mlsanityData to 14 Oct 2026

A Diagnostic Framework for AI Agent Behavior

arXiv 2607.17149 ↗First posted 19 Jul 2026cs.AI cs.CYcited by 0

Not on the map. Why?

Abstract (arXiv)

AI agents increasingly act within the same clinical, political, scientific, and social systems that behavioral scientists study. Evaluating these systems requires source-level diagnosis: the same behavioral pattern may arise from an agent representational substrate or from the roles, objectives, interaction structures, and governance rules that shape its expression. This Perspective proposes a diagnostic framework for AI agent behavior: layer attribution. The foundational computational layer defines what behaviors are possible through architecture, memory, perception, attention, and representation. The behavioral modulation layer shapes how those capacities are expressed through identity, resources, objectives, social interaction, institutional constraints, and governance. The framework clarifies three consequences: surrogate validity is a model-task-layer relation, human-AI divergence provides diagnostic evidence, and governance requires source attribution before intervention. Treating AI agents as behavioral actors therefore requires evaluation methods that determine where behavior originates before deciding how to explain, validate, or govern it.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 40 of its 80 references that are in the map. First posted on arXiv 19 Jul 2026.

Builds on

40 of 80 references.

References · 40

  1. 2017Attention Is All You Needcited by 60,361
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  3. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  4. 2017Deep reinforcement learning from human preferencescited by 3,912
  5. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  6. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 3,050
  7. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
  8. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,808
  9. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,395
  10. 2024OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environmentscited by 1,195
  11. 2018Object Detection with Deep Learning: A Reviewcited by 528
  12. 2022Using cognitive psychology to understand GPT-3cited by 398
28 more
  1. 2025Memory in the Age of AI Agentscited by 303
  2. 2017Emergence of Grounded Compositional Language in Multi-Agent Populationscited by 263
  3. 2023Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectivescited by 257
  4. 2024Reinforcement learningcited by 247
  5. 2024Agent-as-a-Judge: Evaluate Agents with Agentscited by 238
  6. 2023Simulating Opinion Dynamics with Networks of LLM-based Agentscited by 154
  7. 2021Deep physical neural networks enabled by a backpropagation algorithm for arbitrary physical systemscited by 128
  8. 2024GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoningcited by 124
  9. 2024Emergent social conventions and collective bias in LLM populationscited by 123
  10. 2024Cognitive Bias in Decision-Making with LLMscited by 106
  11. 2023Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiationcited by 96
  12. 2025AGrail: A Lifelong Agent Guardrail with Effective and Adaptive Safety Detectioncited by 89
  13. 2025Process Reward Models for LLM Agents: Practical Framework and Directionscited by 85
  14. 2025TRiSM for Agentic AI: A Review of Trust, Risk, and Security Management in LLM-based Agentic Multi-Agent Systemscited by 59
  15. 2024One fish, two fish, but not the whole sea: Alignment reduces language models' conceptual diversitycited by 58
  16. 2026AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Securitycited by 50
  17. 2025Agentic AI: A Comprehensive Survey of Architectures, Applications, and Future Directionscited by 48
  18. 2025A Survey on the Optimization of Large Language Model-based Agentscited by 46
  19. 2024AGILE: A Novel Reinforcement Learning Framework of LLM Agentscited by 45
  20. 2023Visual cognition in multimodal large language modelscited by 38
  21. 2024A new sociology of humans and machinescited by 32
  22. 2025Whose Personae? Synthetic Persona Experiments in LLM Research and Pathways to Transparencycited by 14
  23. 2025Towards Transparent and Incentive-Compatible Collaboration in Decentralized LLM Multi-Agent Systems: A Blockchain-Driven Approachcited by 12
  24. 2025Are LLM-Powered Social Media Bots Realistic?cited by 7
  25. 2025From Single to Societal: Analyzing Persona-Induced Bias in Multi-Agent Interactionscited by 7
  26. 2025Revealing emergent human-like conceptual representations from language predictioncited by 6
  27. 2024An Active Inference Strategy for Prompting Reliable Responses from Large Language Models in Medical Practicecited by 3
  28. 2026From Biased Chatbots to Biased Agents: Examining Role Assignment Effects on LLM Agent Robustnesscited by 3

Built on by

Not cited yet.