# Interpretable Traffic Responsibility from Dashcam Video via Legal Multi Agent Reasoning

arXiv: https://arxiv.org/abs/2603.17930 · HTML: https://mlsanity.com/paper/2603.17930/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 25 references that are in the map.
- First posted on arXiv 18 Mar 2026.

## Builds on (most cited first, 19 of 19)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [Pretrained Transformers for Text Ranking: BERT and Beyond](https://mlsanity.com/paper/2010.06467/) (2020)
- [Self-Chained Image-Language Model for Video Localization and Question Answering](https://mlsanity.com/paper/2305.06988/) (2023)
- [Can I Trust Your Answer? Visually Grounded Video Question Answering](https://mlsanity.com/paper/2309.01327/) (2023)
- [Chatlaw: A Multi-Agent Legal Assistant based on a Role-Aligned Mixture-of-Experts Architecture](https://mlsanity.com/paper/2306.16092/) (2023)
- [SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning over Traffic Events](https://mlsanity.com/paper/2103.15538/) (2021)
- [CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsification](https://mlsanity.com/paper/2508.21046/) (2025)
- [Video Graph Transformer for Video Question Answering](https://mlsanity.com/paper/2207.05342/) (2022)
- [LION-FS: Fast & Slow Video-Language Thinker as Online Video Assistant](https://mlsanity.com/paper/2503.03663/) (2025)
- [Abductive Ego-View Accident Video Understanding for Safe Driving Perception](https://mlsanity.com/paper/2403.00436/) (2024)
- [AgentsCourt: Building Judicial Decision-Making Agents with Court Debate Simulation and Legal Knowledge Augmentation](https://mlsanity.com/paper/2403.02959/) (2024)
- [Blind Judgement: Agent-Based Supreme Court Modelling With GPT](https://mlsanity.com/paper/2301.05327/) (2023)
- [LawGPT: A Chinese Legal Knowledge-Enhanced Large Language Model](https://mlsanity.com/paper/2406.04614/) (2024)
- [Contrastive Video Question Answering via Video Graph Transformer](https://mlsanity.com/paper/2302.13668/) (2023)
- [Applicability of Large Language Models and Generative Models for Legal Case Judgement Summarization](https://mlsanity.com/paper/2407.12848/) (2024)
- [SemanticVLA: Semantic-Aligned Sparsification and Enhancement for Efficient Robotic Manipulation](https://mlsanity.com/paper/2511.10518/) (2025)
- [Vision-Language Embodiment for Monocular Depth Estimation](https://mlsanity.com/paper/2503.16535/) (2025)
- [Embodiment: Self-Supervised Depth Estimation Based on Camera Models](https://mlsanity.com/paper/2408.01565/) (2024)

## Built on by (most cited first, 1 of 1)

- [Multimodal Plant Root Phenotyping with Integration of 3D Skeleton Extraction and Language Analysis](https://mlsanity.com/paper/2608.03109/) (2026)

## Abstract (arXiv)

The widespread adoption of dashcams has made video evidence in traffic accidents increasingly abundant, yet transforming "what happened in the video" into "who is responsible under which legal provisions" still relies heavily on human experts. Existing ego-view traffic accident studies mainly focus on perception and semantic understanding, while LLM-based legal methods are mostly built on textual case descriptions and rarely incorporate video evidence, leaving a clear gap between the two. We first propose C-TRAIL, a multimodal legal dataset that, under the Chinese traffic regulation system, explicitly aligns dashcam videos and textual descriptions with a closed set of responsibility modes and their corresponding Chinese traffic statutes. On this basis, we introduce a two-stage framework: (1) a traffic accident understanding module that generates textual video descriptions; and (2) a legal multi-agent framework that outputs responsibility modes, statute sets, and complete judgment reports. Experimental results on C-TRAIL and MM-AU show that our method outperforms general and legal LLMs, as well as existing agent-based approaches, while providing a transparent and interpretable legal reasoning process.