TraceAV-Bench: Benchmarking Multi-Hop Trajectory Reasoning over Long Audio-Visual Videos

• URL: http://arxiv.org/abs/2605.07593v1
• Date: Fri, 08 May 2026 11:06:43 GMT
• Title: TraceAV-Bench: Benchmarking Multi-Hop Trajectory Reasoning over Long Audio-Visual Videos
• Abstract summary: Real-world audio-visual understanding requires chaining evidence that is sparse, temporally dispersed, and split across the visual and auditory streams.<n>We introduce TraceAV-Bench, the first benchmark to jointly evaluate multi-hop reasoning over long audio-visual trajectories and multimodal hallucination robustness.
• Score: 13.9567665031159
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Real-world audio-visual understanding requires chaining evidence that is sparse, temporally dispersed, and split across the visual and auditory streams, whereas existing benchmarks largely fail to evaluate this capability. They restrict videos to short clips, isolate modalities, or reduce questions to one-hop perception. We introduce TraceAV-Bench, the first benchmark to jointly evaluate multi-hop reasoning over long audio-visual trajectories and multimodal hallucination robustness. TraceAV-Bench comprises 2,200 rigorously validated multiple-choice questions over 578 long videos, totaling 339.5 hours, spanning 4 evaluation dimensions and 15 sub-tasks. Each question is grounded in an explicit reasoning chain that averages 3.68 hops across a 15.1-minute temporal span. The dataset is built by a three-step semi-automated pipeline followed by a strict quality assurance process. Evaluation of multiple representative OmniLLMs on TraceAV-Bench reveals that the benchmark poses a persistent challenge across all models, with the strongest closed-source model (Gemini 3.1 Pro) reaching only 68.29% on general tasks, and the best open-source model (Ming-Flash-Omni-2.0) reaching 51.70%, leaving substantial headroom. Moreover, we find that robustness to multimodal hallucination is largely decoupled from general multimodal reasoning performance. We anticipate that TraceAV-Bench will stimulate further research toward OmniLLMs that can reason coherently and faithfully over long-form audio-visual content.

Related papers

• OmniPro: A Comprehensive Benchmark for Omni-Proactive Streaming Video Understanding [17.161087166882744]
  We present OmniPro, the first benchmark to jointly evaluate omni-modal perception, proactive responding, and diverse video understanding tasks.<n>It comprises 2,700 human-verified samples spanning 9 sub-tasks and 3 cognitive levels, covering 6 basic video understanding capabilities.<n> Notably, 84% of samples require audio signals (speech or non-speech), and each sample is annotated with modality-isolation labels to enable fine-grained multimodal analysis.
  arXiv  Detail & Related papers  (2026-05-18T15:55:22Z)
• LVOmniBench: Pioneering Long Audio-Video Understanding Evaluation for Omnimodal LLMs [68.35684758116453]
  This dataset comprises high-quality videos sourced from open platforms that feature rich audio-visual dynamics.<n>We rigorously evaluate the capabilities of OmniLLMs across domains, including long-term memory, temporal localization, fine-grained understanding, and multimodal perception.<n>Open-source models generally achieve accuracies below 35%, whereas the Gemini 3 Pro reaches a peak accuracy of approximately 65%.
  arXiv  Detail & Related papers  (2026-03-19T17:58:13Z)
• MMOU: A Massive Multi-Task Omni Understanding and Reasoning Benchmark for Long and Complex Real-World Videos [118.61621763485465]
  MMOU consists of 15,000 carefully curated questions paired with 9038 web-collected videos of varying length.<n>The benchmark covers 13 fundamental skill categories, all of which require integrating evidence across modalities and time.<n>We evaluate 20+ state-of-the-art open-source and proprietary multimodal models on MMOU.
  arXiv  Detail & Related papers  (2026-03-14T22:28:38Z)
• A Benchmark and Agentic Framework for Omni-Modal Reasoning and Tool Use in Long Videos [76.98722001848493]
  LongShOTBench is a diagnostic benchmark for long-form multimodal video understanding.<n>It includes open-ended, intent-driven questions; single- and multi-turn dialogues; and tasks requiring multimodal reasoning and agentic tool use.<n>LongShOTAgent is an agentic system that analyzes long videos via preprocessing, search, and iterative refinement.
  arXiv  Detail & Related papers  (2025-12-18T18:59:27Z)
• LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling [87.98096428508181]
  LongVT is an end-to-end agentic framework that enables "Thinking with Long Videos" via interleaved Multimodal Chain-of-Tool-Thought.<n>We exploit LMMs' inherent temporal grounding ability as a native video cropping tool to zoom in on a specific video clip and resample finer-grained video frames.<n>Our training dataset consists of 247.9K samples for tool-integrated cold-start supervised fine-tuning, 1.6K samples for agentic reinforcement learning, and 15.4K samples for agentic reinforcement fine-tuning.
  arXiv  Detail & Related papers  (2025-11-25T19:22:48Z)
• AudioMarathon: A Comprehensive Benchmark for Long-Context Audio Understanding and Efficiency in Audio LLMs [53.248502396225724]
  AudioMarathon is a benchmark designed to evaluate both understanding and inference efficiency on long-form audio.<n>We evaluate state-of-the-art LALMs and observe clear performance drops as audio length grows.<n>The results show large gaps across current LALMs and highlight the need for better temporal reasoning.
  arXiv  Detail & Related papers  (2025-10-08T17:50:16Z)
• MAGNET: A Multi-agent Framework for Finding Audio-Visual Needles by Reasoning over Multi-Video Haystacks [67.31276358668424]
  We introduce a novel task named AV-HaystacksQA, where the goal is to identify salient segments across different videos in response to a query and link them together to generate the most informative answer.<n> AVHaystacks is an audio-visual benchmark comprising 3100 annotated QA pairs designed to assess the capabilities of LMMs in multi-video retrieval and temporal grounding task.<n>We propose a model-agnostic, multi-agent framework to address this challenge, achieving up to 89% and 65% relative improvements over baseline methods on BLEU@4 and GPT evaluation scores in QA task on our proposed AVHaystack
  arXiv  Detail & Related papers  (2025-06-08T06:34:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.