mlsanityData to 14 Oct 2026

Multi-agent Architecture Search via Agentic Supernet

arXiv 2502.04180 ↗First posted 6 Feb 2025cs.LG cs.CL cs.MAcited by 179

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

Abstract (arXiv)

Large Language Model (LLM)-empowered multi-agent systems extend the cognitive boundaries of individual agents through disciplined collaboration and interaction, while constructing these systems often requires labor-intensive manual designs. Despite the availability of methods to automate the design of agentic workflows, they typically seek to identify a static, complex, one-size-fits-all system, which, however, fails to dynamically allocate inference resources based on the difficulty and domain of each query. To address this challenge, we shift away from the pursuit of a monolithic agentic system, instead optimizing the agentic supernet, a probabilistic and continuous distribution of agentic architectures. We introduce MaAS, an automated framework that samples query-dependent agentic systems from the supernet, delivering high-quality solutions and tailored resource allocation (textite.g., LLM calls, tool calls, token cost). Comprehensive evaluation across six benchmarks demonstrates that MaAS (I) requires only 6~45% of the inference costs of existing handcrafted or automated multi-agent systems, (II) surpasses them by 0.54%~11.82%, and (III) enjoys superior cross-dataset and cross-LLM-backbone transferability.

Key facts. Cited by 179 papers in the map (data through 14 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 56 of its 99 references that are in the map. First posted on arXiv 6 Feb 2025.

Builds on

56 of 99 references.

Closest ancestors · 14

Same direction, newest first

  1. 2024TapeAgents: a Holistic Framework for Agent Development and Optimization11 Dec
  2. 2024G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networks15 Oct
  3. 2024AgentSquare: Automatic LLM Agent Search in Modular Design Space8 Oct
  4. 2024Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems3 Oct
  5. 2024Automated Design of Agentic Systems15 Aug
  6. 2024Sibyl: Simple yet Effective Agent Framework for Complex Real-world Reasoning15 Jul
  7. 2024Symbolic Learning Enables Self-Evolving Agents26 Jun
  8. 2024EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms20 Jun
  9. 2024Scaling Large Language Model-based Multi-Agent Collaboration11 Jun
  10. 2024Can Graph Learning Improve Planning in LLM-based Agents?29 May
  11. 2024KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents5 Mar
  12. 2023AutoAgents: A Framework for Automatic Agent Generation29 Sep
2 more
  1. 2023A Survey on Large Language Model based Autonomous Agents22 Aug
  2. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society31 Mar

Other references · 42

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  3. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  4. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  5. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  6. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  7. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  8. 2024Qwen2.5 Technical Reportcited by 4,942
  9. 2021Program Synthesis with Large Language Modelscited by 3,637
  10. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,509
  11. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  12. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
30 more
  1. 2018DARTS: Differentiable Architecture Searchcited by 1,798
  2. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
  3. 2016Neural Architecture Search with Reinforcement Learningcited by 1,499
  4. 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,463
  5. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,389
  6. 2023Mind2Web: Towards a Generalist Agent for the Webcited by 1,242
  7. 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Facecited by 1,190
  8. 2023GAIA: a benchmark for General AI Assistantscited by 1,128
  9. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 1,011
  10. 2023DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelinescited by 832
  11. 2022Automatic Chain of Thought Prompting in Large Language Modelscited by 688
  12. 2023LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusioncited by 564
  13. 2023Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolutioncited by 551
  14. 2024AFlow: Automating Agentic Workflow Generationcited by 432
  15. 2019AutoML: A Survey of the State-of-the-Artcited by 390
  16. 2022Complexity-Based Prompting for Multi-Step Reasoningcited by 388
  17. 2016Solving General Arithmetic Word Problemscited by 360
  18. 2018SNAS: Stochastic Neural Architecture Searchcited by 289
  19. 2020A Comprehensive Survey of Neural Architecture Search: Challenges and Solutionscited by 254
  20. 2024Data Interpreter: An LLM Agent For Data Sciencecited by 225
  21. 2024From Persona to Personalization: A Survey on Role-Playing Language Agentscited by 212
  22. 2024GraphRouter: A Graph-based Router for LLM Selectionscited by 165
  23. 2020A Survey on Evolutionary Neural Architecture Searchcited by 142
  24. 2023Neural Architecture Search: Insights from 1000 Paperscited by 139
  25. 2024Self-Evolving Multi-Agent Collaboration Networks for Software Developmentcited by 74
  26. 2024Harder Tasks Need More Experts: Dynamic Routing in MoE Modelscited by 72
  27. 2024AutoKaggle: A Multi-Agent Framework for Autonomous Data Science Competitionscited by 70
  28. 2024Archon: An Architecture Search Framework for Inference-Time Techniquescited by 60
  29. 2023VerifAI: Verified Generative AIcited by 16
  30. 2020FP-NAS: Fast Probabilistic Neural Architecture Searchcited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 64; 2026: 115.

179 papers.

