Model Releases
APT: Feedback-Driven Agentic Post-Training for Text-to-Image Generation
arXiv:2610.18097v1 Announce Type: new Abstract: Post-training is crucial for improving text-to-image models, yet existing pipelines typically rely on manually curated training data and fixed training
arXiv:2610.18097v1 Announce Type: new Abstract: Post-training is crucial for improving text-to-image models, yet existing pipelines typically rely on manually curated training data and fixed training distributions. We introduce APT (Agentic Post-Training), a fully automated framework that adaptively post-trains a base model according to its evolving capability profile. APT coordinates three agents to construct evaluation sets from user requirements, diagnose model-specific strengths and failure modes, and generate reinforcement learning data with an adaptive prompt distribution that emphasizes underperforming capabilities. By repeatedly evaluating, diagnosing, and updating the generator, APT lets the current model's behavior shape its next training tasks, forming a feedback loop inspired by recursive self-improvement. For general-purpose settings without user-specified evaluation scenarios, we further develop an evaluation harness that enables broad and diverse evaluation set generation. Experiments across multiple base models, benchmarks, and generation architectures demonstrate that APT is model-agnostic, benchmark-agnostic, architecture-agnostic, and fully automated.
Related
- RankE: End-to-End Post-Training for Discrete Text-to-Image Generation with Decoder Co-Evolution
- Ask, Solve, Generate: Self-Evolving Unified Multimodal Understanding and Generation via Self-Consistency Rewards
- Unified Text-Image Generation with Weakness-Targeted Post-Training
Source: arXiv cs.CV | 2026-10-14