# SARE: Sample-wise Adaptive Reasoning for Training-free Fine-grained Visual Recognition

arXiv: https://arxiv.org/abs/2603.17729 · HTML: https://mlsanity.com/paper/2603.17729/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 51 of its 72 references that are in the map.
- First posted on arXiv 18 Mar 2026.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 30 of 51)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [Conditional Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2203.05557/) (2022)
- [FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance](https://mlsanity.com/paper/2305.05176/) (2023)
- [Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback](https://mlsanity.com/paper/2305.14975/) (2023)
- [Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling](https://mlsanity.com/paper/2501.17811/) (2025)
- [Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding](https://mlsanity.com/paper/2311.16922/) (2023)
- [MaPLe: Multi-modal Prompt Learning](https://mlsanity.com/paper/2210.03117/) (2022)
- [RouteLLM: Learning to Route LLMs with Preference Data](https://mlsanity.com/paper/2406.18665/) (2024)
- [FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling](https://mlsanity.com/paper/2110.08263/) (2021)
- [Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling](https://mlsanity.com/paper/2111.03930/) (2021)
- [From System 1 to System 2: A Survey of Reasoning Large Language Models](https://mlsanity.com/paper/2502.17419/) (2025)
- [Fine-Grained Image Analysis with Deep Learning: A Survey](https://mlsanity.com/paper/2111.06119/) (2021)
- [SuS-X: Training-Free Name-Only Transfer of Vision-Language Models](https://mlsanity.com/paper/2211.16198/) (2022)
- [Why are Visually-Grounded Language Models Bad at Image Classification?](https://mlsanity.com/paper/2405.18415/) (2024)
- [FG-CLIP: Fine-Grained Visual and Textual Alignment](https://mlsanity.com/paper/2505.05071/) (2025)
- [K-LITE: Learning Transferable Visual Models with External Knowledge](https://mlsanity.com/paper/2204.09222/) (2022)
- [Learning Customized Visual Models with Retrieval-Augmented Knowledge](https://mlsanity.com/paper/2301.07094/) (2023)
- [MultiTrust: A Comprehensive Benchmark Towards Trustworthy Multimodal Large Language Models](https://mlsanity.com/paper/2406.07057/) (2024)
- [Vocabulary-free Image Classification](https://mlsanity.com/paper/2306.00917/) (2023)
- [African or European Swallow? Benchmarking Large Vision-Language Models for Fine-Grained Object Classification](https://mlsanity.com/paper/2406.14496/) (2024)
- [Investigating and Mitigating the Multimodal Hallucination Snowballing in Large Vision-Language Models](https://mlsanity.com/paper/2407.00569/) (2024)
- [Analyzing and Boosting the Power of Fine-Grained Visual Recognition for Multi-modal Large Language Models](https://mlsanity.com/paper/2501.15140/) (2025)
- [AWT: Transferring Vision-Language Models via Augmentation, Weighting, and Transportation](https://mlsanity.com/paper/2407.04603/) (2024)

## Built on by (most cited first, 3 of 3)

- [Reconciling Process Supervision with Outcome-Based Credit in Agentic Policy Optimization](https://mlsanity.com/paper/2608.31077/) (2026)
- [Dual-Axis Policy Optimization for LLM Agents: Bayesian Feedback Attribution and Trajectory Mass Normalization](https://mlsanity.com/paper/2609.19830/) (2026)
- [DEEPO: Dual-Entropy Enhanced Policy Optimization for Hallucination in MLLMs](https://mlsanity.com/paper/2609.28570/) (2026)

## Abstract (arXiv)

Recent advances in Large Vision-Language Models (LVLMs) have enabled training-free Fine-Grained Visual Recognition (FGVR). However, effectively exploiting LVLMs for FGVR remains challenging due to the inherent visual ambiguity of subordinate-level categories. Existing methods predominantly adopt either retrieval-oriented or reasoning-oriented paradigms to tackle this challenge, but both are constrained by two fundamental limitations:(1) They apply the same inference pipeline to all samples without accounting for uneven recognition difficulty, thereby leading to suboptimal accuracy and efficiency; (2) The lack of mechanisms to consolidate and reuse error-specific experience causes repeated failures on similar challenging cases. To address these limitations, we propose SARE, a Sample-wise Adaptive textbfREasoning framework for training-free FGVR. Specifically, SARE adopts a cascaded design that combines fast candidate retrieval with fine-grained reasoning, invoking the latter only when necessary. In the reasoning process, SARE incorporates a self-reflective experience mechanism that leverages past failures to provide transferable discriminative guidance during inference, without any parameter updates. Extensive experiments across 14 datasets substantiate that SARE achieves state-of-the-art performance while substantially reducing computational overhead.