Luong

The paper introduces FragBench, a novel benchmark designed to detect malicious LLM attacks that are split across multiple, seemingly benign sessions, showing that cross-session graph modeling is necessary for effective defense.

This paper re-examines the role of temperature ($ au$) in LLM distillation, demonstrating that while Reverse KL (RKL) is often preferred, Forward KL (FKL) significantly outperforms RKL at higher temperatures, overturning standard empirical conclusions.

The paper evaluates dynamic coordination strategy selection for enterprise multi-agent systems, finding that a calibrated default routing approach is effective, even if a deterministic winner-selection law is not supported.