# ReCCur: A Recursive Corner-Case Curation Framework for Robust Vision-Language Understanding in Open and Edge Scenarios

arXiv: https://arxiv.org/abs/2601.03011 · HTML: https://mlsanity.com/paper/2601.03011/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 36 of its 45 references that are in the map.
- First posted on arXiv 6 Jan 2026.

## Builds on (most cited first, 30 of 36)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [DataComp: In search of the next generation of multimodal datasets](https://mlsanity.com/paper/2304.14108/) (2023)
- [YOLO-World: Real-Time Open-Vocabulary Object Detection](https://mlsanity.com/paper/2401.17270/) (2024)
- [ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs](https://mlsanity.com/paper/2309.13007/) (2023)
- [Chain of Agents: Large Language Models Collaborating on Long-Context Tasks](https://mlsanity.com/paper/2406.02818/) (2024)
- [Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems](https://mlsanity.com/paper/2505.00212/) (2025)
- [FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Making](https://mlsanity.com/paper/2407.06567/) (2024)
- [Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models?](https://mlsanity.com/paper/2508.17536/) (2025)
- [Automatic Data Curation for Self-Supervised Learning: A Clustering-Based Approach](https://mlsanity.com/paper/2405.15613/) (2024)
- [Evaluating Judges as Evaluators: The JETTS Benchmark of LLM-as-Judges as Test-Time Scaling Evaluators](https://mlsanity.com/paper/2504.15253/) (2025)
- [Vocabulary-free Image Classification](https://mlsanity.com/paper/2306.00917/) (2023)
- [Data curation via joint example selection further accelerates multimodal learning](https://mlsanity.com/paper/2406.17711/) (2024)
- [Transductive Zero-Shot and Few-Shot CLIP](https://mlsanity.com/paper/2405.18437/) (2024)
- [UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection](https://mlsanity.com/paper/2412.03342/) (2024)
- [Noise-aware Learning from Web-crawled Image-Text Data for Image Captioning](https://mlsanity.com/paper/2212.13563/) (2022)
- [Multiple LLM Agents Debate for Equitable Cultural Alignment](https://mlsanity.com/paper/2505.24671/) (2025)
- [Improving Image Recognition by Retrieving from Web-Scale Image-Text Data](https://mlsanity.com/paper/2304.05173/) (2023)
- [Multimodality Helps Few-shot 3D Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2410.22489/) (2024)
- [Active Data Curation Effectively Distills Large-Scale Multimodal Models](https://mlsanity.com/paper/2411.18674/) (2024)
- [Simple Semantic-Aided Few-Shot Learning](https://mlsanity.com/paper/2311.18649/) (2023)
- [Few-Shot Recognition via Stage-Wise Retrieval-Augmented Finetuning](https://mlsanity.com/paper/2406.11148/) (2024)
- [Frozen Feature Augmentation for Few-Shot Image Classification](https://mlsanity.com/paper/2403.10519/) (2024)
- [M-MAD: Multidimensional Multi-Agent Debate for Advanced Machine Translation Evaluation](https://mlsanity.com/paper/2412.20127/) (2024)
- [Webly Supervised Image Classification with Self-Contained Confidence](https://mlsanity.com/paper/2008.11894/) (2020)
- [Boosting Few-Shot Learning via Attentive Feature Regularization](https://mlsanity.com/paper/2403.17025/) (2024)
- [Cross-Domain Few-Shot Learning via Adaptive Transformer Networks](https://mlsanity.com/paper/2401.13987/) (2024)
- [Discriminative Sample-Guided and Parameter-Efficient Feature Space Adaptation for Cross-Domain Few-Shot Learning](https://mlsanity.com/paper/2403.04492/) (2024)

## Abstract (arXiv)

Corner cases are rare or extreme scenarios that drive real-world failures, but they are difficult to curate at scale: web data are noisy, labels are brittle, and edge deployments preclude large retraining. We present ReCCur (Recursive Corner-Case Curation), a low-compute framework that converts noisy web imagery into auditable fine-grained labels via a multi-agent recursive pipeline. First, large-scale data acquisition and filtering expands a domain vocabulary with a vision-language model (VLM), crawls the web, and enforces tri-modal (image, description, keyword) consistency with light human spot checks to yield refined candidates. Next, mixture-of-experts knowledge distillation uses complementary encoders (e.g., CLIP, DINOv2, BEiT) for kNN voting with dual-confidence activation and uncertainty sampling, converging to a high-precision set. Finally, region-evidence VLM adversarial labeling pairs a proposer (multi-granularity regions and semantic cues) with a validator (global and local chained consistency) to produce explainable labels and close the loop. On realistic corner-case scenarios (e.g., flooded-car inspection), ReCCur runs on consumer-grade GPUs, steadily improves purity and separability, and requires minimal human supervision, providing a practical substrate for downstream training and evaluation under resource constraints. Code and dataset will be released.