AITP: Traffic Accident Responsibility Allocation via Multimodal Large Language Models

• URL: http://arxiv.org/abs/2604.20878v1
• Date: Sat, 11 Apr 2026 09:38:45 GMT
• Title: AITP: Traffic Accident Responsibility Allocation via Multimodal Large Language Models
• Abstract summary: We introduce AITP (Artificial Intelligence Traffic Police), a multimodal large language model for responsibility reasoning and allocation.<n>We present DecaTARA, a decathlon-style benchmark unifying ten interrelated traffic accident reasoning tasks with 67,941 annotated videos and 195,821 question-answer pairs.
• Score: 3.6393796347315974
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable progress in Traffic Accident Detection (TAD) and Traffic Accident Understanding (TAU). However, existing studies mainly focus on describing and interpreting accident videos, leaving room for deeper causal reasoning and integration of legal knowledge. Traffic Accident Responsibility Allocation (TARA) is a more challenging task that requires multi-step reasoning grounded in traffic regulations. To address this, we introduce AITP (Artificial Intelligence Traffic Police), a multimodal large language model for responsibility reasoning and allocation. AITP enhances reasoning via a Multimodal Chain-of-Thought (MCoT) mechanism and integrates legal knowledge through Retrieval-Augmented Generation (RAG). We further present DecaTARA, a decathlon-style benchmark unifying ten interrelated traffic accident reasoning tasks with 67,941 annotated videos and 195,821 question-answer pairs. Extensive experiments show that AITP achieves state-of-the-art performance across responsibility allocation, TAD, and TAU tasks, establishing a new paradigm for reasoning-driven multimodal traffic analysis.

