Tag
ToolSearcher is a reinforcement learning framework designed to optimize tool selection for large language models in large-scale tool repositories, using techniques such as category-constrained discrimination and event-level search modeling to improve performance in iterative search and tool composition tasks.
The author shares their past efforts to achieve efficient single-expert loading for high-quality token-level classification at scale, echoing Maxime Rivest's thoughts on the utility of domain-specific expert models.
ScaleSweep proposes a new block scale initialization method for NVFP4 post-training quantization of LLMs, achieving improved accuracy by sweeping over feasible block scale candidates. Experiments on Llama and Qwen models show it preserves over 93% of full-precision performance under aggressive quantization.