mlsanityData to 14 Oct 2026

Control Charts for Multi-agent Systems

arXiv 2605.11135 ↗First posted 11 May 2026cs.MA cs.AI cs.LGcited by 1

On the map: LLM agents and tool use → Agent threats, guardrails and governance

Abstract (arXiv)

Generative agents have proven to be powerful assistants in a wide variety of contexts. Given this success, users are now deploying agents with minimal restrictions in open ended, multi-agent environments. Current methods for monitoring the dynamics of open-ended multi-agent systems are limited to qualitative inspection. In this paper, we extend the process-theoretic notion of adaptive control charts to multi-agent systems to enable automated monitoring. Using simulation, we demonstrate that adaptive control charts are necessary for monitoring multi-agent systems that can learn from their environment. We further demonstrate, both empirically and theoretically, that adaptive control charts are susceptible to adversarial agents that defect sufficiently slowly. These results illustrate a fundamental tradeoff in multi-agent system control: either agents in a system cannot learn or the system is susceptible to adversaries.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use. Builds on 18 of its 29 references that are in the map. First posted on arXiv 11 May 2026.

Builds on

18 of 29 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training10 Jan

Other references · 17

  1. 2024GPT-4o System Cardcited by 4,588
  2. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  3. 2024The Platonic Representation Hypothesiscited by 382
  4. 2024Nomic Embed: Training a Reproducible Long Context Text Embeddercited by 265
  5. 2023Simulating Opinion Dynamics with Networks of LLM-based Agentscited by 154
  6. 2023Evaluating Language-Model Agents on Realistic Autonomous Taskscited by 96
  7. 2024Learning on LoRAs: GL-Equivariant Processing of Low-Rank Weight Spaces for Large Finetuned Modelscited by 22
  8. 2023Comparing Foundation Models using Data Kernelscited by 14
  9. 2024Tracking the perspectives of interacting language modelscited by 14
  10. 2024Consistent estimation of generative model representations in the data kernel perspective spacecited by 10
  11. 2024Statistical inference on black-box generative models in the data kernel perspective spacecited by 9
  12. 2020Multiple Network Embedding for Anomaly Detection in Time Series of Graphscited by 6
5 more
  1. 2022Euclidean mirrors and dynamics in network time seriescited by 6
  2. 2024Investigating social alignment via mirroring in a system of interacting language modelscited by 5
  3. 2024Euclidean mirrors and first-order changepoints in network time seriescited by 4
  4. 2025Detecting Perspective Shifts in Multi-agent Systemscited by 4
  5. 2025Gaussian mixture models as a proxy for interacting language modelscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Sequential statistical inference for Large Language Models: Representation, validity, and monitoringcited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2025Adaptive Monitoring and Real-World Evaluation of Agentic AI Systems
  2. 2026Agentic Visual Generation: From Generative Models to Agentic Control
  3. 2025Does It Run and Is That Enough? Revisiting Text-to-Chart Generation with a Multi-Agent Approach
  4. 2025Exposing Weak Links in Multi-Agent Systems under Adversarial Prompting
  5. 2024Multi-Agent Diagnostics for Robustness via Illuminated Diversity
  6. 2025GenAI-based Multi-Agent Reinforcement Learning towards Distributed Agent Intelligence: A Generative-RL Agent Perspective
  7. 2025An Outlook on the Opportunities and Challenges of Multi-Agent AI Systems
  8. 2026Adaptive Influence Graphs for Failure Attribution in Multi-Agent Systems