Don't Make the LLM Read the Graph: Make the Graph Think
不要让大语言模型读图:让图思考
机构 * Mindoverflow ; University of Waterloo(多伦多大学) ; Carnegie Mellon University(卡内基梅隆大学) ; Foothill College(foothill学院) ; Purdue University(普渡大学) ; University of Wisconsin(威斯康星大学) ; Apple(苹果公司)
AI总结 通过3000多次对照实验,研究显式信念图在合作多智能体推理中是否提升LLM性能,发现集成架构决定图的价值,识别出“规划者违抗”现象,并证明图深度收益递减。
Comments main body has 9 pages, 4 figures, under review for COLM 2026 conference