OctoT2I: A Self-Evolving Agentic Text-to-Image Router
2026-06-01 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors address problems in current Text-to-Image (T2I) systems that use multiple models but rely on manual settings and are slow. They present OctoT2I, a new framework that smarter chooses tools by learning from experience without needing human help. OctoT2I builds a knowledge base using a loop that proposes, solves, evaluates, and learns to improve over time. Their tests show OctoT2I achieves good image generation quality while being much faster and more energy-efficient than top existing methods.
Text-to-Image modelsAgentic methodsInference efficiencyMulti-round routingSelf-evolving mechanismConceptual dimensionsPropose-Solve-Evaluate-Learn loopKnowledge basePerformance optimizationEnergy efficiency
Authors
Xu Jiang, Bin Chen, Gehui Li, Yule Duan, Ronggang Wang, Jian Zhang
Abstract
The explosive growth of Text-to-Image (T2I) models, from large-scale versions to lightweight, real-time ones, now faces diminishing marginal returns from single-model scaling. Agentic T2I methods emerged to alleviate this bottleneck by using multiple models. However, existing agentic T2I methods suffer from three key challenges: reliance on expensive handcrafted priors or human annotations, rigid single-path decision mechanisms, and a neglect of inference efficiency. To address these challenges, we introduce OctoT2I, a novel agentic framework that reformulates the T2I task as a joint optimization of generation quality and inference efficiency. OctoT2I implements a stateful, multi-round routing strategy that adaptively selects the most suitable tool based on its knowledge and memory. This strategy is enabled by a knowledge base built from scratch by our novel Self-Evolving Mechanism. This mechanism, which requires no human supervision, first autonomously defines foundational Conceptual Dimensions (eg, style, color, count) and then intelligently explores their combinations via an iterative" Propose--Solve--Evaluate--Learn"(PSEL) loop. The PSEL loop efficiently discovers each tool's capability frontier, driving continuous improvement without external guidance. Extensive experiments demonstrate that OctoT2I achieves competitive performance (0.96) on GenEval while delivering a 90.3% inference speedup and a 56.6% energy-efficiency gain over the leading baseline (Flow-GRPO), striking an exceptional balance between performance and efficiency. Code and models will be made available.