mlsanityData to 14 Oct 2026

Re3Cap: Retrieval-Guided Refinement for Image Captioning Enhancement via Reinforcement Learning

arXiv 2608.21305 ↗First posted 21 Aug 2026cs.CV cs.AIcited by 0

On the map: LLM reasoning → Multimodal reasoning

also in 1 more
Abstract (arXiv)

Reinforcement Learning (RL) has demonstrated significant gains in image captioning, yet it is still limited in encouraging Large Vision-Language Models (LVLMs) to explore novel reasoning strategies. This limitation leads to a performance gap between RL and Supervised Fine-Tuning (SFT). In this paper, we argue that multi-modal retrieval can serve as an effective reasoning signal for caption refinement. Based on this insight, we present the Retrieval-Guided Refinement for Image Captioning (Re3Cap), a retrieval-guided reasoning strategy that enhances image captioning without requiring additional annotations. Instantiated by Caption Refinement Suggester (CRS) and Caption Quality Assessor (CQA), this strategy identifies hallucinations and omissions in image captions, leading to more accurate and detailed descriptions. Extensive experiments demonstrate the superiority of our method in image captioning, even compared with Supervised Fine-Tuning. Especially, Re3Cap outperforms GRPO with an average improvement of 8.64% in relation reasoning on the COCO-LN500 benchmark.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Multimodal reasoning, one of 17 directions in LLM reasoning. Builds on 49 of its 61 references that are in the map. First posted on arXiv 21 Aug 2026.

Builds on

49 of 61 references.

Closest ancestors · 2

Same direction, newest first

  1. 2026Seeing with You: Perception-Reasoning Coevolution for Multimodal Reasoning30 Mar
  2. 2024Diagnosing the Compositional Knowledge of Vision Language Models from a Game-Theoretic View27 May

Other references · 47

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  4. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  5. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  6. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,876
  7. 2024HybridFlow: A Flexible and Efficient RLHF Frameworkcited by 2,057
  8. 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,463
  9. 2022Reproducible scaling laws for contrastive language-image learningcited by 1,173
  10. 2023mPLUG-Owl: Modularization Empowers Large Language Models with Multimodalitycited by 1,040
  11. 2023ShareGPT4V: Improving Large Multi-Modal Models with Better Captionscited by 1,005
  12. 2025Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?cited by 982
35 more
  1. 2020MPNet: Masked and Permuted Pre-training for Language Understandingcited by 981
  2. 2014Deep Visual-Semantic Alignments for Generating Image Descriptionscited by 968
  3. 2014Show and Tell: A Neural Image Caption Generatorcited by 879
  4. 2023Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decodingcited by 688
  5. 2021ClipCap: CLIP Prefix for Image Captioningcited by 559
  6. 2022GIT: A Generative Image-to-text Transformer for Vision and Languagecited by 537
  7. 2024InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Modelcited by 326
  8. 2019Attention on Attention for Image Captioningcited by 289
  9. 2019Connecting Vision and Language with Localized Narrativescited by 226
  10. 2024OmniMedVQA: A New Large-Scale Comprehensive Evaluation Benchmark for Medical LVLMcited by 184
  11. 2021ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmeticcited by 150
  12. 2016Improved Image Captioning via Policy Gradient optimization of SPIDErcited by 113
  13. 2025Pass@K Policy Optimization: Solving Harder Reinforcement Learning Problemscited by 87
  14. 2022SmallCap: Lightweight Image Captioning Prompted with Retrieval Augmentationcited by 82
  15. 2018Unsupervised Image Captioningcited by 79
  16. 2024DenseFusion-1M: Merging Vision Experts for Comprehensive Multimodal Perceptioncited by 73
  17. 2024CogView3: Finer and Faster Text-to-Image Generation via Relay Diffusioncited by 72
  18. 2022Fine-grained Image Captioning with CLIP Rewardcited by 69
  19. 2025CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learningcited by 38
  20. 2018Show, Tell and Discriminate: Image Captioning by Self-retrieval with Partially Labeled Datacited by 37
  21. 2016Attention Correctness in Neural Image Captioningcited by 35
  22. 2021Batch size-invariance for policy optimizationcited by 35
  23. 2023Transferable Decoding with Visual Entities for Zero-Shot Image Captioningcited by 34
  24. 2023EVCap: Retrieval-Augmented Image Captioning with External Visual-Name Memory for Open-World Comprehensioncited by 32
  25. 2025Cycle Consistency as Reward: Learning Image-Text Alignment without Human Preferencescited by 22
  26. 2024VLRM: Vision-Language Models act as Reward Models for Image Captioningcited by 18
  27. 2023Guiding Image Captioning Models Toward More Specific Captionscited by 17
  28. 2022I-Tuning: Tuning Frozen Language Models with Image for Lightweight Image Captioningcited by 16
  29. 2025SC-Captioner: Improving Image Captioning with Self-Correction by Reinforcement Learningcited by 16
  30. 2025The Best of N Worlds: Aligning Reinforcement Learning with Best-of-N Sampling via max@k Optimisationcited by 16
  31. 2023CgT-GAN: CLIP-guided Text GAN for Image Captioningcited by 10
  32. 2025INTER: Mitigating Hallucination in Large Vision-Language Models by Interaction Guidance Samplingcited by 10
  33. 2024Unleashing Text-to-Image Diffusion Prior for Zero-Shot Image Captioningcited by 7
  34. 2024No Detail Left Behind: Revisiting Self-Retrieval for Fine-Grained Image Captioningcited by 5
  35. 2025CaptionSmiths: Flexibly Controlling Language Pattern in Image Captioningcited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026CCCaption: Dual-Reward Reinforcement Learning for Complete and Correct Image Captioning
  2. 2026CapRL++: Unified Reinforcement Learning with Verifiable Rewards for Dense Image and Video Captioning
  3. 2026BalCapRL: A Balanced Framework for RL-Based MLLM Image Captioning
  4. 2024Distinctive Image Captioning: Leveraging Ground Truth Captions in CLIP Guided Reinforcement Learning
  5. 2026ReflectCAP: Detailed Image Captioning with Reflective Memory
  6. 2026ClaimDiff-RL: Fine-Grained Caption Reinforcement Learning through Visual Claim Comparison
  7. 2025RePIC: Reinforced Post-Training for Personalizing Multi-Modal Language Models
  8. 2025CaptionQA: Is Your Caption as Useful as the Image Itself?