mlsanityData to 14 Oct 2026

Latency and Cost of Multi-Agent Intelligent Tutoring at Scale

arXiv 2604.24110 ↗First posted 27 Apr 2026cs.CY cs.AI cs.DCcited by 0

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

Abstract (arXiv)

Multi-agent LLM tutoring systems improve response quality through agent specialization, but each student query triggers several concurrent API calls whose latencies compound through a parallel-phase maximum effect that single-agent systems do not face. We instrument ITAS, a four-agent tutoring system built on Gemini 2.5 Flash and Google Vertex AI, across three throughput tiers (Standard PayGo, Priority PayGo, and Provisioned Throughput) and eleven concurrency levels up to 50 simultaneous users, producing over 3,000 requests drawn from a live graduate STEM deployment. Priority PayGo maintains flat sub-4-second response times across the full load range; Standard PayGo degrades substantially under classroom-scale concurrency; and Provisioned Throughput delivers the lowest latency at low concurrency but saturates its reserved capacity above approximately 20 concurrent users. Cost analysis places both pay-per-token tiers well below the price of a STEM textbook per student per semester under a worst-case usage ceiling. Provisioned Throughput, expensive under continuous provisioning, becomes cost-competitive for institutions that can predict and concentrate their traffic toward high utilization. These results provide concrete tier-selection guidance across deployment scales from a single seminar to a university-wide rollout.

Key facts. No citing papers in the map yet (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 17 of its 29 references that are in the map. First posted on arXiv 27 Apr 2026.

Builds on

17 of 29 references.

References · 17

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  2. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  3. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
  4. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,808
  5. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
  6. 2022Fast Inference from Transformers via Speculative Decodingcited by 1,653
  7. 2023Accelerating Large Language Model Decoding with Speculative Samplingcited by 1,006
  8. 2023FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performancecited by 853
  9. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 769
  10. 2024DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Servingcited by 617
  11. 2024Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Servecited by 526
  12. 2023Practical and Ethical Challenges of Large Language Models in Education: A Systematic Scoping Reviewcited by 83
5 more
  1. 2022The AI Teacher Test: Measuring the Pedagogical Ability of Blender and GPT-3 in Educational Dialoguescited by 79
  2. 2024Towards Responsible Development of Generative AI for Education: An Evaluation-Driven Approachcited by 54
  3. 2023The BEA 2023 Shared Task on Generating AI Teacher Responses in Educational Dialoguescited by 27
  4. 2024GPT-4 as a Homework Tutor can Improve Student Engagement and Learning Outcomescited by 9
  5. 2025Toward Personalizing Quantum Computing Education: An Evolutionary LLM-Powered Approachcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026ITAS: A Multi-Agent Architecture for LLM-Based Intelligent Tutoring
  2. 2025IntelliCode: A Multi-Agent LLM Tutoring System with Centralized Learner Modeling
  3. 2025TutorGym: A Testbed for Evaluating AI Agents as Tutors and Students
  4. 2025An Empirical Study of Multi-Agent RAG for Real-World University Admissions Counseling
  5. 2026Enhancing LLM Problem Solving via Tutor-Student Multi-Agent Interaction
  6. 2026From 50% to Mastery in 3 Days: A Low-Resource SOP for Localizing Graduate-Level AI Tutors via Shadow-RAG
  7. 2026Learning Engagement Assistant (LEA): Cross-Course Scalability and Classroom Evaluation of an Agentic AI Tutoring System
  8. 2026Scaling Laws for Educational AI Agents