CVJun 9, 2025

A Neurosymbolic Agent System for Compositional Visual Reasoning

Georgia Tech
arXiv:2506.07778v31 citationsh-index: 33
Originality Incremental advance
AI Analysis

This addresses a key bottleneck in multi-modal AI for applications requiring complex visual understanding, though it is an incremental improvement over existing neuro-symbolic methods.

The paper tackles the challenge of compositional visual reasoning in vision-language models by introducing VLAgent, a neuro-symbolic agent system that uses a two-stage reasoning process with error detection and verification, achieving superior performance on six benchmarks compared to state-of-the-art models.

The advancement in large language models (LLMs) and large vision models has fueled the rapid progress in multi-modal vision-language reasoning capabilities. However, existing vision-language models (VLMs) remain challenged by compositional visual reasoning. This paper presents VLAgent, a neuro-symbolic approach to developing a Vision-Language Agent system for efficient compositional visual reasoning with three novel features. First, VLAgent develops an interpretable visualization-enhanced two-stage neuro-symbolic reasoning system. The first stage is managed by a front-end engine that generates a structured visual reasoning plan (symbolic program script) for each compositional visual reasoning task by utilizing a pre-trained LLM powered with few-shot chain-of-thought in-context learning. The second stage is managed by a high-performance back-end engine. It transforms the planning script into executable code based on visual input (image or video) and the combination of neural models and symbolic functions and then performs a sequence of actions for the compositional visual reason task. Second, to ensure and enhance the quality of mapping the logic plan to a sequence of executable instructions, VLAgent introduces the SS-parser, which examines the syntax and semantic correctness of the planning script, detects and repairs the logic errors found in the LLM-generated logic plan before generating the executable program. Third, VLAgent introduces the execution verifier in critical reasoning steps to validate and refine its compositional reasoning results in a stepwise manner, for example, ensemble methods for critical visual reasoning and caption analysis for low-confidence compositional reasoning. Extensive experiments on six visual benchmarks compared to a dozen SoTA visual reasoning models show that VLAgent outperforms existing representative approaches to compositional visual reasoning.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes