{"id":"2609.21386","title":"AgentVidBench: A Multi-Hop Video Question Answering Benchmark for Evaluating MLLM Agents","url":"https://codeofpaper.com/paper/2609.21386","arxiv_url":"https://arxiv.org/abs/2609.21386","published":"2026-09-18","code":"official","best":{"full_name":"krafton-ai/agentvidbench","url":"https://github.com/krafton-ai/agentvidbench","tier":"official","stars":2,"license":"Apache-2.0","framework":null,"language":"Python","last_commit":"2026-06-12T02:03:24"},"most_starred_community":null,"implementations":[{"full_name":"krafton-ai/agentvidbench","url":"https://github.com/krafton-ai/agentvidbench","tier":"official","stars":2,"license":"Apache-2.0","framework":null,"language":"Python","last_commit":"2026-06-12T02:03:24"}],"possible_matches":0}