mlsanityData to 14 Oct 2026

InfiAgent: Self-Evolving Pyramid Agent Framework for Infinite Scenarios

arXiv 2509.22502 ↗First posted 26 Sep 2025cs.AI cs.HCcited by 4

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

also in 1 more
Abstract (arXiv)

Large Language Model (LLM) agents have demonstrated remarkable capabilities in organizing and executing complex tasks, and many such agents are now widely used in various application scenarios. However, developing these agents requires carefully designed workflows, carefully crafted prompts, and iterative tuning, which requires LLM techniques and domain-specific expertise. These hand-crafted limitations hinder the scalability and cost-effectiveness of LLM agents across a wide range of industries. To address these challenges, we propose InfiAgent, a Pyramid-like DAG-based Multi-Agent Framework that can be applied to infinite scenarios, which introduces several key innovations: a generalized "agent-as-a-tool" mechanism that automatically decomposes complex agents into hierarchical multi-agent systems; a dual-audit mechanism that ensures the quality and stability of task completion; an agent routing function that enables efficient task-agent matching; and an agent self-evolution mechanism that autonomously restructures the agent DAG based on new tasks, poor performance, or optimization opportunities. Furthermore, InfiAgent's atomic task design supports agent parallelism, significantly improving execution efficiency. This framework evolves into a versatile pyramid-like multi-agent system capable of solving a wide range of problems. Evaluations on multiple benchmarks demonstrate that InfiAgent achieves 9.9% higher performance compared to ADAS (similar auto-generated agent framework), while a case study of the AI research assistant InfiHelper shows that it generates scientific papers that have received recognition from human reviewers at top-tier IEEE conferences.

Key facts. Cited by 4 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 42 of its 108 references that are in the map. First posted on arXiv 26 Sep 2025.

Builds on

42 of 108 references.

Closest ancestors · 12

Same direction, newest first

  1. 2025A Taxonomy of Hierarchical Multi-Agent Systems: Design Patterns, Coordination Mechanisms, and Industrial Applications18 Aug
  2. 2025A Comprehensive Review of AI Agents: Transforming Possibilities in Technology and Beyond16 Aug
  3. 2025Multi-Agent Collaboration via Evolving Orchestration26 May
  4. 2025Multi-Agent Coordination across Diverse Applications: A Survey20 Feb
  5. 2025Multi-Agent Collaboration Mechanisms: A Survey of LLMs10 Jan
  6. 2024NADER: Neural Architecture Design via Multi-Agent Collaboration26 Dec
  7. 2024Automated Design of Agentic Systems15 Aug
  8. 2024Symbolic Learning Enables Self-Evolving Agents26 Jun
  9. 2024EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms20 Jun
  10. 2024AgentGym: Evolving Large Language Model-based Agents across Diverse Environments6 Jun
  11. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challenges21 Jan
  12. 2023Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration11 Jul

Other references · 30

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  4. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  5. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  6. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  7. 2021Program Synthesis with Large Language Modelscited by 3,637
  8. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  9. 2020The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalizationcited by 1,850
  10. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,517
  11. 2020Meta-Learning in Neural Networks: A Surveycited by 950
  12. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 943
18 more
  1. 2019DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphscited by 903
  2. 2020Fast is better than free: Revisiting adversarial trainingcited by 727
  3. 2023A Comprehensive Overview of Large Language Modelscited by 648
  4. 2025The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Searchcited by 422
  5. 2023Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicinecited by 329
  6. 2021Recent Advances in Adversarial Training for Adversarial Robustnesscited by 279
  7. 2018Meta-Learning: A Surveycited by 256
  8. 2021Fixing Data Augmentation to Improve Adversarial Robustnesscited by 204
  9. 2021On the Convergence and Robustness of Adversarial Trainingcited by 130
  10. 2020A Survey of Deep Meta-Learningcited by 100
  11. 2020Smooth Adversarial Trainingcited by 89
  12. 2021A Comprehensive Survey on Hardware-Aware Neural Architecture Searchcited by 61
  13. 2025PC-Agent: A Hierarchical Multi-Agent Collaboration Framework for Complex Task Automation on PCcited by 40
  14. 2024Richelieu: Self-Evolving LLM-Based Agents for AI Diplomacycited by 36
  15. 2025AGENTiGraph: A Multi-Agent Knowledge Graph Framework for Interactive, Domain-Specific LLM Chatbotscited by 10
  16. 2023Semantically Aligned Task Decomposition in Multi-Agent Reinforcement Learningcited by 8
  17. 2025HealthGenie: Empowering Users with Healthy Dietary Guidance through Knowledge Graph and Large Language Modelscited by 4
  18. 2025Open, Reproducible and Trustworthy Robot-Based Experiments with Virtual Labs and Digital-Twin-Based Execution Tracingcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026Aligning Agentic World Models via Knowledgeable Experience Learningcited by 5
  2. 2026AWCP: A Workspace Delegation Protocol for Deep-Engagement Collaboration across Remote Agentscited by 3
  3. 2026MAGE: Multi-Agent Self-Evolution with Co-Evolutionary Knowledge Graphscited by 2
  4. 2026Project Synapse: A Hierarchical Multi-Agent Framework with Hybrid Memory for Autonomous Resolution of Last-Mile Delivery Disruptionscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2026InfiAgent: An Infinite-Horizon Framework for General-Purpose Autonomous Agents
  2. 2025Multi-Mission Tool Bench: Assessing the Robustness of LLM based Agents through Related and Dynamic Missions
  3. 2025Large Language Model Agent: A Survey on Methodology, Applications and Challenges
  4. 2025AgentNet: Decentralized Evolutionary Coordination for LLM-based Multi-Agent Systems
  5. 2026From Atomic Actions to Standard Operating Procedures: Iterative Tool Optimization for Self-Evolving LLM Agents
  6. 2025LLMs Working in Harmony: A Survey on the Technological Aspects of Building Effective LLM-Based Multi Agent Systems
  7. 2025Youtu-Agent: Scaling Agent Productivity with Automated Generation and Hybrid Policy Optimization
  8. 2025AgentSwift: Efficient LLM Agent Design via Value-guided Hierarchical Search