Polymath: A Self-Optimizing Agent with Dynamic Hierarchical Workflow

• URL: http://arxiv.org/abs/2508.02959v2
• Date: Thu, 07 Aug 2025 01:30:51 GMT
• Title: Polymath: A Self-Optimizing Agent with Dynamic Hierarchical Workflow
• Authors: Chia-Tung Ho, Jing Gong, Xufeng Yao, Yunsheng Bai, Abhishek B Akkur, Haoxing Ren,
• Abstract summary: Large language models (LLMs) excel at solving complex tasks by executing agentic composed of detailed instructions and structured operations.<n>Many researchers have sought to automate the generation and optimization of these through code-based representations.<n>Existing methods often rely on labeled datasets to train and optimize, making them ineffective and inflexible for solving real-world, dynamic problems.
• Score: 6.636150750052998
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) excel at solving complex tasks by executing agentic workflows composed of detailed instructions and structured operations. Yet, building general-purpose agents by manually embedding foundation models into agentic systems such as Chain-of-Thought, Self-Reflection, and ReACT through text interfaces limits scalability and efficiency. Recently, many researchers have sought to automate the generation and optimization of these workflows through code-based representations. However, existing methods often rely on labeled datasets to train and optimize workflows, making them ineffective and inflexible for solving real-world, dynamic problems where labeled data is unavailable. To address this challenge, we introduce Polymath, a self-optimizing agent with dynamic hierarchical workflow that leverages the flexibility of task flow graphs and the expressiveness of code-represented workflows to solve a wide range of real-world, dynamic problems. The proposed optimization methodology integrates multi-grid-inspired graph optimization with a self-reflection-guided evolutionary algorithm to refine workflows without labeled data. Experimental results on six benchmark datasets across coding, math, and multi-turn QA tasks show that Polymath achieves 8.1% average improvement over state-of-the-art baselines.

Related papers

• LAM SIMULATOR: Advancing Data Generation for Large Action Model Training via Online Exploration and Trajectory Feedback [121.78866929908871]
  Large Action Models (LAMs) for AI Agents offer incredible potential but face challenges due to the need for high-quality training data.<n>We present LAM SIMULATOR, a comprehensive framework designed for online exploration of agentic tasks with high-quality feedback.<n>Our framework features a dynamic task query generator, an extensive collection of tools, and an interactive environment where Large Language Model (LLM) Agents can call tools and receive real-time feedback.
  arXiv  Detail & Related papers  (2025-06-02T22:36:02Z)
• SEW: Self-Evolving Agentic Workflows for Automated Code Generation [24.16770109875788]
  We propose textbfSelf-textbfEvolving textbfWork (textbfSEW), a novel framework that automatically generates and optimises multi-agentflow.<n>Our SEW can automatically design agentic and optimise them through self-evolution, bringing up to 33% improvement on LiveCodeBench.
  arXiv  Detail & Related papers  (2025-05-24T11:12:14Z)
• MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering [57.156093929365255]
  Gym-style framework for systematically reinforcement learning, evaluating, and improving autonomous large language model (LLM) agents.<n>MLE-Dojo covers diverse, open-ended MLE tasks carefully curated to reflect realistic engineering scenarios.<n>Its fully executable environment supports comprehensive agent training via both supervised fine-tuning and reinforcement learning.
  arXiv  Detail & Related papers  (2025-05-12T17:35:43Z)
• GNNs as Predictors of Agentic Workflow Performances [48.34485750450876]
  Agentic invoked by Large Language Models (LLMs) have achieved remarkable success in handling complex tasks.<n>This paper formulates agentic as computational graphs and advocates Graph Neural Networks (GNNs) as efficient predictors of agentic performances.<n>We construct FLORA-Bench, a unified platform for benchmarking GNNs for predicting agentic workflow performances.
  arXiv  Detail & Related papers  (2025-03-14T11:11:00Z)
• Flow: Modularized Agentic Workflow Automation [53.073598156915615]
  Multi-agent frameworks powered by large language models (LLMs) have demonstrated great success in automated planning and task execution.<n>However, the effective adjustment of agentic during execution has not been well studied.<n>In this paper, we define an activity-on-vertex (AOV) graph, which allows continuous workflow refinement by agents.<n>Our proposed multi-agent framework achieves efficient concurrent execution of subtasks, effective goal achievement, and enhanced error tolerance.
  arXiv  Detail & Related papers  (2025-01-14T04:35:37Z)
• AFlow: Automating Agentic Workflow Generation [36.61172223528231]
  Large language models (LLMs) have demonstrated remarkable potential in solving complex tasks across diverse domains.<n>We introduce AFlow, an automated framework that efficiently explores this space using Monte Carlo Tree Search.<n> Empirical evaluations across six benchmark datasets demonstrate AFlow's efficacy, yielding a 5.7% average improvement over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2024-10-14T17:40:40Z)
• Benchmarking Agentic Workflow Generation [80.74757493266057]
  We introduce WorfBench, a unified workflow generation benchmark with multi-faceted scenarios and intricate graph workflow structures.<n>We also present WorfEval, a systemic evaluation protocol utilizing subsequence and subgraph matching algorithms.<n>We observe that the generated can enhance downstream tasks, enabling them to achieve superior performance with less time during inference.
  arXiv  Detail & Related papers  (2024-10-10T12:41:19Z)
• AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoning [93.96463520716759]
  Large language model (LLM) agents have demonstrated impressive capabilities in utilizing external tools and knowledge to boost accuracy and hallucinations. Here, we introduce AvaTaR, a novel and automated framework that optimize an LLM agent to effectively leverage provided tools, improving performance on a given task.
  arXiv  Detail & Related papers  (2024-06-17T04:20:02Z)
• Language Agents as Optimizable Graphs [31.220547147952278]
  We describe Large Language Models (LLMs)-based agents as computational graphs. Our framework can be used to efficiently develop, integrate, and automatically improve various LLM agents.
  arXiv  Detail & Related papers  (2024-02-26T18:48:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.