Papers › TraveLER: A Modular Multi-LMM Agent Framework for Video Question-Answering

TraveLER: A Modular Multi-LMM Agent Framework for Video Question-Answering

1 Apr 2024arXiv:2404.01476archive 2025-07-28

Chuyi Shang, Amos You, Sanjay Subramanian, Trevor Darrell, Roei Herzig

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.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

traveler-framework/traveler officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Question AnsweringVideo Question AnsweringZero-Shot Video Question Answer

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Question Answering Perception Test TraveLER Accuracy (Top-1) 50.2 #5 of 6 Archive leaderboard report
Video Question Answering STAR Benchmark TraveLER (0-shot) Average Accuracy 44.9 #11 of 17 Archive leaderboard report
Zero-Shot Video Question Answer EgoSchema (fullset) TraveLER Accuracy 53.3 #16 of 29 Archive leaderboard report
Zero-Shot Video Question Answer NExT-QA TraveLER (GPT-4) Accuracy 68.2 #13 of 27 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections