource Exhaustion in AI Agent Infrastructure
May 12, 2026Zi Liang, Ronghua Li, Yanyun Wang +2AI Agent Security LLM Agent Security
The Hong Kong Polytechnic University, Hong Kong SAR, China · HKUST (GZ), Guangzhou, China
Content-Aware Attack Detection in LLM Agent Tool-Call Traffic: An Empirical Study of Features, Architectures, and Evaluation Protocols
May 11, 2026Sultan ZavrakData Leakage Graph Neural Networks
Department of Computer Engineering, Duzce University, Duzce, Turkey
Machine Psychometrics: A Mathematical Psychology of Artificial Intelligence
May 10, 2026Alex Bogdan, Adrian de Valois-FranklinAI Agent Evaluation AI Agent Monitoring
Evolutionairy AI · Toronto, Canada
AgentShield: Deception-based Compromise Detection for Tool-using LLM Agents
May 10, 2026Yassin H. Rassul, Tarik A. RashidLLM Agent Security AI Agent Monitoring
Computer Science and Engineering Department, School of Science and Engineering, University of Kurdistan Hewlêr, Erbil, Iraq · Artificial Intelligence and Innovation Centre, University of Kurdistan Hewlêr, Erbil, Iraq
MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring
May 10, 2026Monika Jotautaitė, Maria Angelica Martinez, Ollie Matthews +1Software Engineering Agents AI Agent Security Benchmarks
Independent · Redwood Research
Skill Drift Is Contract Violation: Proactive Maintenance for LLM Agent Skill Libraries
May 9, 2026Linfeng Fan, Yuan Tian, Ziwei Li +1AI Agent Monitoring
Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China · King Abdullah University of Science and Technology, Thuwal, Saudi Arabia
AgentForesight: Online Auditing for Early Failure Prediction in Multi-Agent Systems
May 9, 2026Boxuan Zhang, Jianing Zhu, Zeru Shi +2Multi-Agent LLM Systems AI Agent Monitoring
Rutgers University · The University of Texas at Austin · Purdue University
Beyond the Black Box: Interpretability of Agentic AI Tool Use
May 7, 2026Hariom Tatsat, Ariye ShaterAI Agent Reliability Mechanistic Interpretability
Quantitative Analytics, Barclays
PrefixGuard: Online Failure Warning and Trace-Grounded Diagnosis for LLM Agents
May 7, 2026Xinmiao Huang, Jinwei Hu, Qisong He +4Fault Detection AI Agent Monitoring
University of Liverpool · Université Grenoble Alpes
Monitoring autonomous persistent surveillance missions using invariance
May 7, 2026Vladislav Nenchev, Prodromos SotiriadisAI Agent Monitoring Runtime Verification
Department of Electrical and Computer Engineering, University of the Bundeswehr Munich, 85579 Neubiberg, Germany.
AgentTrust: Runtime Safety Evaluation and Interception for AI Agent Tool Use
May 6, 2026Chenglin YangAI Agent Security AI Agent Security Benchmarks
Independent Researcher
Hidden Coalitions in Multi-Agent AI: A Spectral Diagnostic from Internal Representations
May 4, 2026Cameron Berg, Susan L. Schneider, Mark M. BaileyAI Agent Monitoring Spectral Clustering
Reciprocal Research · New York, NY, USA · Center for the Future of AI, Mind, and Society +5
Evaluating Agentic AI in the Wild: Failure Modes, Drift Patterns, and a Production Evaluation Framework
May 2, 2026Mukund PandeyAI Agent Reliability AI Agent Evaluation
Independent Researcher
A Low-Latency Fraud Detection Layer for Detecting Adversarial Interaction Patterns in LLM-Powered Agents
May 1, 2026Sheldon Yu, Yingcheng Sun, Hanqing Guo +1AI Agent Security LLM Agent Security
University of California, San Diego · UNC at Greensboro · Indiana University Bloomington
Modeling Clinical Concern Trajectories in Language Model Agents
Apr 30, 2026Sukesh Subaharan, Venkatesan VS, Murugadasan P +3LLM Interpretability AI Agent Monitoring
Coimbatore Medical College · Coimbatore, TN · India
Trace-Level Analysis of Information Contamination in Multi-Agent Systems
Apr 30, 2026Anna Mazhar, Huzaifa Suri, Sainyam GalhotraAgentic Workflows AI Agent Monitoring
Cornell University Ithaca, NY, USA · University of Illinois Urbana-Champaign, IL, USA
End-to-End Evaluation and Governance of an EHR-Embedded AI Agent for Clinicians
Apr 30, 2026Aaryan Shah, Andrew Hines, Alexia Downs +6Healthcare AI Agent Evaluation
1Canvas Medical, San Francisco, CA, USA · Department of Biomedical Data Science, Stanford University, Stanford, CA, USA · 3XPC (X Primary Care) +2
Step-level Optimization for Efficient Computer-use Agents
Apr 29, 2026Jinbiao Wei, Kangqi Ni, Yilun Zhao +2Computer-Use Agents AI Agent Monitoring
Y Yale NLP Lab · CUniversity of North Carolina at Chapel Hill
Enforcing Benign Trajectories: A Behavioral Firewall for Structured-Workflow AI Agents
Apr 29, 2026Hung DangLLM Agent Security AI Agent Monitoring
Van Lang University, Ho Chi Minh City, Vietnam
Operating-Layer Controls for Onchain Language-Model Agents Under Real Capital
Apr 28, 2026T. J. Barton, Chris Constantakis, Patti Hauseman +4AI Agent Reliability LLM Agent Evaluation
DX Research Group (DXRG)
OxyGent: Making Multi-Agent Systems Modular, Observable, and Evolvable via Oxy Abstraction
Apr 28, 2026Junxing Hu, Tianlong Li, Lei Yu +1Multi-Agent Orchestration AI Agent Monitoring
JD.com Beijing, China
Governing What You Cannot Observe: Adaptive Runtime Governance for Autonomous AI Agents
Apr 27, 2026German Marin, Jatin ChaudharyAI Agent Safety AI Agent Monitoring
Department of Computing, University of Turku, Turku, Finland
GAMMAF: A Common Framework for Graph-Based Anomaly Monitoring Benchmarking in LLM Multi-Agent Systems
Apr 27, 2026Pablo Mateo-Torrejón, Alfonso Sánchez-MaciánMulti-Agent LLM Systems Graph-Based Anomaly Detection
University Carlos III of Madrid · Leganés, Spain
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
Auditing and Controlling AI Agent Actions in Spreadsheets
Apr 22, 2026Sadra Sabouri, Zeinabsadat Saghi, Run Huang +4Human-in-the-Loop AI AI Agent Monitoring
University of Southern California Los Angeles, USA · California State Polytechnic University Pomona, USA · Microsoft Redmond, USA

