mlsanityData to 7 Oct 2026

Reliable agent engineering should integrate machine-compatible organizational principles

arXiv 2512.07665 ↗First posted 8 Dec 2025cs.CY cs.MA cs.SEcited by 2

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

As AI agents built on large language models (LLMs) become increasingly embedded in society, issues of coordination, control, delegation, and accountability are entangled with concerns over their reliability. To design and implement LLM agents around reliable operations, we should consider the task complexity in the application settings and reduce their limitations while striving to minimize agent failures and optimize resource efficiency. High-functioning human organizations have faced similar balancing issues, which led to evidence-based theories that seek to understand their functioning strategies. We examine the parallels between LLM agents and the compatible frameworks in organization science, focusing on what the design, scaling, and management of organizations can inform agentic systems towards improving reliability. We offer three preliminary accounts of organizational principles for AI agent engineering to attain reliability and effectiveness, through balancing agency and capabilities in agent design, resource constraints and performance benefits in agent scaling, and internal and external mechanisms in agent management. Our work extends the growing exchanges between the operational and governance principles of AI systems and social systems to facilitate system integration.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 69 of its 169 references that are in the map. First posted on arXiv 8 Dec 2025.

Builds on

69 of 169 references.

Closest ancestors · 11

Same direction, newest first

  1. 2025Self-Improving LLM Agents at Test-Time9 Oct
  2. 2025ARE: Scaling Up Agent Environments and Evaluations21 Sep
  3. 2025A Comprehensive Review of AI Agents: Transforming Possibilities in Technology and Beyond16 Aug
  4. 2025Efficient Agents: Building Effective Agents While Reducing Cost24 Jul
  5. 2025Small Language Models are the Future of Agentic AI2 Jun
  6. 2025Agentic AI Needs a Systems Theory28 Feb
  7. 2025AgentBreeder: Mitigating the AI Safety Risks of Multi-Agent Scaffolds via Self-Improvement2 Feb
  8. 2025Multi-Agent Collaboration Mechanisms: A Survey of LLMs10 Jan
  9. 2024τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains17 Jun
  10. 2024Improving Multi-Agent Debate with Sparse Communication Topology17 Jun
  11. 2024More Agents Is All You Need3 Feb

Other references · 58

  1. 2020Scaling Laws for Neural Language Modelscited by 6,411
  2. 2023Let's Verify Step by Stepcited by 3,598
  3. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,302
  4. 2024Evaluating Very Long-Term Conversational Memory of LLM Agentscited by 800
  5. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 751
  6. 2023Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedbackcited by 743
  7. 2024A Survey on Large Language Models for Code Generationcited by 646
  8. 2024GPT-4V(ision) is a Generalist Web Agent, if Groundedcited by 547
  9. 2024Executable Code Actions Elicit Better LLM Agentscited by 537
  10. 2025LLMs Get Lost In Multi-Turn Conversationcited by 400
  11. 2023MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoningcited by 311
  12. 2024Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Modelscited by 282
38 more
  1. 2025ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memorycited by 253
  2. 2023Challenges and Applications of Large Language Modelscited by 251
  3. 2025Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safetycited by 222
  4. 2025A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?cited by 215
  5. 2024From Persona to Personalization: A Survey on Role-Playing Language Agentscited by 206
  6. 2023Inverse Scaling: When Bigger Isn't Bettercited by 205
  7. 2023Personality Traits in Large Language Modelscited by 166
  8. 2024MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Makingcited by 162
  9. 2024GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoningcited by 113
  10. 2024When combinations of humans and AI are useful: A systematic review and meta-analysiscited by 100
  11. 2024Systematic Biases in LLM Simulations of Debatescited by 98
  12. 2024The Butterfly Effect of Altering Prompts: How Small Changes and Jailbreaks Affect Large Language Model Performancecited by 97
  13. 2023Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiationcited by 94
  14. 2024How Well Can LLMs Negotiate? NegotiationArena Platform and Analysiscited by 93
  15. 2023Language Model Behavior: A Comprehensive Surveycited by 92
  16. 2024Coercing LLMs to do and reveal (almost) anythingcited by 88
  17. 2024Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solvingcited by 82
  18. 2024ToolSword: Unveiling Safety Issues of Large Language Models in Tool Learning Across Three Stagescited by 77
  19. 2022Inverse scaling can become U-shapedcited by 76
  20. 2024Building Machines that Learn and Think with Peoplecited by 73
  21. 2025Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learningcited by 68
  22. 2025Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agentscited by 66
  23. 2025Talk Isn't Always Cheap: Understanding Failure Modes in Multi-Agent Debatecited by 63
  24. 2025Collaborative Memory: Multi-User Memory Sharing in LLM Agents with Dynamic Access Controlcited by 56
  25. 2024Learning to Use Tools via Cooperative and Interactive Agentscited by 54
  26. 2024What Are Tools Anyway? A Survey from the Language Model Perspectivecited by 53
  27. 2025SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolutioncited by 52
  28. 2025Demonstrating specification gaming in reasoning modelscited by 48
  29. 2025Fully Autonomous AI Agents Should Not be Developedcited by 43
  30. 2025A Survey of Process Reward Models: From Outcome Signals to Process Supervisions for Large Language Modelscited by 37
  31. 2025Medical Large Language Model Benchmarks Should Prioritize Construct Validitycited by 36
  32. 2024Take Caution in Using LLMs as Human Surrogates: Scylla Ex Machinacited by 29
  33. 2025Why Are Web AI Agents More Vulnerable Than Standalone LLMs? A Security Analysiscited by 27
  34. 2025(Mis)Fitting: A Survey of Scaling Lawscited by 24
  35. 2025Security Challenges in AI Agent Deployment: Insights from a Large Scale Public Competitioncited by 22
  36. 2024Advancing Social Intelligence in AI Agents: Technical Challenges and Open Questionscited by 21
  37. 2025Remote Labor Index: Measuring AI Automation of Remote Workcited by 18
  38. 2025Build the web for agents, not agents for the webcited by 17

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026TopoPilot: Reliable Conversational Workflow Automation for Topological Data Analysis and Visualizationcited by 3
  2. 2026Loop-Back Authority in LLM Agent Teams: A Paired Experiment on Flat and Hierarchical Coordinationcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2026Architecting Agentic Communities using Design Patterns
  2. 2025Empowering Real-World: A Survey on the Technology, Practice, and Evaluation of LLM-driven Industry Agents
  3. 2026If You Want Coherence, Orchestrate a Team of Rivals: Multi-Agent Models of Organizational Intelligence
  4. 2026Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems
  5. 2025A Call for Collaborative Intelligence: Why Human-Agent Systems Should Precede AI Autonomy
  6. 2026Toward an Organizational Science of Multi-Agent LLM Systems: Decoupling Who, How, and Which Algorithm
  7. 2026Can LLM Agents Sustain Long-Horizon Organizational Dynamics?
  8. 2026The Agent Use of Agent Beings: Agent Cybernetics Is the Missing Science of Foundation Agents