Traffic collision reconstruction traditionally relies on human expertise and can be accurate, but pre-crash reconstruction is more challenging. This study develops a multi-agent AI framework that reconstructs pre-crash scenarios and infers vehicle behaviors from fragmented collision data. We propose a two-phase collaborative framework with reconstruction and reasoning stages. The system processes 277 rear-end lead vehicle deceleration (LVD) crashes from the Crash Investigation Sampling System (CISS, 2017 to 2022), integrating narrative reports, structured tabular variables, and scene diagrams. Phase I generates natural-language crash reconstructions from multimodal inputs. Phase II combines these reconstructions with Event Data Recorder (EDR) signals to (1) identify striking and struck vehicles and (2) isolate the EDR records most relevant to the collision moment, enabling inference of key pre-crash behaviors. For validation, we evaluated all LVD cases and emphasized 39 complex crashes where multiple EDR records per crash created ambiguity due to missing or conflicting data. Ground truth was set by consensus of two independent manual annotators, with a separate language model used only to flag potential conflicts for re-checking. The framework achieved 100% accuracy across 4,155 trials; three reasoning models produced identical outputs, indicating that performance is driven by the structured prompts rather than model choice. Research analysts without reconstruction training achieved 92.31% accuracy on the same 39 complex cases. Ablation tests showed that removing structured reasoning anchors reduced case-level accuracy from 99.7% to 96.5% and increased errors across multiple output dimensions. The system remained robust under incomplete inputs. This zero-shot evaluation, without domain-specific training or fine-tuning, suggests a scalable approach for AI-assisted pre-crash analysis.

翻译：传统的交通事故碰撞重建主要依赖人工经验，虽能实现精确分析，但碰撞前场景重建更具挑战性。本研究开发了一种多智能体AI框架，能够从碎片化的碰撞数据中重建碰撞前场景并推断车辆行为。我们提出了包含重建与推理两阶段的协同框架。该系统处理了来自碰撞调查抽样系统（CISS，2017-2022年）的277起追尾前车减速事故，整合了叙述报告、结构化表格变量和现场示意图。第一阶段从多模态输入生成自然语言的事故重建描述。第二阶段将这些重建描述与事件数据记录器信号相结合，以（1）识别碰撞与被撞车辆，以及（2）筛选出与碰撞时刻最相关的EDR记录，从而推断关键的碰撞前行为。为验证有效性，我们评估了所有前车减速事故案例，并重点分析了39起复杂事故——这些事故中每个碰撞存在多个EDR记录，因数据缺失或冲突而产生歧义。通过两位独立人工标注者达成共识确立真实值，并单独使用语言模型仅标记潜在冲突以供复核。该框架在4,155次试验中达到100%准确率；三种推理模型产生完全一致的输出，表明性能取决于结构化提示而非模型选择。未经重建培训的研究分析人员对相同39起复杂案例的准确率达到92.31%。消融实验显示，移除结构化推理锚点会使案例级准确率从99.7%降至96.5%，并在多个输出维度增加错误。系统在不完整输入下仍保持稳健性。这种无需领域特定训练或微调的零样本评估方法，为AI辅助的碰撞前分析提供了可扩展的解决方案。