Long-term memory is critical for autonomous Large Language Model (LLM) agents executing multi-session, long-horizon tasks. However, existing memories often inappropriately store, retain, or retrieve over-generalized, misattributed, or privacy-sensitive information, a problem we term memory misalignment. To study this p...
Shu-Ning Zhang, Teng-Hao Ji, Jing-Ruo Chen et al.· 0 citations
Across three LLMs, it is found that when preferences compete with task goals, a higher success rate in meeting both requirements and preferences does not mean better responses: it can come with a greater quality loss compared with responses without a profile.
Teng-Hao Ji, Qi-Chen Sun, Zhuo-Ran Lu· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.