paper-with-me

Papers

ELLMPEG: An Edge-based Agentic LLM Video Processing Tool

2026-01-17 · Zoha Azimi, Reza Farahani, Radu Prodan, Christian Timmerer arxiv

Large language models (LLMs), the foundation of generative AI systems like ChatGPT, are transforming many fields and applications, including multimedia, enabling more advanced content generation, analysis, and interaction. However, cloud-based LLM deployments face three key limitations: high computational and energy demands, privacy and reliability risks from remote processing, and recurring API costs. Recent advances in agentic AI, especially in structured reasoning and tool use, offer a better way to exploit open and locally deployed tools and LLMs. This paper presents ELLMPEG, an edge-enabled agentic LLM framework for the automated generation of video-processing commands. ELLMPEG integrates tool-aware Retrieval-Augmented Generation (RAG) with iterative self-reflection to produce and locally verify executable FFmpeg and VVenC commands directly at the edge, eliminating reliance on external cloud APIs. To evaluate ELLMPEG, we collect a dedicated prompt dataset comprising 480 diverse queries covering different categories of FFmpeg and the Versatile Video Codec (VVC) encoder (VVenC) commands. We validate command generation accuracy and evaluate four open-source LLMs based on command validity, tokens generated per second, inference time, and energy efficiency. We also execute the generated commands to assess their runtime correctness and practical applicability. Experimental results show that Qwen2.5, when augmented with the ELLMPEG framework, achieves an average command-generation accuracy of 78 % with zero recurring API cost, outperforming all other open-source models across both the FFmpeg and VVenC datasets.

📄 PDF Abstract BibTeX arXiv:2602.00028

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

PyVision-RL: Forging Open Agentic Vision Models via RL

2026-02-24 · Shitian Zhao, Shaoheng Lin, Ming Li, Haoquan Zhang 외 arxiv

Reinforcement learning for agentic multimodal models often suffers from interaction collapse, where models learn to reduce tool usage and multi-turn reasoning, limiting the benefits of agentic behavior. We introduce PyVi…

Reinforcement Learning

MemDreamer: Decoupling Perception and Reasoning for Long Video Understanding via Hierarchical Graph Memory and Agentic Retrieval Mechanism

2026-06-05 · Cong Chen, Guo Gan, Kaixiang Ji, ZhaoYang Zhang 외 arxiv

Current Vision-Language Models struggle with hours-long videos because processing full-length visual sequences induces prohibitive token explosion and attention dilution. To overcome this, we introduce MemDreamer to deco…

VideoARM: Agentic Reasoning over Hierarchical Memory for Long-Form Video Understanding

2025-12-13 · Yufei Yin, Qianke Meng, Minghao Chen, Jiajun Ding 외 arxiv

Long-form video understanding remains challenging due to the extended temporal structure and dense multimodal cues. Despite recent progress, many existing approaches still rely on hand-crafted reasoning pipelines or empl…

VideoThinker: Building Agentic VideoLLMs with LLM-Guided Tool Reasoning

2026-01-22 · Chenglin Li, Qianglong Chen, Feng Han, Yikun Wang 외 arxiv

Long-form video understanding remains a fundamental challenge for current Video Large Language Models. Most existing models rely on static reasoning over uniformly sampled frames, which weakens temporal localization and …

LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling

2025-11-25 · Zuhao Yang, Sudong Wang, Kaichen Zhang, Keming Wu 외 arxiv

Large multimodal models (LMMs) have shown great potential for video reasoning with textual Chain-of-Thought. However, they remain vulnerable to hallucinations, especially when processing long-form videos where evidence i…

Reinforcement Learning