Paper
HyEvo: Self-Evolving Hybrid Agentic Workflows for Efficient Reasoning
Authors
Beibei Xu, Yutong Ye, Chuyun Shen, Yingbo Zhou, Cheng Chen, Mingsong Chen
Abstract
Although agentic workflows have demonstrated strong potential for solving complex tasks, existing automated generation methods remain inefficient and underperform, as they rely on predefined operator libraries and homogeneous LLM-only workflows in which all task-level computation is performed through probabilistic inference. To address these limitations, we propose HyEvo, an automated workflow-generation framework that leverages heterogeneous atomic synthesis. HyEvo integrates probabilistic LLM nodes for semantic reasoning with deterministic code nodes for rule-based execution, offloading predictable operations from LLM inference and reducing inference cost and execution latency. To efficiently navigate the hybrid search space, HyEvo employs an LLM-driven multi-island evolutionary strategy with a reflect-then-generate mechanism, iteratively refining both workflow topology and node logic via execution feedback. Comprehensive experiments show that HyEvo consistently outperforms existing methods across diverse reasoning and coding benchmarks, while reducing inference cost and execution latency by up to 19$\times$ and 16$\times$, respectively, compared to the state-of-the-art open-source baseline.
Metadata
Related papers
Vibe Coding XR: Accelerating AI + XR Prototyping with XR Blocks and Gemini
Ruofei Du, Benjamin Hersh, David Li, Nels Numan, Xun Qian, Yanhe Chen, Zhongy... • 2026-03-25
Comparing Developer and LLM Biases in Code Evaluation
Aditya Mittal, Ryan Shar, Zichu Wu, Shyam Agarwal, Tongshuang Wu, Chris Donah... • 2026-03-25
The Stochastic Gap: A Markovian Framework for Pre-Deployment Reliability and Oversight-Cost Auditing in Agentic Artificial Intelligence
Biplab Pal, Santanu Bhattacharya • 2026-03-25
Retrieval Improvements Do Not Guarantee Better Answers: A Study of RAG for AI Policy QA
Saahil Mathur, Ryan David Rittner, Vedant Ajit Thakur, Daniel Stuart Schiff, ... • 2026-03-25
MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucination
Zhuo Li, Yupeng Zhang, Pengyu Cheng, Jiajun Song, Mengyu Zhou, Hao Li, Shujie... • 2026-03-25
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2603.19639v1</id>\n <title>HyEvo: Self-Evolving Hybrid Agentic Workflows for Efficient Reasoning</title>\n <updated>2026-03-20T04:45:21Z</updated>\n <link href='https://arxiv.org/abs/2603.19639v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2603.19639v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>Although agentic workflows have demonstrated strong potential for solving complex tasks, existing automated generation methods remain inefficient and underperform, as they rely on predefined operator libraries and homogeneous LLM-only workflows in which all task-level computation is performed through probabilistic inference. To address these limitations, we propose HyEvo, an automated workflow-generation framework that leverages heterogeneous atomic synthesis. HyEvo integrates probabilistic LLM nodes for semantic reasoning with deterministic code nodes for rule-based execution, offloading predictable operations from LLM inference and reducing inference cost and execution latency. To efficiently navigate the hybrid search space, HyEvo employs an LLM-driven multi-island evolutionary strategy with a reflect-then-generate mechanism, iteratively refining both workflow topology and node logic via execution feedback. Comprehensive experiments show that HyEvo consistently outperforms existing methods across diverse reasoning and coding benchmarks, while reducing inference cost and execution latency by up to 19$\\times$ and 16$\\times$, respectively, compared to the state-of-the-art open-source baseline.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n <published>2026-03-20T04:45:21Z</published>\n <arxiv:primary_category term='cs.AI'/>\n <author>\n <name>Beibei Xu</name>\n </author>\n <author>\n <name>Yutong Ye</name>\n </author>\n <author>\n <name>Chuyun Shen</name>\n </author>\n <author>\n <name>Yingbo Zhou</name>\n </author>\n <author>\n <name>Cheng Chen</name>\n </author>\n <author>\n <name>Mingsong Chen</name>\n </author>\n </entry>"
}