{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/mmctagent-multi-modal-critical-thinking-agent","title":"MMCTAgent: Multi-modal Critical Thinking Agent Framework for Complex Visual Reasoning","arxiv_id":"2405.18358","date":"2024-05-28","proceeding":null,"authors":["Somnath Kumar","Yash Gadhia","Tanuja Ganu","Akshay Nambi"],"abstract":"Recent advancements in Multi-modal Large Language Models (MLLMs) have significantly improved their performance in tasks combining vision and language. However, challenges persist in detailed multi-modal understanding, comprehension of complex tasks, and reasoning over multi-modal information. This paper introduces MMCTAgent, a novel multi-modal critical thinking agent framework designed to address the inherent limitations of current MLLMs in complex visual reasoning tasks. Inspired by human cognitive processes and critical thinking, MMCTAgent iteratively analyzes multi-modal information, decomposes queries, plans strategies, and dynamically evolves its reasoning. Additionally, MMCTAgent incorporates critical thinking elements such as verification of final answers and self-reflection through a novel approach that defines a vision-based critic and identifies task-specific evaluation criteria, thereby enhancing its decision-making abilities. Through rigorous evaluations across various image and video understanding benchmarks, we demonstrate that MMCTAgent (with and without the critic) outperforms both foundational MLLMs and other tool-augmented pipelines.","url_abs":"https://arxiv.org/abs/2405.18358v1","url_pdf":"https://arxiv.org/pdf/2405.18358v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"video-understanding","task_name":"Video Understanding"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-reasoning","task_name":"Visual Reasoning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-question-answering-on-mm-vet","task":"Visual Question Answering","dataset":"MM-Vet","model":"MMCTAgent (GPT-4 + GPT-4V)","rank_in_archive_order":4,"of":231,"metrics":{"GPT-4 score":"74.24"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2405.18358","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}