Tag
本文提出DiscernMem，一个免训练框架，通过缺陷感知记忆精炼与边界学习元记忆机制，帮助基于LLM的多智能体系统修正有缺陷的记忆并学习何时正确使用记忆，在AutoGen、CAMEL和MacNet上取得最佳平均分。
Emo-Jev is a training-free framework that uses Jev's probabilistic decision interface for text classification, decomposing tasks into atomic judgments or aggregating multiple judgment paths to improve over direct prediction, evaluated across eight sentiment, emotion, sarcasm, and humor datasets against five state-of-the-art LLMs.