mlsanityData to 14 Oct 2026

Multi-Stakeholder Alignment in LLM-Powered Collaborative AI Systems: A Multi-Agent Framework for Intelligent Tutoring

arXiv 2510.23245 ↗First posted 27 Oct 2025cs.HC cs.MAcited by 2

On the map: LLM agents and tool use → Educational agents and math problem solving

Abstract (arXiv)

The integration of Large Language Models into Intelligent Tutoring Systems pre-sents significant challenges in aligning with diverse and often conflicting values from students, parents, teachers, and institutions. Existing architectures lack for-mal mechanisms for negotiating these multi-stakeholder tensions, creating risks in accountability and bias. This paper introduces the Advisory Governance Layer (AGL), a non-intrusive, multi-agent framework designed to enable distributed stakeholder participation in AI governance. The AGL employs specialized agents representing stakeholder groups to evaluate pedagogical actions against their spe-cific policies in a privacy-preserving manner, anticipating future advances in per-sonal assistant technology that will enhance stakeholder value expression. Through a novel policy taxonomy and conflict-resolution protocols, the frame-work provides structured, auditable governance advice to the ITS without altering its core pedagogical decision-making. This work contributes a reference architec-ture and technical specifications for aligning educational AI with multi-stakeholder values, bridging the gap between high-level ethical principles and practical implementation.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Educational agents and math problem solving, one of 16 directions in LLM agents and tool use. Builds on 59 of its 100 references that are in the map. First posted on arXiv 27 Oct 2025.

Builds on

59 of 100 references.

References · 59

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  3. 2022Emergent Abilities of Large Language Modelscited by 2,512
  4. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
  5. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,808
  6. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
  7. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,745
  8. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,439
  9. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 1,011
  10. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 769
  11. 2024Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Trainingcited by 529
  12. 2022LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Modelscited by 462
38 more
  1. 2025Multi-Agent Collaboration Mechanisms: A Survey of LLMscited by 431
  2. 2023Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedbackcited by 353
  3. 2023Tool Learning with Foundation Modelscited by 302
  4. 2023The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learningcited by 257
  5. 2023AI Control: Improving Safety Despite Intentional Subversioncited by 229
  6. 2025AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agentscited by 223
  7. 2023Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology Viewcited by 222
  8. 2023AI Deception: A Survey of Examples, Risks, and Potential Solutionscited by 188
  9. 2023Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmarkcited by 182
  10. 2023Large Language Models can Strategically Deceive their Users when Put Under Pressurecited by 146
  11. 2024Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospectscited by 132
  12. 2023Are Emergent Abilities in Large Language Models just In-Context Learning?cited by 109
  13. 2023Avalon's Game of Thoughts: Battle Against Deception through Recursive Contemplationcited by 104
  14. 2022Picking on the Same Person: Does Algorithmic Monoculture lead to Outcome Homogenization?cited by 91
  15. 2023On the Planning Abilities of Large Language Models (A Critical Investigation with a Proposed Benchmark)cited by 85
  16. 2023How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questionscited by 83
  17. 2023Training Socially Aligned Language Models on Simulated Social Interactionscited by 78
  18. 2025Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agentscited by 71
  19. 2023Empirical Study of Zero-Shot NER with ChatGPTcited by 60
  20. 2023On the Creativity of Large Language Modelscited by 57
  21. 2025A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasurescited by 57
  22. 2024zkLLM: Zero Knowledge Proofs for Large Language Modelscited by 51
  23. 2023Self-Polish: Enhance Reasoning in Large Language Models via Problem Refinementcited by 43
  24. 2023SentimentGPT: Exploiting GPT for Advanced Sentiment Analysis and its Departure from Current Machine Learningcited by 38
  25. 2024Trust in AI: Progress, Challenges, and Future Directionscited by 35
  26. 2023A Comprehensive AI Policy Education Framework for University Teaching and Learningcited by 34
  27. 2025Explainable Rule Application via Structured Prompting: A Neural-Symbolic Approachcited by 14
  28. 2022A Transparency Index Framework for AI in Educationcited by 13
  29. 2023DP-Auditorium: a Large Scale Library for Auditing Differential Privacycited by 11
  30. 2025Speaking the Language of Teamwork: LLM-Guided Credit Assignment in Multi-Agent Reinforcement Learningcited by 10
  31. 2024AI and personalized learning: bridging the gap with modern educational goalscited by 8
  32. 2025Position: Towards a Responsible LLM-empowered Multi-Agent Systemscited by 8
  33. 2023A Survey of Federated Evaluation in Federated Learningcited by 7
  34. 2024From Guidelines to Governance: A Study of AI Policies in Educationcited by 4
  35. 2025Enforcement Agents: Enhancing Accountability and Resilience in Multi-Agent AI Frameworkscited by 4
  36. 2023Understanding Your Agent: Leveraging Large Language Models for Behavior Explanationcited by 3
  37. 2025Selecting and Merging: Towards Adaptable and Scalable Named Entity Recognition with Large Language Modelscited by 3
  38. 2022RV4JaCa -- Runtime Verification for Multi-Agent Systemscited by 2

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Fair Agents: Balancing Multistakeholder Alignment in Multi-Agent Personalization Systemscited by 0
  2. 2026Agentic AI Ecosystems in Higher Education: A Perspective on AI Agents to Emerging Inclusive, Agentic Multi-Agent AI Framework for Learning, Teaching and Institutional Intelligencecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Modularizing Educational LLM-Agency for Fostering Responsible Learning Assistance
  2. 2026Addressing the Reality Gap: A Three-Tension Framework for Agentic AI Adoption
  3. 2025Bidirectional Human-AI Alignment in Education for Trustworthy Learning Environments
  4. 2026LLM Constitutional Multi-Agent Governance
  5. 2025Hierarchical Pedagogical Oversight: A Multi-Agent Adversarial Framework for Reliable AI Tutoring
  6. 2025Enabling Multi-Agent Systems as Learning Designers: Applying Learning Sciences to AI Instructional Design
  7. 2025Multi-level Value Alignment in Agentic AI Systems: Survey and Perspectives
  8. 2026Computational Reflective Equilibrium for Agentic AI: A Rawlsian Alignment Scaffold for Governance