HyEvo: Self-Evolving Hybrid Agentic Workflows for Efficient Reasoning

Computer Science > Artificial Intelligence [Submitted on 20 Mar 2026] HyEvo: Self-Evolving Hybrid Agentic Workflows for Efficient Reasoning Beibei Xu, Yutong Ye, Chuyun Shen, Yingbo Zhou, Cheng Chen, Mingsong Chen 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. Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2603.19639 [cs.AI]   (or arXiv:2603.19639v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2603.19639 Focus to learn more Submission history From: Beibei Xu [view email] [v1] Fri, 20 Mar 2026 04:45:21 UTC (2,850 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-03 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)