计算机科学与探索2026，Vol.20Issue(5)：1403-1416,14.DOI:10.3778/j.issn.1673-9418.2508069
RCRQ:面向交通事故文本的多智能体信息抽取框架
RCRQ:Multi-agent Information Extraction Framework for Traffic Accident Texts
摘要
Abstract
Building on the police traffic authority's reliance on textual evidence for handling and regulating autonomous-vehicle(AV)incidents,this paper addresses extraction challenges posed by heterogeneous report genres,frequent cross-sentence coreference,disordered timelines,and missing causal statements.This paper proposes a multi-agent entity-event-relation structured information-extraction framework that treats large language models(LLMs)as agents and produces inter-pretable,high-confidence outputs through multi-stage processing,to support knowledge-graph construction and rule mining.For the constructed Accident-Benchmark dataset,this paper generates gold annotations via a dual-model collabo-ration with human-in-the-loop(HITL)verification.Then,this paper uses progressive prompt screening to select the best performer as the single-agent baseline.This paper designs an RCRQ MA framework that enhances extraction through staged reasoning,targeted error diagnosis,iterative repair,and consistency checking,and introduces a joint distillation method that leverages both reasoning trajectories and final outputs to further reduce inference cost.Experiments show that,relative to the single-agent baseline,the RCRQ MA framework yields substantial gains:on DeepSeek-V3,F1 for enti-ties,event triggers,and event arguments improves by 1.89,7.32,and 5.75 percentage points,respectively;on GLM-4-9B,the human-evaluation average score for relation extraction increases by 0.4 on a five-point scale.Both models outperform alternative baselines,validating the effectiveness of the proposed approach.关键词
多智能体/自动驾驶事故文本/大语言模型/信息抽取/蒸馏学习Key words
multi-agent/autonomous driving accident texts/large language models/information extraction/distillation learning分类
信息技术与安全科学引用本文复制引用
史丹煜,王景升,丛浩哲,王二娜,刘明帅..RCRQ:面向交通事故文本的多智能体信息抽取框架[J].计算机科学与探索,2026,20(5):1403-1416,14.基金项目
中国人民公安大学拔尖创新人才培养经费支持研究生科研创新一般项目(2025yjsky031) （2025yjsky031）
国家重点研发计划(2023YFB4302701).This work was supported by the Top-Notch Innovative Talent Training Fund(Graduate Research Innovation General Program)of the People's Public Security University of China(2025yjsky031),and the National Key Research and Development Program of China(2023YFB4302701). （2023YFB4302701）
