MageBench: Bridging Large Multimodal Models to Agents

• URL: http://arxiv.org/abs/2412.04531v1
• Date: Thu, 05 Dec 2024 17:08:19 GMT
• Title: MageBench: Bridging Large Multimodal Models to Agents
• Authors: Miaosen Zhang, Qi Dai, Yifan Yang, Jianmin Bao, Dongdong Chen, Kai Qiu, Chong Luo, Xin Geng, Baining Guo,
• Abstract summary: LMMs have shown impressive visual understanding capabilities, with the potential to be applied in agents. Existing benchmarks mostly assess their reasoning abilities in language part. MageBench is a reasoning capability oriented multimodal agent benchmark.
• Score: 90.59091431806793
• License:
• Abstract: LMMs have shown impressive visual understanding capabilities, with the potential to be applied in agents, which demand strong reasoning and planning abilities. Nevertheless, existing benchmarks mostly assess their reasoning abilities in language part, where the chain-of-thought is entirely composed of text.We consider the scenario where visual signals are continuously updated and required along the decision making process. Such vision-in-the-chain reasoning paradigm is more aligned with the needs of multimodal agents, while being rarely evaluated. In this paper, we introduce MageBench, a reasoning capability oriented multimodal agent benchmark that, while having light-weight environments, poses significant reasoning challenges and holds substantial practical value. This benchmark currently includes three types of environments: WebUI, Sokoban, and Football, comprising a total of 483 different scenarios. It thoroughly validates the agent's knowledge and engineering capabilities, visual intelligence, and interaction skills. The results show that only a few product-level models are better than random acting, and all of them are far inferior to human-level. More specifically, we found current models severely lack the ability to modify their planning based on visual feedback, as well as visual imagination, interleaved image-text long context handling, and other abilities. We hope that our work will provide optimization directions for LMM from the perspective of being an agent. We release our code and data at https://github.com/microsoft/MageBench.

Related papers

• Visual-O1: Understanding Ambiguous Instructions via Multi-modal Multi-turn Chain-of-thoughts Reasoning [53.45295657891099]
  This paper proposes Visual-O1, a multi-modal multi-turn chain-of-thought reasoning framework. It simulates human multi-modal multi-turn reasoning, providing instantial experience for highly intelligent models. Our work highlights the potential of artificial intelligence to work like humans in real-world scenarios with uncertainty and ambiguity.
  arXiv  Detail & Related papers  (2024-10-04T11:18:41Z)
• VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents [50.12414817737912]
  Large Multimodal Models (LMMs) have ushered in a new era in artificial intelligence, merging capabilities in both language and vision to form highly capable Visual Foundation Agents. Existing benchmarks fail to sufficiently challenge or showcase the full potential of LMMs in complex, real-world environments. VisualAgentBench (VAB) is a pioneering benchmark specifically designed to train and evaluate LMMs as visual foundation agents.
  arXiv  Detail & Related papers  (2024-08-12T17:44:17Z)
• Smart Vision-Language Reasoners [0.0]
  We investigate vision-language models (VLM) as reasoners. The ability to form abstractions underlies mathematical reasoning, problem-solving, and other Math AI tasks. We employ the abstractions given in the SMART task as meta-reasoning and problem-solving skills along eight axes.
  arXiv  Detail & Related papers  (2024-07-05T01:47:21Z)
• ReMI: A Dataset for Reasoning with Multiple Images [41.954830849939526]
  We introduce ReMI, a dataset designed to assess large language models' ability to Reason with Multiple Images. This dataset encompasses a diverse range of tasks, spanning various reasoning domains such as math, physics, logic, code, table/chart understanding, and spatial and temporal reasoning. We have benchmarked several cutting-edge LLMs and found a substantial gap between their performance and human-level proficiency.
  arXiv  Detail & Related papers  (2024-06-13T14:37:04Z)
• CODIS: Benchmarking Context-Dependent Visual Comprehension for Multimodal Large Language Models [58.95889895912716]
  We introduce a new benchmark, named as CODIS, designed to assess the ability of models to use context provided in free-form text to enhance visual comprehension. Our findings indicate that MLLMs consistently fall short of human performance on this benchmark. This underscores the pressing need to enhance the ability of MLLMs to comprehend visuals in a context-dependent manner.
  arXiv  Detail & Related papers  (2024-02-21T08:21:12Z)
• VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks [93.85005277463802]
  VisualWebArena is a benchmark designed to assess the performance of multimodal web agents on realistic tasks. To perform on this benchmark, agents need to accurately process image-text inputs, interpret natural language instructions, and execute actions on websites to accomplish user-defined objectives.
  arXiv  Detail & Related papers  (2024-01-24T18:35:21Z)
• MAgIC: Investigation of Large Language Model Powered Multi-Agent in Cognition, Adaptability, Rationality and Collaboration [98.18244218156492]
  Large Language Models (LLMs) have significantly advanced natural language processing. As their applications expand into multi-agent environments, there arises a need for a comprehensive evaluation framework. This work introduces a novel competition-based benchmark framework to assess LLMs within multi-agent settings.
  arXiv  Detail & Related papers  (2023-11-14T21:46:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.