Generation Navigator: A State-Aware Agentic Framework for Image Generation

• URL: http://arxiv.org/abs/2605.17969v1
• Date: Mon, 18 May 2026 07:26:45 GMT
• Title: Generation Navigator: A State-Aware Agentic Framework for Image Generation
• Abstract summary: Existing systems rely on either simple prompt rewriting or closed-loop agents driven by hand-crafted rules.<n>We propose Generation Navigator, a multi-turn T2I agent that learns to dynamically steer the generation trajectory and output the next action.<n>We resolve this with PRE-GRPO, a trajectory-level reinforcement learning objective that explicitly rewards discovering a high-quality image.
• Score: 27.152909600620095
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite rapid advances in text-to-image generation, faithfully realizing user intent remains challenging, often requiring manual multi-turn trial and error. To automate this process, existing systems rely on either simple prompt rewriting or closed-loop agents driven by hand-crafted rules, rather than learning to adapt actions to the evolving generation process. In this paper, we reformulate image generation as a state-conditioned action-making problem and propose Generation Navigator, a multi-turn T2I agent that learns to dynamically steer the generation trajectory and output the next action. However, training this agent via reinforcement learning introduces a critical credit assignment challenge: naively rewarding a trajectory based solely on a single state assigns equal credit to all actions in the rollout, ignores the quality dynamics across turns, and fails to distinguish actions that improve the trajectory from those that degrade it or waste turns without progress. We resolve this with PRE-GRPO (Peak-Retention-Efficiency Group Relative Policy Optimization), a trajectory-level reinforcement learning objective that explicitly rewards discovering a high-quality image (Peak), avoiding subsequent quality degradation across turns (Retention), and minimizing unnecessary turns (Efficiency). Experiments show substantial improvements across benchmarks, reaching a WISE score of 0.90 and 79.06% reasoning accuracy on T2I-ReasonBench.

