# Enhancing Video-LLM Reasoning via Agent-of-Thoughts Distillation

arXiv: https://arxiv.org/abs/2412.01694 · HTML: https://mlsanity.com/paper/2412.01694/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 50 of its 60 references that are in the map.
- First posted on arXiv 2 Dec 2024.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 30 of 50)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://mlsanity.com/paper/2311.16502/) (2023)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis](https://mlsanity.com/paper/2405.21075/) (2024)
- [Video-LLaVA: Learning United Visual Representation by Alignment Before Projection](https://mlsanity.com/paper/2311.10122/) (2023)
- [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024)
- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [MVBench: A Comprehensive Multi-modal Video Understanding Benchmark](https://mlsanity.com/paper/2311.17005/) (2023)
- [Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models](https://mlsanity.com/paper/2306.05424/) (2023)
- [VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs](https://mlsanity.com/paper/2406.07476/) (2024)
- [Multimodal Chain-of-Thought Reasoning in Language Models](https://mlsanity.com/paper/2302.00923/) (2023)
- [NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions](https://mlsanity.com/paper/2105.08276/) (2021)
- [ViperGPT: Visual Inference via Python Execution for Reasoning](https://mlsanity.com/paper/2303.08128/) (2023)
- [ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering](https://mlsanity.com/paper/1906.02467/) (2019)
- [LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models](https://mlsanity.com/paper/2311.17043/) (2023)
- [Visual Programming: Compositional visual reasoning without training](https://mlsanity.com/paper/2211.11559/) (2022)
- [CLEVRER: CoLlision Events for Video REpresentation and Reasoning](https://mlsanity.com/paper/1910.01442/) (2019)
- [TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding](https://mlsanity.com/paper/2312.02051/) (2023)
- [Scaling Open-Vocabulary Object Detection](https://mlsanity.com/paper/2306.09683/) (2023)
- [Perception Test: A Diagnostic Benchmark for Multimodal Video Models](https://mlsanity.com/paper/2305.13786/) (2023)
- [Simple Open-Vocabulary Object Detection with Vision Transformers](https://mlsanity.com/paper/2205.06230/) (2022)

## Built on by (most cited first, 30 of 37)

- [Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems](https://mlsanity.com/paper/2504.01990/) (2025)
- [Thinking With Videos: Multimodal Tool-Augmented Reinforcement Learning for Long Video Reasoning](https://mlsanity.com/paper/2508.04416/) (2025)
- [Video-Thinker: Sparking "Thinking with Videos" via Reinforcement Learning](https://mlsanity.com/paper/2510.23473/) (2025)
- [StreamAgent: Towards Anticipatory Agents for Streaming Video Understanding](https://mlsanity.com/paper/2508.01875/) (2025)
- [RL Fine-Tuning Heals OOD Forgetting in SFT](https://mlsanity.com/paper/2509.12235/) (2025)
- [Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding](https://mlsanity.com/paper/2512.05774/) (2025)
- [CoS: Chain-of-Shot Prompting for Long Video Understanding](https://mlsanity.com/paper/2502.06428/) (2025)
- [Universal Video Temporal Grounding with Generative Multi-modal Large Language Models](https://mlsanity.com/paper/2506.18883/) (2025)
- [ReWatch-R1: Boosting Complex Video Reasoning in Large Vision-Language Models through Agentic Data Synthesis](https://mlsanity.com/paper/2509.23652/) (2025)
- [RL Is Neither a Panacea Nor a Mirage: Understanding Supervised vs. Reinforcement Learning Fine-Tuning for LLMs](https://mlsanity.com/paper/2508.16546/) (2025)
- [When Thinking Drifts: Evidential Grounding for Robust Video Reasoning](https://mlsanity.com/paper/2510.06077/) (2025)
- [UniVA: Universal Video Agent towards Open-Source Next-Generation Video Generalist](https://mlsanity.com/paper/2511.08521/) (2025)
- [Learning to Pose Problems: Reasoning-Driven and Solver-Adaptive Data Synthesis](https://mlsanity.com/paper/2511.09907/) (2025)
- [CountGD++: Generalized Prompting for Open-World Counting](https://mlsanity.com/paper/2512.23351/) (2025)
- [Think, Then Verify: A Hypothesis-Verification Multi-Agent Framework for Long Video Understanding](https://mlsanity.com/paper/2603.04977/) (2026)
- [Debunk and Infer: Multimodal Fake News Detection via Diffusion-Generated Evidence and LLM Reasoning](https://mlsanity.com/paper/2506.21557/) (2025)
- [Merge-of-Thought Distillation](https://mlsanity.com/paper/2509.08814/) (2025)
- [Video-STR: Reinforcing MLLMs in Video Spatio-Temporal Reasoning with Relation Graph](https://mlsanity.com/paper/2510.10976/) (2025)
- [FineQuest: Adaptive Knowledge-Assisted Sports Video Understanding via Agent-of-Thoughts Reasoning](https://mlsanity.com/paper/2509.11796/) (2025)
- [Video-Skill-CoT: Skill-based Chain-of-Thoughts for Domain-Adaptive Video Reasoning](https://mlsanity.com/paper/2506.03525/) (2025)
- [CoTasks: Chain-of-Thought based Video Instruction Tuning Tasks](https://mlsanity.com/paper/2507.13609/) (2025)
- [NeMo: Needle in a Montage for Video-Language Understanding](https://mlsanity.com/paper/2509.24563/) (2025)
- [Find, Fix, Reason: Context Repair for Video Reasoning](https://mlsanity.com/paper/2604.16243/) (2026)
- [CurEvo: Curriculum-Guided Self-Evolution for Video Understanding](https://mlsanity.com/paper/2604.26707/) (2026)
- [Deep Thought Alignment: Trajectory-Level Latent Distillation for Video Reasoning](https://mlsanity.com/paper/2608.16316/) (2026)
- [CompAgent: An Agentic Framework for Visual Compliance Verification](https://mlsanity.com/paper/2511.00171/) (2025)
- [DuoTeach: Dual Role Self-Teaching for Coarse-to-Fine Decision Coordination in Vision--Language Models](https://mlsanity.com/paper/2511.18415/) (2025)
- [Weaver: End-to-End Agentic System Training for Video Interleaved Reasoning](https://mlsanity.com/paper/2602.05829/) (2026)
- [Lightweight Structured Multimodal Reasoning for Clinical Scene Understanding in Robotics](https://mlsanity.com/paper/2509.22014/) (2025)
- [Enhancing Lightweight Vision Language Models through Group Competitive Learning for Socially Compliant Navigation](https://mlsanity.com/paper/2603.11447/) (2026)

## Abstract (arXiv)

This paper tackles the problem of video question answering (VideoQA), a task that often requires multi-step reasoning and a profound understanding of spatial-temporal dynamics. While large video-language models perform well on benchmarks, they often lack explainability and spatial-temporal grounding. In this paper, we propose Agent-of-Thoughts Distillation (AoTD), a method that enhances models by incorporating automatically generated Chain-of-Thoughts (CoTs) into the instruction-tuning process. Specifically, we leverage an agent-based system to decompose complex questions into sub-tasks, and address them with specialized vision models, the intermediate results are then treated as reasoning chains. We also introduce a verification mechanism using a large language model (LLM) to ensure the reliability of generated CoTs. Extensive experiments demonstrate that AoTD improves the performance on multiple-choice and open-ended benchmarks.