LongVideoAgent: Multi-Agent Reasoning with Long Videos
This work addresses the challenge of fine-grained temporal grounding in long-video question answering for AI systems, representing an incremental improvement over existing methods.
The authors tackled the problem of reasoning over hour-long videos by proposing a multi-agent framework where a master LLM coordinates grounding and vision agents to localize relevant segments and extract textual observations, significantly outperforming non-agent baselines on their LongTVQA and LongTVQA+ datasets.
Recent advances in multimodal LLMs and systems that use tools for long-video QA point to the promise of reasoning over hour-long episodes. However, many methods still compress content into lossy summaries or rely on limited toolsets, weakening temporal grounding and missing fine-grained cues. We propose a multi-agent framework in which a master LLM coordinates a grounding agent to localize question-relevant segments and a vision agent to extract targeted textual observations. The master agent plans with a step limit, and is trained with reinforcement learning to encourage concise, correct, and efficient multi-agent cooperation. This design helps the master agent focus on relevant clips via grounding, complements subtitles with visual detail, and yields interpretable trajectories. On our proposed LongTVQA and LongTVQA+ which are episode-level datasets aggregated from TVQA/TVQA+, our multi-agent system significantly outperforms strong non-agent baselines. Experiments also show reinforcement learning further strengthens reasoning and planning for the trained agent. Code and data will be shared at https://longvideoagent.github.io/.