Plan-Retrieve-Verify: An LLM-Driven Framework for Long-Video Audio-Visual Evidence Reasoning
Open Access
- 9 November 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 12030-12039
Abstract
No abstract availableThis publication has 16 references indexed in Scilit:
- VideoRAG: Retrieval-Augmented Generation with Extreme Long-Context Videos2026
- T2Agent: A Tool-augmented Multimodal Misinformation Detection Agent with Monte Carlo Tree SearchProceedings of the AAAI Conference on Artificial Intelligence, 2026
- CounterVid: Counterfactual Video Generation for Mitigating Action and Temporal Hallucinations in Video-Language Models2026
- AVTrustBench: Assessing and Enhancing Reliability and Robustness in Audio-Visual LLMs2025
- LongVALE: Vision-Audio-Language-Event Benchmark Towards Time-Aware Omni-Modal Perception of Long Videos2025
- InternVideo2: Scaling Foundation Models for Multimodal Video Understanding2024
- VideoAgent: Long-Form Video Understanding with Large Language Model as Agent2024
- From Pixels to Graphs: Open-Vocabulary Scene Graph Generation with Vision-Language Models2024
- VideoLLM-online: Online Video Large Language Model for Streaming Video2024
- Intern VL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks2024