Related papers

• HarnessEvolve: Learning from Reference Trajectories for Reliable Agent Self-Evolution [11.431479238875712]
  We introduce HarnessEvolve, a self-evolving framework that learns from reference trajectories to achieve reliable agent self-evolution.<n>We conduct extensive experiments on several benchmarks spanning open-domain and enterprise scenarios, using different models and agent frameworks.<n>Results demonstrate that HarnessEvolve consistently outperforms state-of-the-art baselines across all benchmarks and settings.
  arXiv  Detail & Related papers  (2026-09-01T07:31:18Z)
• High-Fidelity Two-Step Image Generation via Teacher-Aligned End-to-End Distillation [66.19462276967869]
  Few-step diffusion distillation has become increasingly mature for 4-8-step generation, yet pushing further to 2 steps remains challenging.<n>We introduce Z-Image Turbo++, a high-quality 2-step image generation model distilled from the 8-step Z-Image Turbo teacher.
  arXiv  Detail & Related papers  (2026-06-10T18:24:50Z)
• HERO: Hindsight-Enhanced Reflection from Environment Observations for Agentic Self-Distillation [50.53459634301361]
  HERO is a hindsight-enhanced self-distillation framework that uses next environment observations as locally aligned feedback.<n> HERO improves task success and reduces unnecessary turns over environment-feedback-only self-distillation and GRPO.
  arXiv  Detail & Related papers  (2026-06-10T01:35:34Z)
• CASCADE: Context-Aware Relaxation for Speculative Image Decoding [9.004650208708235]
  Autoregressive generation is a powerful approach for high-fidelity image synthesis.<n>Current approaches fail to achieve efficiency gains comparable to those observed in text generation.<n>We identify previously overlooked patterns in the target model's behavior that emerge naturally in tree-based speculative decoding.
  arXiv  Detail & Related papers  (2026-05-08T04:32:17Z)
• Q-DeepSight: Incentivizing Thinking with Images for Image Quality Assessment and Refinement [58.15004031934379]
  We propose Q-DeepSight, a think-with-image framework that emulates this human-like process.<n>Q-DeepSight achieves state-of-the-art performance across diverse benchmarks, including natural, restored, and AI-generated content.<n>We demonstrate its practical value with Perceptual-in-Generation (PiG), a training-free framework where Q-DeepSight's diagnoses guide iterative image enhancement.
  arXiv  Detail & Related papers  (2026-04-18T06:10:57Z)
• UI-Voyager: A Self-Evolving GUI Agent Learning via Failed Experience [56.50613398808361]
  We propose a novel two-stage self-evolving mobile GUI agent.<n>In the first stage, we employ Rejection Fine-Tuning (RFT), which enables the continuous co-evolution of data and models in a fully autonomous loop.<n>The second stage introduces Group Relative Self-Distillation (GRSD), which identifies critical fork points in group rollouts and constructs dense step-level supervision from successful trajectories to correct failed ones.
  arXiv  Detail & Related papers  (2026-03-25T17:10:29Z)
• See, Plan, Rewind: Progress-Aware Vision-Language-Action Models for Robust Robotic Manipulation [59.07792608884117]
  We introduce See, Plan, Rewind (SPR), a progress-aware vision-language-action framework.<n>SPR operates through a continuous core cycle, Seeing the current state and upcoming milestone, Planning a trajectory towards the next 2D waypoint, and Rewinding to a recoverable state upon failure.<n>SPR achieves state-of-the-art robustness with the smallest performance drop, surpassing OpenVLA-OFT and UniVLA.
  arXiv  Detail & Related papers  (2026-03-10T07:22:51Z)
• Supervised Contrastive Learning for Few-Shot AI-Generated Image Detection and Attribution [3.103291412074661]
  This work proposes a novel two-stage detection framework to address the generalization challenge inherent in synthetic image detection.<n>The proposed framework achieves an average detection accuracy of 91.3%, representing a 5.2 percentage point improvement over existing approaches.
  arXiv  Detail & Related papers  (2025-11-20T16:53:24Z)
• STAGE: Stable and Generalizable GRPO for Autoregressive Image Generation [16.40446848402754]
  Reinforcement learning has recently been explored to improve text-to-image generation.<n>Applying existing GRPO algorithms to autoregressive (AR) image models remains challenging.<n>In this work, we revisit GRPO for AR image generation and identify two key issues: contradictory gradients from unnecessary tokens and unstable policy entropy dynamics.
  arXiv  Detail & Related papers  (2025-09-29T16:50:21Z)
• Understand Before You Generate: Self-Guided Training for Autoregressive Image Generation [110.03631978640298]
  We present the first systematic investigation into the mechanisms of applying the next-token prediction paradigm to the visual domain.<n>We identify three key properties that hinder the learning of high-level visual semantics.<n>We show that these issues can be effectively addressed by introducing self-supervised objectives during training.
  arXiv  Detail & Related papers  (2025-09-18T17:47:40Z)
• Reward Incremental Learning in Text-to-Image Generation [26.64026346266299]
  We present Reward Incremental Distillation (RID), a method that mitigates forgetting with minimal computational overhead. The experimental results demonstrate the efficacy of RID in achieving consistent, high-quality gradient generation in RIL scenarios.
  arXiv  Detail & Related papers  (2024-11-26T10:54:33Z)
• Towards Deviation-Robust Agent Navigation via Perturbation-Aware Contrastive Learning [125.61772424068903]
  Vision-and-language navigation (VLN) asks an agent to follow a given language instruction to navigate through a real 3D environment. We present a model-agnostic training paradigm, called Progressive Perturbation-aware Contrastive Learning (PROPER) to enhance the generalization ability of existing VLN agents.
  arXiv  Detail & Related papers  (2024-03-09T02:34:13Z)
• P2DT: Mitigating Forgetting in task-incremental Learning with progressive prompt Decision Transformer [49.716834343064015]
  Catastrophic forgetting poses a substantial challenge for managing intelligent agents controlled by a large model.<n>We propose a novel solution - the Progressive Prompt Decision Transformer (P2DT)<n>This method enhances a transformer-based model by dynamically appending decision tokens during new task training, thus fostering task-specific policies.
  arXiv  Detail & Related papers  (2024-01-22T02:58:53Z)

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.