Tag
This paper distinguishes tool use from tool discovery in LLM agents, decomposing discovery into curiosity, recognition, and efficiency. It introduces the Lomekwi framework and demonstrates inverse scaling of recognition with model size in combinatorial games.
This academic paper challenges the effectiveness of long-context scaling in time series forecasting, demonstrating that retrieval-based methods outperform standard architectures like PatchTST and foundation models such as Chronos and Moirai.