{"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/traveler-a-multi-lmm-agent-framework-for","title":"TraveLER: A Modular Multi-LMM Agent Framework for Video Question-Answering","arxiv_id":"2404.01476","date":"2024-04-01","proceeding":null,"authors":["Chuyi Shang","Amos You","Sanjay Subramanian","Trevor Darrell","Roei Herzig"],"abstract":"Recently, image-based Large Multimodal Models (LMMs) have made significant progress in video question-answering (VideoQA) using a frame-wise approach by leveraging large-scale pretraining in a zero-shot manner. Nevertheless, these models need to be capable of finding relevant information, extracting it, and answering the question simultaneously. Currently, existing methods perform all of these steps in a single pass without being able to adapt if insufficient or incorrect information is collected. To overcome this, we introduce a modular multi-LMM agent framework based on several agents with different roles, instructed by a Planner agent that updates its instructions using shared feedback from the other agents. Specifically, we propose TraveLER, a method that can create a plan to \"Traverse\" through the video, ask questions about individual frames to \"Locate\" and store key information, and then \"Evaluate\" if there is enough information to answer the question. Finally, if there is not enough information, our method is able to \"Replan\" based on its collected knowledge. Through extensive experiments, we find that the proposed TraveLER approach improves performance on several VideoQA benchmarks without the need to fine-tune on specific datasets. Our code is available at https://github.com/traveler-framework/TraveLER.","url_abs":"https://arxiv.org/abs/2404.01476v2","url_pdf":"https://arxiv.org/pdf/2404.01476v2.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":[{"paper_slug":"traveler-a-multi-lmm-agent-framework-for","repo_url":"https://github.com/traveler-framework/traveler","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"video-question-answering","task_name":"Video Question Answering"},{"task_slug":"zeroshot-video-question-answer","task_name":"Zero-Shot Video Question Answer"}],"methods":[{"method_slug":null,"method_name":null}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-question-answering-on-perception-test","task":"Video Question Answering","dataset":"Perception Test","model":"TraveLER","rank_in_archive_order":5,"of":6,"metrics":{"Accuracy (Top-1)":"50.2"},"uses_additional_data":false},{"leaderboard":"/sota/video-question-answering-on-situated","task":"Video Question Answering","dataset":"STAR Benchmark","model":"TraveLER (0-shot)","rank_in_archive_order":11,"of":17,"metrics":{"Average Accuracy":"44.9"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-video-question-answer-on-egoschema-1","task":"Zero-Shot Video Question Answer","dataset":"EgoSchema (fullset)","model":"TraveLER","rank_in_archive_order":16,"of":29,"metrics":{"Accuracy":"53.3"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-video-question-answer-on-next-qa","task":"Zero-Shot Video Question Answer","dataset":"NExT-QA","model":"TraveLER (GPT-4)","rank_in_archive_order":13,"of":27,"metrics":{"Accuracy":"68.2"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2404.01476","atlas_url":"https://app.syntology.ai/?focus=2404.01476","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}