Related papers

• UniTraffic-Agent: Unified Traffic Video Reasoning for AI City Challenge 2026 Track 3 with Two Out-of-Domain Evaluations [87.58552218939225]
  We introduce UniTraffic-Agent, the MR-CAS solution for Track3 of the 10th AI City Challenge.<n>UniTraffic-Agent follows an observe--reason--act-verify workflow that samples timestamped visual evidence.<n>On the official Public leaderboards, MR-CAS ranks 16th on TAR with a score of 0.5780, 2nd on FETV with 0.4884, and 4th on PSI-VQA with 64.4161.
  arXiv  Detail & Related papers  (2026-08-13T10:00:27Z)
• Responsibility Distribution Estimation in Ego-View Accident Videos with Multimodal Large Language Models [2.0339465062586566]
  ego-view accident videos represent the driver's visual perspective, making them suitable for reasoning about avoidability and driver responsibility.<n>We introduce responsibility distribution estimation for ego-view traffic accident videos, a new task in which a model predicts the percentage of responsibility assigned to each involved agent.<n>Our findings suggest that ego-centric accident videos provide a promising foundation for socially and legally meaningful multimodal reasoning.
  arXiv  Detail & Related papers  (2026-07-03T20:23:05Z)
• TrafficRAG: A Multimodal RAG Framework for Traffic Accident Liability Determination [8.432460382640143]
  Existing methods often suffer from low efficiency, subjective judgment, and inconsistent analysis results.<n>This work presents TrafficRAG, a multimodal retrieval-augmented framework for automated traffic accident analysis and report generation.
  arXiv  Detail & Related papers  (2026-06-01T06:01:04Z)
• ExpressMind: A Multimodal Pretrained Large Language Model for Expressway Operation [15.229240986097304]
  This paper constructs a pre-trained multimodal large language model (MLLM) for expressways, ExpressMind, which serves as the cognitive core for intelligent expressway operations.<n>This paper constructs the industry's first full-stack expressway dataset, encompassing traffic knowledge texts, emergency reasoning chains, and annotated video events.<n>Experiments on our newly released multi-modal expressway benchmark demonstrate that ExpressMind comprehensively outperforms existing baselines in event detection, safety response generation, and complex traffic analysis.
  arXiv  Detail & Related papers  (2026-03-17T13:22:53Z)
• DriveCombo: Benchmarking Compositional Traffic Rule Reasoning in Autonomous Driving [34.19974984127512]
  We present DriveCombo, a text-based benchmark for compositional traffic rule reasoning.<n>Inspired by human drivers' cognitive development, we propose a systematic Five-Level Cognitive Ladder.<n>We also propose a Rule2Scene Agent that maps language-based traffic rules to dynamic driving scenes.
  arXiv  Detail & Related papers  (2026-03-02T09:12:40Z)
• RoadSceneVQA: Benchmarking Visual Question Answering in Roadside Perception Systems for Intelligent Transportation System [15.222742182076459]
  RoadSceneVQA is a large-scale visual question answering dataset specifically tailored for roadside scenarios.<n>The dataset comprises 34,736 diverse QA pairs collected under varying weather, illumination, and traffic conditions.<n>RoadSceneVQA challenges models to perform both explicit recognition and implicit commonsense reasoning.
  arXiv  Detail & Related papers  (2025-11-23T04:40:50Z)
• Traffic-MLLM: A Spatio-Temporal MLLM with Retrieval-Augmented Generation for Causal Inference in Traffic [8.754321713184483]
  We propose Traffic-LM, a multimodal large language model tailored for fine-grained traffic analysis.<n>Our model leverages high-quality traffic-specific multimodal datasets and uses LowRanktemporal Adaptation (LoRA) for lightweight fine-tuning.<n>We also introduce an innovative knowledge module fusing Chain-of-the-art reasoning with Retrieval-Lomented Generation (LoRAG)
  arXiv  Detail & Related papers  (2025-09-14T08:53:06Z)
• VL-Cogito: Progressive Curriculum Reinforcement Learning for Advanced Multimodal Reasoning [69.44871115752055]
  We propose an advanced multimodal reasoning model trained via a novel Progressive Curriculum Reinforcement Learning (PCuRL) framework.<n>PCuRL systematically guides the model through tasks of gradually increasing difficulty, substantially improving its reasoning abilities across diverse multimodal contexts.<n>The framework introduces two key innovations: (1) an online difficulty soft weighting mechanism, dynamically adjusting training difficulty across successive RL training stages; and (2) a dynamic length reward mechanism, which encourages the model to adaptively regulate its reasoning path length according to task complexity.
  arXiv  Detail & Related papers  (2025-07-30T12:23:21Z)
• Progressive Multimodal Reasoning via Active Retrieval [64.74746997923967]
  Multi-step multimodal reasoning tasks pose significant challenges for large language models (MLLMs)<n>We propose AR-MCTS, a universal framework designed to progressively improve the reasoning capabilities of MLLMs.<n>We show that AR-MCTS can optimize sampling diversity and accuracy, yielding reliable multimodal reasoning.
  arXiv  Detail & Related papers  (2024-12-19T13:25:39Z)
• Thought Propagation: An Analogical Approach to Complex Reasoning with Large Language Models [62.96551299003463]
  We propose textbftextitThought Propagation (TP) to enhance the complex reasoning ability of Large Language Models. TP first prompts LLMs to propose and solve a set of analogous problems that are related to the input one. TP reuses the results of analogous problems to directly yield a new solution or derive a knowledge-intensive plan for execution to amend the initial solution obtained from scratch.
  arXiv  Detail & Related papers  (2023-10-06T01:40:09Z)
• A Study of Situational Reasoning for Traffic Understanding [63.45021731775964]
  We devise three novel text-based tasks for situational reasoning in the traffic domain. We adopt four knowledge-enhanced methods that have shown generalization capability across language reasoning tasks in prior work. We provide in-depth analyses of model performance on data partitions and examine model predictions categorically.
  arXiv  Detail & Related papers  (2023-06-05T01:01:12Z)
• Intelligent Traffic Monitoring with Hybrid AI [78.65479854534858]
  We introduce HANS, a neuro-symbolic architecture for multi-modal context understanding. We show how HANS addresses the challenges associated with traffic monitoring while being able to integrate with a wide range of reasoning methods.
  arXiv  Detail & Related papers  (2022-08-31T17:47:22Z)

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.