May 13, 2026J/K move · Enter open · S save

How to Interpret Agent Behavior

Jie Gao, Kaiser Sun, Jen-tse Huang, Katherine Van Koevering+7

1Johns Hopkins University · 2California Institute of Technology · 3Northeastern University+1

Hierarchical Classification AI Agent Monitoring LLM Agents Agent Trajectory Analysis

Open paper AskPDF arXiv

Autonomous agents such as Claude Code and Codex now operate for hours or even days. Understanding their runtime behavior has become critical for downstream tasks such as diagnosing inefficiencies, fixing bugs, and ensuring better oversight. A primary way to gain this understanding is analyzing the reasoning trajectories and execution traces these agents generate. Yet such data remains in unstructured natural-language form, making it difficult for humans to interpret at scale. We introduce ACTONOMY (a combination of Action and Taxonomy), a taxonomy for describing and analyzing agent behavior at runtime. ACTONOMY has two components: (1) the taxonomy itself, developed through Grounded Theory and structured as a three-level hierarchy of 10 actions, 46 subactions, and 120 leaf categories; and (2) an open repository that hosts the living taxonomy, provides an automated analysis pipeline that applies it to agent trajectories analysis, and defines an extension protocol for customization and growth. Our experiments show that ACTONOMY can compare behavioral profiles across agents and characterize a single agent's behavior across diverse trajectories, surfacing patterns indicative of failure modes. By providing a shared vocabulary, ACT*ONOMY helps researchers, agent designers, and end users interpret agent behavior more consistently, enabling better oversight and control.