HiVA: Self-organized Hierarchical Variable Agent via Goal-driven Semantic-Topological Evolution
By: Jinzhou Tang , Jusheng Zhang , Qinhan Lv and more
Potential Business Impact:
Helps AI agents learn and solve problems better.
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&A, 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.
Similar Papers
Hi-Agent: Hierarchical Vision-Language Agents for Mobile Device Control
Artificial Intelligence
Helps phones learn to do tasks by themselves.
Designing Domain-Specific Agents via Hierarchical Task Abstraction Mechanism
Artificial Intelligence
Helps AI solve hard science problems step-by-step.
Beyond Shortest Path: Agentic Vehicular Routing with Semantic Context
Artificial Intelligence
Helps cars plan routes using your specific needs.