mlsanityData to 7 Oct 2026

Stop Reducing Responsibility in LLM-Powered Multi-Agent Systems to Local Alignment

arXiv 2510.14008 ↗First posted 15 Oct 2025cs.MAcited by 7

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

Abstract (arXiv)

LLM-powered Multi-Agent Systems (LLM-MAS) unlock new potentials in distributed reasoning, collaboration, and task generalization but also introduce additional risks due to unguaranteed agreement, cascading uncertainty, and adversarial vulnerabilities. We argue that ensuring responsible behavior in such systems requires a paradigm shift: from local, superficial agent-level alignment to global, systemic agreement. We conceptualize responsibility not as a static constraint but as a lifecycle-wide property encompassing agreement, uncertainty, and security, each requiring the complementary integration of subjective human-centered values and objective verifiability. Furthermore, a dual-perspective governance framework that combines interdisciplinary design with human-AI collaborative oversight is essential for tracing and ensuring responsibility throughout the lifecycle of LLM-MAS. Our position views LLM-MAS not as loose collections of agents, but as unified, dynamic socio-technical systems that demand principled mechanisms to support each dimension of responsibility and enable ethically aligned, verifiably coherent, and resilient behavior for sustained, system-wide agreement.

Key facts. Cited by 7 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 112 of its 157 references that are in the map. First posted on arXiv 15 Oct 2025.

Builds on

112 of 157 references.

Closest ancestors · 17

Same direction, newest first

  1. 2025Enhancing Robustness of LLM-Driven Multi-Agent Systems through Randomized Smoothing5 Jul
  2. 2025Large Language Model Based Multi-Agent System Augmented Complex Event Processing Pipeline for Internet of Multimedia Things1 Jan
  3. 2024Control Industrial Automation System with Large Language Model Agents26 Sep
  4. 2024Autonomous Agents for Collaborative Task under Information Asymmetry21 Jun
  5. 2024AgentCoord: Visually Exploring Coordination Strategy for LLM-based Multi-Agent Collaboration18 Apr
  6. 2024Confidence Calibration and Rationalization for LLMs via Multi-Agent Deliberation14 Apr
  7. 2024In-context learning agents are asymmetric belief updaters6 Feb
  8. 2024LLM Multi-Agent Systems: Challenges and Open Problems5 Feb
  9. 2024Towards Uncertainty-Aware Language Agent25 Jan
  10. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challenges21 Jan
  11. 2024Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospects7 Jan
  12. 2023Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectives19 Dec
5 more
  1. 2023Multi-Agent Consensus Seeking via Large Language Models31 Oct
  2. 2023Balancing Autonomy and Alignment: A Multi-Dimensional Taxonomy for Autonomous LLM-powered Multi-Agent Architectures5 Oct
  3. 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate14 Aug
  4. 2023Of Models and Tin Men: A Behavioural Economics Study of Principal-Agent Problems in AI Alignment using Large-Language Models20 Jul
  5. 2022Improving alignment of dialogue agents via targeted human judgements28 Sep

Other references · 95

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2017Proximal Policy Optimization Algorithmscited by 14,441
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  4. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  5. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  6. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  7. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  8. 2020Learning to summarize from human feedbackcited by 2,562
  9. 2019Fine-Tuning Language Models from Human Preferencescited by 2,124
  10. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  11. 2022Language Models (Mostly) Know What They Knowcited by 1,783
  12. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,582
38 more
  1. 2023WizardLM: Empowering large pre-trained language models to follow complex instructionscited by 1,116
  2. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 995
  3. 2023ChatDev: Communicative Agents for Software Developmentcited by 893
  4. 2023Enhancing Chat Language Models by Scaling High-quality Instructional Conversationscited by 825
  5. 2023Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generationcited by 795
  6. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 739
  7. 2023RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignmentcited by 672
  8. 2022Large Language Models Can Self-Improvecited by 656
  9. 2024Self-Rewarding Language Modelscited by 654
  10. 2023RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedbackcited by 615
  11. 2023Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolutioncited by 521
  12. 2023Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervisioncited by 445
  13. 2024AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Basescited by 402
  14. 2018AI safety via debatecited by 384
  15. 2023Robots That Ask For Help: Uncertainty Alignment for Large Language Model Plannerscited by 298
  16. 2023Generating with Confidence: Uncertainty Quantification for Black-box Large Language Modelscited by 286
  17. 2023Principled Reinforcement Learning with Human Feedback from Pairwise or K-wise Comparisonscited by 244
  18. 2023Large Language Model Alignment: A Surveycited by 241
  19. 2023Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategiescited by 236
  20. 2023Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology Viewcited by 221
  21. 2023In-Context Unlearning: Language Models as Few Shot Unlearnerscited by 214
  22. 2024Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judgecited by 202
  23. 2024Advancing LLM Reasoning Generalists with Preference Treescited by 191
  24. 2025AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Societycited by 180
  25. 2024Security and Privacy Challenges of Large Language Models: A Surveycited by 179
  26. 2023Can LLM-Generated Misinformation Be Detected?cited by 173
  27. 2023Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Modelscited by 147
  28. 2018Supervising strong learners by amplifying weak expertscited by 139
  29. 2023LLM4Drive: A Survey of Large Language Models for Autonomous Drivingcited by 136
  30. 2018Stronger Data Poisoning Attacks Break Data Sanitization Defensescited by 125
  31. 2024A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directionscited by 115
  32. 2021Truthful AI: Developing and governing AI that does not liecited by 109
  33. 2023The Earth is Flat because...: Investigating LLMs' Belief towards Misinformation via Persuasive Conversationcited by 107
  34. 2024Secret Collusion among AI Agents: Multi-Agent Deception via Steganographycited by 107
  35. 2024Controllable Preference Optimization: Toward Controllable Multi-Objective Alignmentcited by 105
  36. 2020A Survey of Deep Meta-Learningcited by 99
  37. 2023A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validationcited by 91
  38. 2024SciAgents: Automating scientific discovery through multi-agent intelligent graph reasoningcited by 90

50 most cited of 95 All 95 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 5.

7 papers.

  1. 2026Lying with Truths: Open-Channel Multi-Agent Collusion for Belief Manipulation via Generative Montagecited by 17
  2. 2026Institutional AI: Governing LLM Collusion in Multi-Agent Cournot Markets via Public Governance Graphscited by 17
  3. 2025Chain-of-Thought as a Lens: Evaluating Structured Reasoning Alignment between Human Preferences and Large Language Modelscited by 5
  4. 2026AI Organizations are More Effective but Less Aligned than Individual Agentscited by 4
  5. 2025The Narrative Continuity Test: A Conceptual Framework for Evaluating Identity Persistence in AI Systemscited by 3
  6. 2026Responsible Agentic AI Requires Explicit Provenancecited by 3
  7. 2026Where Do Prompt Perturbations Break Generation? A Segment-Level View of Robustness in LoRA-Tuned Language Modelscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025Position: Towards a Responsible LLM-empowered Multi-Agent Systems
  2. 2026Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems
  3. 2025Inherent and emergent liability issues in LLM-based agentic systems: a principal-agent perspective
  4. 2026Value-Preserving Architectures for Agentic AI Systems
  5. 2026Moral Competence Before Moral Content: Why LLM Agents Lack the Prerequisites for Coherent Alignment
  6. 2025LLM-Based Human-Agent Collaboration and Interaction Systems: A Survey
  7. 2025Reliable agent engineering should integrate machine-compatible organizational principles
  8. 2025LLMs Working in Harmony: A Survey on the Technological Aspects of Building Effective LLM-Based Multi Agent Systems