# FIKA-Bench: From Fine-grained Recognition to Fine-Grained Knowledge Acquisition

arXiv: https://arxiv.org/abs/2605.13193 · HTML: https://mlsanity.com/paper/2605.13193/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 45 references that are in the map.
- First posted on arXiv 13 May 2026.

## Builds on (most cited first, 24 of 24)

- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments](https://mlsanity.com/paper/2404.07972/) (2024)
- [Visual-RFT: Visual Reinforcement Fine-Tuning](https://mlsanity.com/paper/2503.01785/) (2025)
- [WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models](https://mlsanity.com/paper/2401.13919/) (2024)
- [ABO: Dataset and Benchmarks for Real-World 3D Object Understanding](https://mlsanity.com/paper/2110.06199/) (2021)
- [Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrieval](https://mlsanity.com/paper/2004.01804/) (2020)
- [WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agent](https://mlsanity.com/paper/2508.05748/) (2025)
- [MMSearch: Benchmarking the Potential of Large Models as Multi-modal Search Engines](https://mlsanity.com/paper/2409.12959/) (2024)
- [MMInA: Benchmarking Multihop Multimodal Internet Agents](https://mlsanity.com/paper/2404.09992/) (2024)
- [The 2021 Image Similarity Dataset and Challenge](https://mlsanity.com/paper/2106.09672/) (2021)
- [Products-10K: A Large-scale Product Recognition Dataset](https://mlsanity.com/paper/2008.10545/) (2020)
- [MMSearch-Plus: Benchmarking Provenance-Aware Search for Multimodal Browsing Agents](https://mlsanity.com/paper/2508.21475/) (2025)
- [GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents](https://mlsanity.com/paper/2604.26752/) (2026)
- [Benchmarking Large Vision-Language Models on Fine-Grained Image Tasks: A Comprehensive Evaluation](https://mlsanity.com/paper/2504.14988/) (2025)
- [A Hierarchical Grocery Store Image Dataset with Visual and Semantic Labels](https://mlsanity.com/paper/1901.00711/) (2019)
- [Fine-R1: Make Multi-modal LLMs Excel in Fine-Grained Visual Recognition by Chain-of-Thought Reasoning](https://mlsanity.com/paper/2602.07605/) (2026)
- [WorldVQA: Measuring Atomic World Knowledge in Multimodal Large Language Models](https://mlsanity.com/paper/2602.02537/) (2026)
- [MERRIN: A Benchmark for Multimodal Evidence Retrieval and Reasoning in Noisy Web Environments](https://mlsanity.com/paper/2604.13418/) (2026)
- [Towards Fine-Grained Recognition with Large Visual Language Models: Benchmark and Optimization Strategies](https://mlsanity.com/paper/2512.10384/) (2025)

## Abstract (arXiv)

Fine-grained recognition in everyday life is often not a closed-book classification problem: when encountering unfamiliar objects, humans actively search, compare visual details, and verify evidence before deciding. Existing benchmarks primarily evaluate visually recognition, leaving this active external knowledge acquisition ability underexplored. We study fine-grained knowledge acquisition, where a system must seek, verify, and use external evidence to answer open-ended fine-grained recognition questions. We introduce FIKA-Bench, a leakage-aware and evidence-grounded collection of 311 public-source and real-life instances. To ensure high quality, every example is filtered against frontier closed-book models to remove memorized cases and audited to eliminate image-answer leakage, retaining only samples supported by verified evidence. Our evaluation of latest Large Multimodal Models (LMMs) and agents reveals that the task remains a formidable challenge: the best system reaches only 25.1% accuracy, with no model exceeding 30%. Crucially, we find that merely equipping models with tools is insufficient to bridge this gap; agent failures are predominantly driven by wrong entity retrieval and poor visual judgement. These results show that reliable knowledge acquisition needs better agent designs that focus on fine-grained recognition.