SPARC:用于电路问答的多智能体系统
SPARC: A Multi-Agent System for Electrical Circuit Question Answering
AI总结:
提出SPARC多智能体系统,通过可执行的物理仿真程序进行推理,在电路问答任务上实现83%准确率,较基线提升高达58%。
摘要:
电路图问答任务需要复杂的数学推理,这对多模态大语言模型仍然具有挑战性。我们提出SPARC,一个多智能体系统,通过将推理基于可执行的物理仿真程序来回答电路图问题。SPARC使用大语言模型智能体来合成、执行和分析仿真程序,从而通过设计提高准确性和可靠性。它实现了83%的准确率,较基线绝对提升高达58%,同时支持系统性的错误诊断。
英文摘要:
Electrical circuit diagram QA tasks require complex mathematical reasoning, which remains challenging for multimodal LLMs. We present SPARC, a multi-agent system that answers questions over circuit diagrams by grounding reasoning in executable physics-based simulations. SPARC uses LLM agents to synthesize, execute, and analyze simulation programs, improving accuracy and reliability by design. It achieves 83% accuracy, with up to a 58% absolute improvement over baselines, while enabling systematic error diagnosis.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。