mlsanityData to 13 Oct 2026

When Should We Orchestrate Multiple Agents?

arXiv 2503.13577 ↗First posted 17 Mar 2025cs.MA cs.CY cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

Strategies for orchestrating the interactions between multiple agents, both human and artificial, can wildly overestimate performance and underestimate the cost of orchestration. We design a framework to orchestrate agents under realistic conditions, such as inference costs or availability constraints. We show theoretically that orchestration is only effective if there are performance or cost differentials between agents. We then empirically demonstrate how orchestration between multiple agents can be helpful for selecting agents in a simulated environment, picking a learning strategy in the infamous Rogers' Paradox from social science, and outsourcing tasks to other agents during a question-answer task in a user study.

Key facts. Cited by 7 papers in the map (data through 13 Oct 2026). Builds on 25 of its 43 references that are in the map. First posted on arXiv 17 Mar 2025.

Builds on

25 of 43 references.

References · 25

  1. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,072
  2. 2020Measuring Massive Multitask Language Understandingcited by 7,876
  3. 2021Scaling Vision with Sparse Mixture of Expertscited by 744
  4. 2020Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performancecited by 399
  5. 2020Consistent Estimators for Learning to Defer to an Expertcited by 268
  6. 2017Predict Responsibly: Improving Fairness and Accuracy by Learning to Defercited by 232
  7. 2023Do LLMs exhibit human-like response biases? A case study in survey designcited by 177
  8. 2024When combinations of humans and AI are useful: A systematic review and meta-analysiscited by 105
  9. 2024Building Machines that Learn and Think with Peoplecited by 73
  10. 2021Towards Unbiased and Accurate Deferral to Multiple Expertscited by 71
  11. 2022Human-AI Collaboration via Conditional Delegation: A Case Study of Content Moderationcited by 67
  12. 2022Sample Efficient Learning of Predictors that Complement Humanscited by 46
13 more
  1. 2022Forming Effective Human-AI Teams: Building Machine Learning Models that Complement the Capabilities of Multiple Expertscited by 40
  2. 2019Ask Not What AI Can Do, But What AI Should Do: Towards a Framework of Task Delegabilitycited by 36
  3. 2021Human-AI Collaboration with Bandit Feedbackcited by 36
  4. 2021Teaching Humans When To Defer to a Classifier via Exemplarscited by 29
  5. 2017Online Learning with Abstentioncited by 28
  6. 2024A Decision Theoretic Framework for Measuring AI Reliancecited by 27
  7. 2023Accuracy-Time Tradeoffs in AI-Assisted Decision Making under Time Pressurecited by 17
  8. 2023Learning Personalized Decision Support Policiescited by 13
  9. 2024Modulating Language Model Experiences through Frictionscited by 13
  10. 2023Optimizing delegation between human and AI collaborative agentscited by 9
  11. 2023Learning Complementary Policies for Human-AI Teamscited by 7
  12. 2024Representational Alignment Supports Effective Machine Teachingcited by 3
  13. 2025Revisiting Rogers' Paradox in the Context of Human-AI Interactioncited by 2

Built on by

Cited by year (2026 to 13 Oct)

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

7 papers.

  1. 2025A Survey of Context Engineering for Large Language Modelscited by 122
  2. 2025Inherent and emergent liability issues in LLM-based agentic systems: a principal-agent perspectivecited by 12
  3. 2025Terrarium: Revisiting the Blackboard for Multi-Agent Safety, Privacy, and Security Studiescited by 10
  4. 2025UFO3: Weaving the Digital Agent Galaxycited by 6
  5. 2026Why Human Guidance Matters in Collaborative Vibe Codingcited by 3
  6. 2025Guided by the Experts: Provable Feature Learning Dynamic of Soft-Routed Mixture-of-Expertscited by 2
  7. 2026Multi-Agent Coordination Adaptation via Structure-Guided Orchestrationcited by 2