PersonaMem-v3 is introduced, a real-world-grounded benchmark and evaluation harness for omni-platform personal intelligence that evaluates whether AI agents can infer holistic user understanding from cross-platform evidence, personalize responses, rerank recommendations on social media, follow user steering through nat...
Bo-Wen Jiang, Yuan Yuan, Zhuo-Qun Hao et al.· 0 citations
Modern recommendation systems on social media platforms such as Meta must model complex social relationships, including friendships, group memberships, and creator interactions, alongside massive and heterogeneous content such as text and video. Traditional recommendation models, however, often omit these signals or tr...
Haoyu Han, Yuming Liu, Lei Huang et al.· 0 citations
Production recommender systems shape what billions of people see, and sustaining their performance requires continual optimization: as content, user behavior, and upstream models shift, the choices governing retrieval, ranking, and serving must be revisited. Traditionally, human engineers test such changes through onli...
Muhammad Azhar, Yu-Hang Zhou, Gilbert Jiang et al.· 1 citation
Ablations show that selective intervention outperforms passive bank exposure, always-on injection, advisor-only guidance, advisor-only guidance, and general retrieval, and general retrieval and that selective intervention outperforms passive bank exposure, always-on injection, advisor-only guidance, and general retriev...
EvoHarness-RL is introduced, which exposes Belief, Progress, and Experience (BPE) as policy-facing harness state and reveals two key dynamics: harness annealing, where training internalizes recurring harness-use patterns into the model policy and shifts the agent from frequent harness calls toward selective external-st...
Xuying Ning, Dongqi Fu, Tianxin Wei et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
