# InfiAgent: Self-Evolving Pyramid Agent Framework for Infinite Scenarios

arXiv: https://arxiv.org/abs/2509.22502 · HTML: https://mlsanity.com/paper/2509.22502/

## 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.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)
- Synthetic data and self-improvement for LLMs / [Self-evolving LLM agents](https://mlsanity.com/synth/self-evolving-llm-agents/)

## Builds on (most cited first, 30 of 42)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](https://mlsanity.com/paper/2006.16241/) (2020)
- [Theoretically Principled Trade-off between Robustness and Accuracy](https://mlsanity.com/paper/1901.08573/) (2019)
- [Meta-Learning in Neural Networks: A Survey](https://mlsanity.com/paper/2004.05439/) (2020)
- [MnasNet: Platform-Aware Neural Architecture Search for Mobile](https://mlsanity.com/paper/1807.11626/) (2018)
- [DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs](https://mlsanity.com/paper/1903.00161/) (2019)
- [Large Language Model based Multi-Agents: A Survey of Progress and Challenges](https://mlsanity.com/paper/2402.01680/) (2024)
- [Fast is better than free: Revisiting adversarial training](https://mlsanity.com/paper/2001.03994/) (2020)
- [A Comprehensive Overview of Large Language Models](https://mlsanity.com/paper/2307.06435/) (2023)
- [Multi-Agent Collaboration Mechanisms: A Survey of LLMs](https://mlsanity.com/paper/2501.06322/) (2025)
- [The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search](https://mlsanity.com/paper/2504.08066/) (2025)
- [Automated Design of Agentic Systems](https://mlsanity.com/paper/2408.08435/) (2024)
- [Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine](https://mlsanity.com/paper/2311.16452/) (2023)
- [Recent Advances in Adversarial Training for Adversarial Robustness](https://mlsanity.com/paper/2102.01356/) (2021)
- [Meta-Learning: A Survey](https://mlsanity.com/paper/1810.03548/) (2018)
- [Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration](https://mlsanity.com/paper/2307.05300/) (2023)
- [Fixing Data Augmentation to Improve Adversarial Robustness](https://mlsanity.com/paper/2103.01946/) (2021)
- [On the Convergence and Robustness of Adversarial Training](https://mlsanity.com/paper/2112.08304/) (2021)
- [AgentGym: Evolving Large Language Model-based Agents across Diverse Environments](https://mlsanity.com/paper/2406.04151/) (2024)
- [EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms](https://mlsanity.com/paper/2406.14228/) (2024)
- [Multi-Agent Collaboration via Evolving Orchestration](https://mlsanity.com/paper/2505.19591/) (2025)
- [Symbolic Learning Enables Self-Evolving Agents](https://mlsanity.com/paper/2406.18532/) (2024)
- [A Survey of Deep Meta-Learning](https://mlsanity.com/paper/2010.03522/) (2020)

## Built on by (most cited first, 4 of 4)

- [Aligning Agentic World Models via Knowledgeable Experience Learning](https://mlsanity.com/paper/2601.13247/) (2026)
- [AWCP: A Workspace Delegation Protocol for Deep-Engagement Collaboration across Remote Agents](https://mlsanity.com/paper/2602.20493/) (2026)
- [MAGE: Multi-Agent Self-Evolution with Co-Evolutionary Knowledge Graphs](https://mlsanity.com/paper/2605.10064/) (2026)
- [Project Synapse: A Hierarchical Multi-Agent Framework with Hybrid Memory for Autonomous Resolution of Last-Mile Delivery Disruptions](https://mlsanity.com/paper/2601.08156/) (2026)

## 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.