Author

Levina Li

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Sep 2026

Privacy-Preserving Topology-Guided Safety for LLM-Based Multi-Agent Systems via Federated Graph Learning

On Agent-SafetyBench, R-Judge, and AgentDojo, federated FGLGuard exceeds the in-domain centralized ceiling on all three benchmarks without pooling any data---where unsupervised anomaly guards and local-only training fail.

Jin-Xi Yu, E. Jiang, Levina Li et al. · 0 citations

#artificial intelligence Preprint Sep 2026

Codebook Agent: Amortized Topology Design for LLM Multi-Agent Systems

Codebook Agent is the most accurate method on all six benchmarks the authors compare, and an MLP proxy that reads the flattened adjacency, regressed on measured utility and per-task normalized token cost, reranks the top decoded candidates in a single batched forward pass.

Jin-Xi Yu, Yubei Li, E. Jiang et al. · 1 citation