Sort:

By area:

  1. 2025Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agentscited by 356
  2. 2025A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligencecited by 170
  3. 2025Towards a Science of Scaling Agent Systemscited by 138
  4. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 126
  5. 2025G-Memory: Tracing Hierarchical Memory for Multi-Agent Systemscited by 122
  6. 2025A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deploymentcited by 116
  7. 2025AgenTracer: Who Is Inducing Failure in the LLM Agentic Systems?cited by 116
  8. 2025A Survey on Trustworthy LLM Agents: Threats and Countermeasurescited by 96
  9. 2025MemEvolve: Meta-Evolution of Agent Memory Systemscited by 95
  10. 2025FlowReasoner: Reinforcing Query-Level Meta-Agentscited by 63
  11. 2025FLEX: Continuous Agent Evolution via Forward Learning from Experiencecited by 52
  12. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 50
38 more
  1. 2025EvoAgentX: An Automated Framework for Evolving Agentic Workflowscited by 44
  2. 2025AGENTSAFE: Benchmarking the Safety of Embodied Agents on Hazardous Instructionscited by 38
  3. 2026MAS-Orchestra: Understanding and Improving Multi-Agent Reasoning Through Holistic Orchestration and Controlled Benchmarkscited by 32
  4. 2025Two Heads are Better Than One: Test-time Scaling of Multi-agent Collaborative Reasoningcited by 29
  5. 2025Adaptive Graph Pruning for Multi-Agent Communicationcited by 29
  6. 2026From Failed Trajectories to Reliable LLM Agents: Diagnosing and Repairing Harness Flawscited by 29
  7. 2025We Should Identify and Mitigate Third-Party Safety Risks in MCP-Powered Agent Systemscited by 27
  8. 2025Difficulty-Aware Agentic Orchestration for Query-Specific Multi-Agent Workflowscited by 27
  9. 2026From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agentscited by 24
  10. 2025DyFlow: Dynamic Workflow Framework for Agentic Reasoningcited by 23
  11. 2025Weak-for-Strong: Training Weak Meta-Agent to Harness Strong Executorscited by 22
  12. 2025Aegis: Automated Error Generation and Attribution for Multi-Agent Systemscited by 22
  13. 2026HarnessForge: Joint Harness and Policy Evolution for Adaptive Agent Systemscited by 21
  14. 2025RobustFlow: Towards Robust Agentic Workflow Generationcited by 20
  15. 2025Failure-Driven Workflow Refinementcited by 20
  16. 2025VFlow: Discovering Optimal Agentic Workflows for Verilog Generationcited by 19
  17. 2026Learning to Continually Learn via Meta-learning Agentic Memory Designscited by 18
  18. 2025MermaidFlow: Redefining Agentic Workflow Generation via Safety-Constrained Evolutionary Programmingcited by 16
  19. 2026EvoRoute: Experience-Driven Self-Routing LLM Agent Systemscited by 16
  20. 2026Effective Strategies for Asynchronous Software Engineering Agentscited by 16
  21. 2026JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolutioncited by 16
  22. 2025AgentSwift: Efficient LLM Agent Design via Value-guided Hierarchical Searchcited by 15
  23. 2025SafeMobile: Chain-level Jailbreak Detection and Automated Evaluation for Multimodal Mobile Agentscited by 15
  24. 2026LatentMem: Customizing Latent Memory for Multi-Agent Systemscited by 15
  25. 2025Graph-Augmented Large Language Model Agents: Current Progress and Future Prospectscited by 14
  26. 2026OFA-MAS: One-for-All Multi-Agent System Topology Design based on Mixture-of-Experts Graph Generative Modelscited by 14
  27. 2025Visual Multi-Agent System: Mitigating Hallucination Snowballing via Visual Flowcited by 13
  28. 2026AgentConductor: Topology Evolution for Multi-Agent Competition-Level Code Generationcited by 13
  29. 2026Synthesizing Multi-Agent Harnesses for Vulnerability Discoverycited by 13
  30. 2025Stop Wasting Your Tokens: Towards Efficient Runtime Multi-Agent Systemscited by 12
  31. 2026FALAT: Tracing Failures in LLM Agent Trajectories via Dependency-Guided Searchcited by 12
  32. 2025Exploring Advanced LLM Multi-Agent Systems Based on Blackboard Architecturecited by 11
  33. 2025Dynamic Generation of Multi-LLM Agents Communication Topologies with Graph Diffusion Modelscited by 11
  34. 2025AgentAsk: Multi-Agent Systems Need to Askcited by 10
  35. 2025Automated Composition of Agents: A Knapsack Approach for Agentic Component Selectioncited by 10
  36. 2025Aime: Towards Fully-Autonomous Multi-Agent Frameworkcited by 9
  37. 2026MetaGen: Self-Evolving Roles and Topologies for Multi-Agent LLM Reasoningcited by 9
  38. 2026The Illusion of Multi-Agent Advantagecited by 9

50 most cited of 179 All 179 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025AutoMaAS: Self-Evolving Multi-Agent Architecture Search for Large Language Models
  2. 2026Can Small Agents Collaborate to Beat a Single Large Language Model?
  3. 2025AgentsNet: Coordination and Collaborative Reasoning in Multi-Agent LLMs
  4. 2026Agentic Artificial Intelligence (AI): Architectures, Taxonomies, and Evaluation of Large Language Model Agents
  5. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challenges
  6. 2026An Empirical Study of Multi-Agent Collaboration for Automated Research
  7. 2025AgentNet: Decentralized Evolutionary Coordination for LLM-based Multi-Agent Systems
  8. 2025MAPRO: Recasting Multi-Agent Prompt Optimization as Maximum a Posteriori Inference