一作ICLR 2026Poster· Deep Learning / Everything Else
DoVer: Intervention-Driven Auto Debugging for LLM Multi-Agent Systems
Ming Ma · Jue Zhang · Fangkai Yang · Yu Kang · Qingwei Lin · Saravan Rajmohan · Dongmei Zhang
智能体与工具OpenReview
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Ming Ma · Jue Zhang · Fangkai Yang · Yu Kang · Qingwei Lin · Saravan Rajmohan · Dongmei Zhang
Bowen Zheng · Ming Ma · Zhongqiao Lin · Tianming Yang
Large Language Models (LLMs) have demonstrated remarkable abilities, one of the most important being in-context learning (ICL). With ICL, LLMs can derive the underlying rule from a few demonstrations and provide answers that comply with the rule. Previous work hypothesized that the network create...