RCRQ:面向交通事故文本的多智能体信息抽取框架OA

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.