mlsanityData to 14 Oct 2026

Glia: A Human-Inspired AI for Automated Systems Design and Optimization

arXiv 2510.27176 ↗First posted 31 Oct 2025cs.AI cs.CL cs.DCcited by 16

Not on the map. Why?

Abstract (arXiv)

Can AI autonomously design mechanisms for computer systems on par with the creativity and reasoning of human experts? We present Glia, an AI architecture for networked systems design that uses large language models (LLMs) in a human-inspired multi-agent workflow. Each agent specializes in reasoning, experimentation, and analysis, collaborating through an evaluation framework that grounds abstract reasoning in empirical feedback. Unlike prior ML-for-systems methods that optimize black-box policies, Glia generates interpretable designs and exposes its reasoning. When applied to a distributed GPU cluster for LLM inference, it produces new algorithms for request routing, scheduling, and auto-scaling that perform at human-expert levels in significantly less time, while yielding novel insights into workload behavior. Our results suggest that combining reasoning LLMs with structured experimentation, an AI can produce creative and understandable designs for complex systems problems.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Builds on 42 of its 130 references that are in the map. First posted on arXiv 31 Oct 2025.

Builds on

42 of 130 references.

References · 42

  1. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  2. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  3. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  4. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameterscited by 1,986
  5. 2022Competition-Level Code Generation with AlphaCodecited by 1,462
  6. 2025AlphaEvolve: A coding agent for scientific and algorithmic discoverycited by 867
  7. 2023Splitwise: Efficient generative LLM inference using phase splittingcited by 558
  8. 2024Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Servecited by 526
  9. 2024Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Modelcited by 268
  10. 2018Learning Scheduling Algorithms for Data Processing Clusterscited by 134
  11. 2024Vidur: A Large-Scale Simulation Framework For LLM Inferencecited by 117
  12. 2025Monte Carlo Tree Search for Comprehensive Exploration in LLM-Based Automatic Heuristic Designcited by 109
30 more
  1. 2019Neo: A Learned Query Optimizercited by 80
  2. 2019Scaling Distributed Machine Learning with In-Network Aggregationcited by 65
  3. 2020Bao: Learning to Steer Query Optimizerscited by 62
  4. 2025An AI system to help scientists write expert-level empirical softwarecited by 60
  5. 2024Multi-objective Evolution of Heuristic Using Large Language Modelcited by 54
  6. 2025Astra: A Multi-Agent System for GPU Kernel Performance Optimizationcited by 51
  7. 2025SR-Scientist: Scientific Equation Discovery With Agentic AIcited by 35
  8. 2024LLM4AD: A Platform for Algorithm Design with Large Language Modelcited by 33
  9. 2025CALM: Co-evolution of Algorithms and Language Model for Automatic Heuristic Designcited by 29
  10. 2019Adaptive Neural Signal Detection for Massive MIMOcited by 27
  11. 2025AlgoTune: Can Language Models Speed Up General-Purpose Numerical Programs?cited by 27
  12. 2025GPU Kernel Scientist: An LLM-Driven Framework for Iterative Kernel Optimizationcited by 22
  13. 2025Scientific Algorithm Discovery by Augmenting AlphaEvolve with Deep Researchcited by 19
  14. 2024A Queueing Theoretic Perspective on Low-Latency LLM Inference with Variable Token Lengthcited by 16
  15. 2020Real-world Video Adaptation with Reinforcement Learningcited by 12
  16. 2024Designing Network Algorithms via Large Language Modelscited by 12
  17. 2024Improving Parallel Program Performance with LLM Optimizers via Agent-System Interfacescited by 11
  18. 2025Current and Future Use of Large Language Models for Knowledge Workcited by 10
  19. 2025Fitness Landscape of Large Language Model-Assisted Automated Algorithm Searchcited by 9
  20. 2022Gemino: Practical and Robust Neural Compression for Video Conferencingcited by 8
  21. 2023Reparo: Loss-Resilient Generative Codec for Video Conferencingcited by 8
  22. 2018Internet Congestion Control via Deep Reinforcement Learningcited by 7
  23. 2025(X)-evolve: Solution space evolution powered by large language modelscited by 6
  24. 2025Man-Made Heuristics Are Dead. Long Live Code Generators!cited by 6
  25. 2025Congestion Control System Optimization with Large Language Modelscited by 5
  26. 2025MetaMuse: Algorithm Generation via Creative Ideationcited by 4
  27. 2017DeepConfig: Automating Data Center Network Topologies Management with Machine Learningcited by 3
  28. 2018Iroko: A Framework to Prototype Reinforcement Learning for Data Center Traffic Controlcited by 3
  29. 2024Towards Safer Heuristics With XPlaincited by 2
  30. 2017RLWS: A Reinforcement Learning based GPU Warp Schedulercited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 14.

16 papers.

Sort:

By area:

  1. 2026Improving Coherence and Persistence in Agentic AI for System Optimizationcited by 7
  2. 2026AI-Driven Research for Databasescited by 2
  3. 2026GENESIS: Harnessing AI Agents for Autonomous 6G RAN Synthesis, Research, and Testingcited by 2
  4. 2026Don't Gamble, GAMBLe: An Analytical Framework for AI-Driven Research Systemscited by 2
  5. 2025Automated Design Optimization via Strategic Search with Large Language Modelscited by 1
  6. 2025Vulcan: Instance-specialized, Verifiable Systems Heuristics Through LLM-driven Searchcited by 1
  7. 2026ArchAgent v2: A Case Study with the Data Prefetching Championshipcited by 1
  8. 2026FLARE: Verifying MILP Reformulations with LLM-Based Theorem Provingcited by 1
  9. 2026Airavat: An Agentic Framework for Internet Measurementcited by 0
  10. 2026Agent-Aided Design for Dynamic CAD Modelscited by 0
  11. 2026Assistants, Not Architects: The Role of LLMs in Networked Systems Designcited by 0
  12. 2026TuxBot: Semantic-Aware Online OS Tuning with Large Language Modelscited by 0
4 more
  1. 2026The Time is Here for Just-in-Time Systems: Challenges and Opportunitiescited by 0
  2. 2026A Vocabulary for Multi-Agent Automated Research Systemscited by 0
  3. 2026ROAR: Unifying Runs across Heterogeneous AI-Driven Research Systemscited by 0
  4. 2026A Self-Defining Operator for Distributed Applicationscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026AgentFactory: Towards Automated Agentic System Design and Optimization
  2. 2026Co-evolving Agent Architectures and Interpretable Reasoning for Automated Optimization
  3. 2025The FM Agent
  4. 2026Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligence
  5. 2026When Cloud Agents Meet Device Agents: Lessons from Hybrid Multi-Agent Systems
  6. 2026SimpleEvol: An Agent-Loop Framework for LLM-Driven Automated Heuristic Design with Minimal Human Priors
  7. 2025The Cost of Dynamic Reasoning: Demystifying AI Agents and Test-Time Scaling from an AI Infrastructure Perspective
  8. 2026Brain-Inspired Graph Multi-Agent Systems for LLM Reasoning