# Provoking Multi-modal Few-Shot LVLM via Exploration-Exploitation In-Context Learning

arXiv: https://arxiv.org/abs/2506.09473 · HTML: https://mlsanity.com/paper/2506.09473/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 48 references that are in the map.
- First posted on arXiv 11 Jun 2025.

## Builds on (most cited first, 30 of 39)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [Towards VQA Models That Can Read](https://mlsanity.com/paper/1904.08920/) (2019)
- [ImageBind: One Embedding Space To Bind Them All](https://mlsanity.com/paper/2305.05665/) (2023)
- [Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity](https://mlsanity.com/paper/2104.08786/) (2021)
- [OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge](https://mlsanity.com/paper/1906.00067/) (2019)
- [GLM: General Language Model Pretraining with Autoregressive Blank Infilling](https://mlsanity.com/paper/2103.10360/) (2021)
- [Are We on the Right Way for Evaluating Large Vision-Language Models?](https://mlsanity.com/paper/2403.20330/) (2024)
- [Learning To Retrieve Prompts for In-Context Learning](https://mlsanity.com/paper/2112.08633/) (2021)
- [Explainability for Large Language Models: A Survey](https://mlsanity.com/paper/2309.01029/) (2023)
- [MM-LLMs: Recent Advances in MultiModal Large Language Models](https://mlsanity.com/paper/2401.13601/) (2024)
- [Generating Images with Multimodal Language Models](https://mlsanity.com/paper/2305.17216/) (2023)
- [MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and Text](https://mlsanity.com/paper/2210.02928/) (2022)
- [Self-Adaptive In-Context Learning: An Information Compression Perspective for In-Context Example Selection and Ordering](https://mlsanity.com/paper/2212.10375/) (2022)
- [Unified Demonstration Retriever for In-Context Learning](https://mlsanity.com/paper/2305.04320/) (2023)
- [Diverse Demonstrations Improve In-context Compositional Generalization](https://mlsanity.com/paper/2212.06800/) (2022)
- [Case-based Reasoning for Natural Language Queries over Knowledge Bases](https://mlsanity.com/paper/2104.08762/) (2021)
- [Training Data is More Valuable than You Think: A Simple and Effective Method by Retrieving from Training Data](https://mlsanity.com/paper/2203.08773/) (2022)
- [Eliciting the Translation Ability of Large Language Models via Multilingual Finetuning with Translation Instructions](https://mlsanity.com/paper/2305.15083/) (2023)
- [Gloss Attention for Gloss-free Sign Language Translation](https://mlsanity.com/paper/2307.07361/) (2023)
- [MvP: Multi-view Prompting Improves Aspect Sentiment Tuple Prediction](https://mlsanity.com/paper/2305.12627/) (2023)
- [Exploring Human-Like Translation Strategy with Large Language Models](https://mlsanity.com/paper/2305.04118/) (2023)

## Built on by (most cited first, 7 of 7)

- [ContextNav: Towards Agentic Multimodal In-Context Learning](https://mlsanity.com/paper/2510.04560/) (2025)
- [Retrieving Counterfactuals Improves Visual In-Context Learning](https://mlsanity.com/paper/2603.16737/) (2026)
- [TADS: Task-Aware Data Selection for Multi-Task Multimodal Pre-Training](https://mlsanity.com/paper/2602.05251/) (2026)
- [Gradient-free Task-Conditioned Retrieval for On-Device In-Context Learning](https://mlsanity.com/paper/2607.27766/) (2026)
- [MAG: MAnifold Guided Semi-Supervised Multi-modal In-Context Learning](https://mlsanity.com/paper/2608.12724/) (2026)
- [The Value of Being Wrong: Self-Mined Visual In-Context Learning from Errors](https://mlsanity.com/paper/2610.16977/) (2026)
- [ActICL: Post-Training for Agentic Multimodal In-Context Learning](https://mlsanity.com/paper/2610.19475/) (2026)

## Abstract (arXiv)

In-context learning (ICL), a predominant trend in instruction learning, aims at enhancing the performance of large language models by providing clear task guidance and examples, improving their capability in task understanding and execution. This paper investigates ICL on Large Vision-Language Models (LVLMs) and explores the policies of multi-modal demonstration selection. Existing research efforts in ICL face significant challenges: First, they rely on pre-defined demonstrations or heuristic selecting strategies based on human intuition, which are usually inadequate for covering diverse task requirements, leading to sub-optimal solutions; Second, individually selecting each demonstration fails in modeling the interactions between them, resulting in information redundancy. Unlike these prevailing efforts, we propose a new exploration-exploitation reinforcement learning framework, which explores policies to fuse multi-modal information and adaptively select adequate demonstrations as an integrated whole. The framework allows LVLMs to optimize themselves by continually refining their demonstrations through self-exploration, enabling the ability to autonomously identify and generate the most effective selection policies for in-context learning. Experimental results verify the superior performance of our approach on four Visual Question-Answering (VQA) datasets, demonstrating its effectiveness in enhancing the generalization capability of few-shot LVLMs.