{"ID":2876882,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.00189","arxiv_id":"2509.00189","title":"HiVA: Self-organized Hierarchical Variable Agent via Goal-driven Semantic-Topological Evolution","abstract":"Autonomous agents play a crucial role in advancing Artificial General Intelligence, enabling problem decomposition and tool orchestration through Large Language Models (LLMs). However, existing paradigms face a critical trade-off. On one hand, reusable fixed workflows require manual reconfiguration upon environmental changes; on the other hand, flexible reactive loops fail to distill reasoning progress into transferable structures. We introduce Hierarchical Variable Agent (HiVA), a novel framework modeling agentic workflows as self-organized graphs with the Semantic-Topological Evolution (STEV) algorithm, which optimizes hybrid semantic-topological spaces using textual gradients as discrete-domain surrogates for backpropagation. The iterative process comprises Multi-Armed Bandit-infused forward routing, diagnostic gradient generation from environmental feedback, and coordinated updates that co-evolve individual semantics and topology for collective optimization in unknown environments. Experiments on dialogue, coding, Long-context Q\u0026A, mathematical, and agentic benchmarks demonstrate improvements of 5-10% in task accuracy and enhanced resource efficiency over existing baselines, establishing HiVA's effectiveness in autonomous task execution.","short_abstract":"Autonomous agents play a crucial role in advancing Artificial General Intelligence, enabling problem decomposition and tool orchestration through Large Language Models (LLMs). However, existing paradigms face a critical trade-off. On one hand, reusable fixed workflows require manual reconfiguration upon environmental c...","url_abs":"https://arxiv.org/abs/2509.00189","url_pdf":"https://arxiv.org/pdf/2509.00189v1","authors":"[\"Jinzhou Tang\",\"Jusheng Zhang\",\"Qinhan Lv\",\"Sidi Liu\",\"Jing Yang\",\"Chengpei Tang\",\"Keze Wang\"]","published":"2025-08-29T18:51:18Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.MA\"]","methods":"[\"Large Language Model\",\"Language Model\",\"Generative Adversarial Network\"]","has_code":false}