Challenge: Existing Large Multi-modal Models lack a robust visual processing capability that is often masked by evaluation metrics that prioritize final-answer accuracy.
Approach: They propose a three-layer evaluation framework that scrutinizes the generation of valid visual aids and the soundness of subsequent reasoning steps.
Outcome: The proposed framework examines the generation of valid visual aids and the soundness of subsequent reasoning steps on state-of-the-art models.

Similar Papers

Selective Vision is the Challenge for Visual Reasoning: A Benchmark for Visual Argument Understanding (2024.emnlp-main)

Copied to clipboard

Challenge: Visual arguments rely on images to persuade viewers to do or believe something .
Approach: They propose three tasks for evaluating visual argument understanding . they use visual premises, commonsense premises and reasoning trees to analyze visual arguments .
Outcome: The proposed tasks evaluate visual argument understanding using a dataset of 1,611 images annotated with 5,112 visual premises (with regions), 5,574 commonsense premises, and reasoning trees connecting them into structured arguments.
LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs (2025.findings-acl)

Copied to clipboard

Challenge: Existing approaches do not emphasize step-wise problem-solving.
Approach: They propose a visual reasoning chain benchmark and a fine-grained reasoning metric that evaluates correctness and logical coherence at each step.
Outcome: The proposed framework outperforms existing models in six benchmarks and is 5x faster during inference scaling.
SpatialMath: Spatial Comprehension-Infused Symbolic Reasoning for Mathematical Problem-Solving (2026.findings-eacl)

Copied to clipboard

Challenge: Current models struggle to accurately decompose intricate visual inputs and connect perception with structured reasoning, leading to suboptimal performance.
Approach: They propose a Spatial Comprehension-Infused Symbolic Reasoning Framework to integrate spatial representations into structured symbolic reasoning chains.
Outcome: The proposed framework outperforms existing models in vision-intensive mathematical problems.
We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning? (2025.acl-long)

Copied to clipboard

Challenge: Existing benchmarks focus more on end-to-end performance, but neglect the underlying principles of knowledge acquisition and generalization.
Approach: They propose a benchmark specifically designed to explore the problem-solving principles by decomposing 6.5K visual math problems into 10.9K step-level questions for evaluation.
Outcome: The proposed benchmark covers 6.5K visual math problems and 10.9K step-level questions spanning 5 layers of knowledge granularity and 67 hierarchical knowledge concepts.
UTMath: A Benchmark for Math Evaluation with Unit Test (2025.findings-emnlp)

Copied to clipboard

Challenge: Prevailing benchmarks for mathematical reasoning include MATH and AIME . predicated on single-instantiation problems with fixed numbers, these models leave generalization on isomorphic problem variants untested.
Approach: They propose a mathematical reasoning benchmark that quantifies solution accuracy and solution space generality.
Outcome: The proposed model solves 1,053 problems spanning 9 mathematical domains . the best-performing model solved only 32.57% of the problems .
MathCanvas: Intrinsic Visual Chain-of-Thought for Multimodal Mathematical Reasoning (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches to visual chain-of-thought are limited by external tools or fail to generate high-fidelity diagrams.
Approach: They propose a framework to enable large multimodal models with VCoT capabilities . they pre-train a model on a 15.2M-pair corpus and teach it how to leverage visual aids .
Outcome: The proposed framework unlocks complex, human-like visual reasoning in large language models . it pre-trains the model on a 15.2M-pair corpus and fine-tunes it on MathCanvas-Instruct .
TurtleBench: A Visual Programming Benchmark in Turtle Geometry (2025.naacl-long)

Copied to clipboard

Challenge: Large Multimodal Models (LMMs) are capable of reasoning about geometric patterns, but they are still a challenge to evaluate.
Approach: They propose a benchmark to evaluate LMMs’ ability to interpret geometric patterns and generate precise code outputs.
Outcome: The benchmark compared LMMs with turtle geometry and GPT-4V, and found that few-shot prompting improved their performance (2%).
Challenging the Boundaries of Reasoning: An Olympiad-Level Math Benchmark for Large Language Models (2026.acl-long)

Copied to clipboard

Challenge: Existing evaluation frameworks for large reasoning models are saturated by a lack of reliable and verifiable benchmarks.
Approach: They propose a rigorously curated, Olympiad-level math benchmark comprising 350 problems, each with parallel English and Chinese versions.
Outcome: The proposed benchmark unifies two evaluation paradigms and offers 150 problems formalized in Lean 4 for rigorous process-level evaluation.
Your Reasoning Benchmark May Not Test Reasoning: Revealing Perception Bottleneck in Abstract Reasoning Benchmarks (2026.acl-long)

Copied to clipboard

Challenge: Abstraction and Reasoning Corpus and ARC-AGI are widely used to assess progress in artificial intelligence.
Approach: They propose a two-stage pipeline that separates perception and reasoning . they propose to test this pipeline against standard end-to-end one-stage evaluation .
Outcome: The proposed pipeline separates perception and reasoning, and isolates reasoning from bottlenecks.
MathSight: A Benchmark Exploring Have Vision-Language Models Really Seen in University-Level Mathematical Reasoning? (2026.acl-long)

Copied to clipboard

Challenge: Existing benchmarks rarely isolate how much visual information contributes to reasoning . a growing collection of benchmarks has catalyzed rapid progress in multimodal reasoning - but how much it contributes remains unclear .
Approach: They propose a university-level multimodal mathematical reasoning benchmark to quantify the effect of visual input.
Outcome: The proposed benchmark disentangles and quantifies the effect of visual input on multimodal reasoning models.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations