OctoT2I：一种自进化的智能体文本到图像路由器
OctoT2I: A Self-Evolving Agentic Text-to-Image Router
提出一种无需人工标注的自进化路由框架，通过PSEL循环自动发现各T2I模型的能力边界，实现质量与效率的联合优化；其知识库构建和路由策略可复用于多模型集成、模型选择等视觉生成任务。
原文依据 OctoT2I implements a stateful, multi-round routing strategy that adaptively selects the most suitable tool based on its knowledge and memory.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论文本到图像（T2I）模型的爆炸式增长，从大规模版本到轻量级实时版本，如今正面临单模型扩展带来的边际收益递减。智能体T2I方法应运而生，通过使用多个模型来缓解这一瓶颈。然而，现有的智能体T2I方法面临三个关键挑战：依赖昂贵的手工先验或人工标注、僵化的单路径决策机制，以及对推理效率的忽视。为应对这些挑战，我们提出了OctoT2I，一种新颖的智能体框架，将T2I任务重新表述为生成质量与推理效率的联合优化。OctoT2I实现了一种有状态的多轮路由策略，根据其知识和记忆自适应地选择最合适的工具。该策略由我们新颖的自进化机制从零构建的知识库所支持。该机制无需人工监督，首先自主定义基础概念维度（例如风格、颜色、数量），然后通过迭代的“提议—求解—评估—学习”（PSEL）循环智能地探索它们的组合。PSEL循环高效地发现每个工具的能力边界，在无外部指导的情况下驱动持续改进。大量实验表明，OctoT2I在GenEval上取得了有竞争力的性能（0.96），同时相比领先的基线（Flow-GRPO）实现了90.3%的推理加速和56.6%的能效提升，在性能与效率之间取得了卓越的平衡。代码和模型将公开。
英文原文摘要 1603 字符
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 (e.g., 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.