Latest / Models & Agents — Video Edition
Ep 194: Closed-loop agent tests show naming the right Xiangqi move succeeds in only 13.9 percent…
Models & Agents Closed-loop agent tests show naming the right Xiangqi move succeeds in only 13.9 percent of trials once an engine defender responds. What You Need to Know: Today's arXiv releases include XiangqiBench exposing large gaps between static move naming and actual closed-loop wins for frontier LLMs, HakemBench a Turkish typed-decision benchmark with 2,346 items, and SymCE a corpus of 4,707 false conjectures paired with Python verifiers that reveals an imitation trap under supervised fine-tuning. FinDialogLens demonstrates a hybrid pipeline reaching 92.1 percent accuracy on final…
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.