InterleaveThinker: Reinforcing Agentic Interleaved Generation

• URL: http://arxiv.org/abs/2606.13679v2
• Date: Fri, 12 Jun 2026 06:34:25 GMT
• Title: InterleaveThinker: Reinforcing Agentic Interleaved Generation
• Abstract summary: We introduce InterleaveThinker, the first multi-agent pipeline designed to endow any existing image generator with interleaved generation capabilities.<n>Specifically, we employ a planner agent to organize the image-text input sequence, instructing the image generator on the required execution at each step.<n>Subsequently, we introduce a critic agent to evaluate the generator's outputs, identify samples that deviate from the planned instructions, and refine the instructions for regeneration.
• Score: 37.528182608182554
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent image generators have demonstrated impressive photorealism and instruction-following capabilities in single-image generation and editing. However, constrained by their architectures, they cannot achieve interleaved generation (text-image sequence), which has crucial applications in visual narratives, guidance, and embodied manipulation. Even the latest open-source Unified Multimodal Models (UMMs) exhibit limited performance in this regard. In this paper, we introduce InterleaveThinker, the first multi-agent pipeline designed to endow any existing image generator with interleaved generation capabilities. Specifically, we employ a planner agent to organize the image-text input sequence, instructing the image generator on the required execution at each step. Subsequently, we introduce a critic agent to evaluate the generator's outputs, identify samples that deviate from the planned instructions, and refine the instructions for regeneration. To implement this pipeline, we construct the Interleave-Planner-SFT-80k and Interleave-Critic-SFT-112k to perform a format cold-start. Then we develop Interleave-Critic-RL-13k to reinforce the step-wise instruction correction capability within a generation trajectory using GRPO. Since a single interleaved generation trajectory may involve over 25 generator calls, optimizing the entire trajectory is computationally impractical. Therefore, we propose accuracy reward and step-wise reward, allowing single-step RL to effectively guide the entire generation trajectory. The results show that InterleaveThinker improves performance across various image generators. On interleaved generation benchmarks, it achieves performance comparable to Nano Banana and GPT-5. Surprisingly, it also significantly enhances the base model on reasoning-based benchmarks; for example, on 4-step FLUX.2-klein, we observe substantial gains on WISE and RISE.

Related papers

• GenRouter: Unified Workflow Routing for Agentic Image Generation [28.956890449336456]
  We present GenCanvas, the first unified workflow routing framework for agentic image generation.<n>Gen achieves superior visual alignment while reducing execution costs by over 95% and by 65% compared to heavyweight pipelines.<n>The system continuously self-evolves via accumulated experience, enabling robust zero-shot generalizations that boosts performance and halves computational overhead.
  arXiv  Detail & Related papers  (2026-08-17T15:36:45Z)
• Disentangling Generation and Regression in Stochastic Interpolants for Controllable Image Restoration [30.480465453951982]
  DiSI is a unified framework that Disentangles the Interpolant process into independent generation and regression components.<n>We show that DiSI efficiently achieves competitive results on various Image Restoration tasks, while uniquely offering the inference-time flexibility to control the distortion-perception trade-off within a single model.
  arXiv  Detail & Related papers  (2026-05-20T16:41:32Z)
• GriDiT: Factorized Grid-Based Diffusion for Efficient Long Image Sequence Generation [77.13582457917418]
  We train a generative model solely on grid images comprising subsampled frames.<n>We learn to generate image sequences, using the strong self-attention mechanism of the Diffusion Transformer (DiT) to capture correlations between frames.<n>Our method consistently outperforms SoTA in quality and inference speed (at least twice-as-fast) across datasets.
  arXiv  Detail & Related papers  (2025-12-24T16:46:04Z)
• Chain-of-Image Generation: Toward Monitorable and Controllable Image Generation [7.987662261007762]
  Chain-of-Image Generation (CoIG) framework reframes image generation as a sequential, semantic process analogous to how humans create art.<n>Our experimental results indicate that CoIG substantially enhances quantitative monitorability while achieving competitive robustness compared to established baseline models.
  arXiv  Detail & Related papers  (2025-12-09T14:35:12Z)
• Policy Optimized Text-to-Image Pipeline Design [73.9633527029941]
  We introduce a novel reinforcement learning-based framework for text-to-image generation.<n>Our approach first trains an ensemble of reward models capable of predicting image quality scores directly from prompt-workflow combinations.<n>We then implement a two-phase training strategy: initial vocabulary training followed by GRPO-based optimization.
  arXiv  Detail & Related papers  (2025-05-27T17:50:47Z)
• Iterative Flow Matching -- Path Correction and Gradual Refinement for Enhanced Generative Modeling [6.343872515377999]
  We explain and demonstrate why flow matching can generate hallucinations, and propose an iterative process to improve the generation process.<n>Our iterative process can be integrated into virtually $textitany$ generative modeling technique, thereby enhancing the performance and robustness of synthesis image systems.
  arXiv  Detail & Related papers  (2025-02-23T05:08:06Z)
• Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step [86.69947123512836]
  Chain-of-Thought (CoT) reasoning has been extensively explored in large models to tackle complex understanding tasks.<n>We provide the first comprehensive investigation of the potential of CoT reasoning to enhance autoregressive image generation.<n>We propose the Potential Assessment Reward Model (PARM) and PARM++, specialized for autoregressive image generation.
  arXiv  Detail & Related papers  (2025-01-23T18:59:43Z)
• StraIT: Non-autoregressive Generation with Stratified Image Transformer [63.158996766036736]
  Stratified Image Transformer(StraIT) is a pure non-autoregressive(NAR) generative model. Our experiments demonstrate that StraIT significantly improves NAR generation and out-performs existing DMs and AR methods.
  arXiv  Detail & Related papers  (2023-03-01T18:59:33Z)
• DynaST: Dynamic Sparse Transformer for Exemplar-Guided Image Generation [56.514462874501675]
  We propose a dynamic sparse attention based Transformer model to achieve fine-level matching with favorable efficiency. The heart of our approach is a novel dynamic-attention unit, dedicated to covering the variation on the optimal number of tokens one position should focus on. Experiments on three applications, pose-guided person image generation, edge-based face synthesis, and undistorted image style transfer, demonstrate that DynaST achieves superior performance in local details.
  arXiv  Detail & Related papers  (2022-07-13T11:12:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.