AI Agent Monitoring

Follow this topic Ask about this topic

Momentum

20 papers in the last four weeks, up 186% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 170

All topics

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 AI Agent Security Benchmarks
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
Causal-Temporal Event Graphs: A Formal Model for Recursive Agent Execution Traces
Apr 19, 2026Simon FoldvikAI Agent Monitoring
Independent researcher
From Admission to Invariants: Measuring Deviation in Delegated Agent Systems
Apr 19, 2026Marcelo FernandezAI Agent Monitoring AI Agent Governance
TraslaIA
Agentic Explainability at Scale: Between Corporate Fears and XAI Needs
Apr 16, 2026Yomna Elsayed, Cecily JonesExplainable Artificial Intelligence AI Agent Monitoring
Credo AI
LinuxArena: A Control Setting for AI Agents in Live Production Software Environments
Apr 16, 2026Tyler Tracy, Ram Potham, Nick Kuhn +31Software Engineering Agents AI Agent Security
Redwood Research · EquiStamp
The Alignment Flywheel: A Governance-Centric Hybrid MAS for Architecture-Agnostic Safety
Feb 28, 2026Elias Malomgré, Pieter SimoensAI Agent Safety AI Agent Monitoring
IDLab, Ghent University - imec, Belgium
StepShield: When, Not Whether to Intervene on Rogue Agents
Jan 29, 2026Gloria Felicia, Zitha Sasindran, Jinfeng He +3LLM Guardrails AI Agent Security
University of Virginia · Indian Institute of Science Bangalore · Indian Institute of Science, Bangalore +5
Measuring Harmfulness of Computer-Using Agents
Jul 31, 2025Aaron Xuxiang Tian, Ruofan Zhang, Janet Tang +3Computer-Use Agent Benchmarks Computer-Use Agents
Independent Researcher · Arizona State University · Gradient +1
Towards Mitigation of Hallucination for LLM-empowered Agents: Progressive Generalization Bound Exploration and Watchdog Monitor
Jul 21, 2025Siyuan Liu, Wenjing Liu, Zhiwei Xu +3LLM Hallucination Mitigation Hallucination in Language Models
College of Computer Science, Nankai University · College of intelligent Science and Technology, Inner Mongolia University of Technology · Institute of Computing Technology, Chinese Academy of Sciences +3
Verification of Adaptive Agentic Controllers through Finite Rule Revision
Date pendingRoberto GarroneAgent Failure Analysis Formal Verification
Open University of Cyprus
A False Average: Pooled CoT-Monitor Accuracy Conceals a Reasoning-Dependent Fragility
Date pendingShikhar Shiromani, Leo RichterReward Hacking Adversarial Attacks on LLMs
Pivotal Research · University College London
ETHOS: Towards a Modular Ethics Framework for Clinical Multi-Agent Systems
Date pendingRakesh Sharma, Sydney Pugh, Cameron Beeche +14AI Agent Safety AI Agent Monitoring
Department of Radiology, University of Pennsylvania, Philadelphia, PA 19104, USA · Department of Biostatistics, Epidemiology, and Informatics, University of Pennsylvania, Philadelphia, PA 19104, USA · Department of Medicine, Division of Translational Medicine and Human Genetics, University of Pennsylvania, Philadelphia, PA 19104, USA +6
Your Agent Says Yes: Interpreting Adversarial Market Behavior Beyond Individual Transactions
Date pendingZelin Li, Yiyun Su, Matt White +3LLM Agent Evaluation AI Agent Security
The Ohio State University · Rutgers University · University of California, Berkeley +3

Apr 29, 2026, cs.AIJ/K move · Enter open · S save

Step-level Optimization for Efficient Computer-use Agents

Jinbiao Wei, Kangqi Ni, Yilun Zhao, Guo Gan+1

Y Yale NLP Lab · CUniversity of North Carolina at Chapel Hill

Computer-Use Agents AI Agent Monitoring Long-Horizon Agent Tasks

Open paper AskPDF arXiv

Computer-use agents provide a promising path toward general software automation because they can interact directly with arbitrary graphical user interfaces instead of relying on brittle, application-specific integrations. Despite recent advances in benchmark performance, strong computer-use agents remain expensive and slow in practice, since most systems invoke large multimodal models at nearly every interaction step. We argue that this uniform allocation of compute is fundamentally inefficient for long-horizon GUI tasks. Such trajectories are highly heterogeneous: many steps are routine and can be handled reliably by smaller, cheaper policies, while errors tend to concentrate at a relatively small number of high-risk moments. Across computer-use benchmarks, these failures repeatedly take two forms: progress stalls, where the agent loops, repeats ineffective actions, or fails to make meaningful progress, and silent semantic drift, where the agent continues taking locally plausible actions after already deviating from the user's true goal. To address this inefficiency, we propose an event-driven, step-level cascade for computer-use agents that runs a small policy by default and escalates to a stronger model only when lightweight learned monitors detect elevated risk. Our framework combines two complementary signals: a Stuck Monitor that detects degraded progress from recent reasoning-action history and triggers recovery, and a Milestone Monitor that identifies semantically meaningful checkpoints where sparse verification is most informative for catching drift. This design turns always-on frontier-model inference into adaptive, on-demand compute allocation over the course of an evolving interaction. The framework is modular and deployment-oriented: it can be layered on top of existing computer-use agents without changing the underlying agent architecture or retraining the large model.

Momentum

Related topics

Latest papers 170