Overview

Iterative refinement studies how a model can improve a solution over multiple steps instead of producing it in one pass, which can help resolve errors and use additional computation at inference time. Common approaches include recurrent or weight-shared networks, residual and multiscale correction, diffusion or flow-based updates, and generate–evaluate–revise loops with external feedback. These methods appear in reasoning, image generation and segmentation, 3D reconstruction, scientific simulation, and inverse problems, and are evaluated on tasks ranging from Sudoku and image benchmarks to turbulent-flow reconstruction. A central tension is that more steps can improve accuracy or detail, but add cost and do not guarantee progress: results depend on whether the feedback reliably identifies errors and whether simpler one-shot methods are already sufficient.

Latest papers

CardsList

54 papers5 papers in the last four weeks, down 17% on the four weeks before. 0.0% of all new papers.

  1. Proximal Targets: Training Looped Refiners on Problems with Many Correct Answers

    Nov 17, 2026Syed Affan DaimiIterative RefinementConstraint Satisfaction

  2. Just Image Transformers with Late-Stage Pixel Refinement

    Nov 9, 2026Denis Lukovnikov, Andreas Müller, Asja FischerDiffusion-Based Image GenerationDiffusion Transformer

  3. Evolving Explanations: Complexity-Adaptive Refinement of Faithful Explanations for Symbolic Regression

    Nov 2, 2026Elisabeth Mayrhuber, Ting Hu, Stephan WinklerExplainable Artificial IntelligenceFaithfulness of Language Model Explanations

  4. MedPAO-VL: Interpretable and Protocol-Compliant Agent for Structured Radiology Report Generation

    Oct 15, 2026Shrish Shrinath Vaidya, Gowthamaan Palani, Minmini Selvam +2Radiology Report GenerationVLM Hallucination Mitigation

  5. Making Language the Low-Rate Code of Vision: Successive Refinement from Words to Pixels

    Oct 12, 2026Ruilin Gong, Hao GongT2I GenerationImage Tokenization

  6. Scaling RNA Foundation Models through Iterative Refinement

    Oct 9, 2026Pengan Chen, Liang Hong, Xinyuan Liu +6Iterative Refinement

  7. Few-Step Generation via Data-Space Iteration

    Oct 8, 2026Shanchuan Lin, Yansong Peng, Fu-Yun Wang +1Iterative RefinementFlow-Based Generative Modeling

  8. Learning from Evolving Errors: Adaptive Iterative Repair for On-Policy Distillation

    Oct 2, 2026Rui Li, Liyang He, Zheng Zhang +3On-Policy Self-DistillationOn-Policy Distillation

  9. Iterative Atom Refinement: A Monotonicity Principle for Dictionary Learning

    Sep 20, 2026Alexander Christie, Miguel Moscoso, Alexei Novikov +2Sparse RecoveryDictionary Learning

  10. Evolving Error States: Failure-Aware Progressive Repair for Ultrasound Lesion Segmentation

    Sep 16, 2026Ziliang Wang, XuJiang Tang, Lu Yuting +4Medical Image SegmentationUltrasound Image Segmentation

  11. UnitBoost: Managing Compound LLM Systems with a Merge Operator, Not a Model

    Sep 9, 2026Xing Zhang, Guanghui Wang, Yanwei Cui +2Multi-Agent System OptimizationLLM Agent Orchestration

  12. PragAlign: Feedback-Guided Pragmatic Alignment for Controlled Synthetic Dialogue Generation

    Sep 2, 2026Smitha Muthya Sudheendra, Jaideep SrivastavaText GenerationControllable Text Generation

  13. Evaluating Constrained Iterative Refinement for Scalable Vector Graphics Generation with Off-the-Shelf VLMs

    Aug 26, 2026Matthew Perlman, James Beetham, Niels Da Vitoria Lobo +2Vector Graphics GenerationVLM Adaptation

  14. Diagnosing and narrowing the simulation-to-real gap in powder X-ray diffraction with a wet-dry agentic loop

    Aug 23, 2026Shaoguang Wang, Weiyu Guo, Ben Fei +3Synthetic-to-Real Domain AdaptationMaterials Science

  15. SolarFlowRefiner: Refinement-Aware Flow Matching for Surface Solar Radiation Downscaling

    Aug 21, 2026Udbhav Srivastava, Antonita Racheal, Yiheng Chen +2Iterative RefinementClimate Downscaling

  16. Iterative Refinement Diffusion for Super-Resolved Data Assimilation of Multiscale Physical Systems

    Aug 13, 2026Mrigank Dhingra, Ramchandran Muthukumar, Rebecca Willett +1Data AssimilationIterative Refinement

  17. ODE-Based Transformer Decoders for Iterative Sign Language Translation

    Aug 11, 2026Tuğçe Kızıltepe, Hacer Yalim KelesSign Language TranslationIterative Refinement

  18. ReflexTrack: A Feedback-Driven Agent for Training-Free Referring Video Object Segmentation

    Jul 27, 2026Yuanjia Li, Tianyang Xu, Tao Zhou +3Video Object SegmentationReferring Video Object Segmentation

  19. Exact ReLU realization of affine one-dimensional refinement iterates via residual memory and offset frames

    Jul 22, 2026Boldsaikhan Bolorkhuu, Tsogtgerel GantumurReLU Neural NetworksIterative Refinement

  20. Neural network realization of binary refinement iterates via a two-chart atlas selector

    Jul 21, 2026Tsogtgerel GantumurReLU Neural NetworksNeural Network Approximation Theory

  21. RecRec: Recursive Refinement for Sequential Recommendation

    Jul 12, 2026Pervez Shaik, Prosenjit Biswas, Abhinav Thorat +2Sequential RecommendationIterative Refinement

  22. Lightweight Polyp Segmentation via a Gain-Aware Prediction-Space Recursive Controller

    Jul 3, 2026Jiachi Zhang, Zhuoyu Wu, Quanjun Wang +2Polyp SegmentationMedical Image Segmentation

  23. Flow Reasoning Models: Turning Flows Into Efficient Recurrent Reasoners

    Jun 28, 2026Alec Helbling, Andrey Bryutkin, Mauro Martino +3Self-ConditioningStructured Reasoning