Richard C. Suwandi(@richardcsuwandi):Excited to share PlugBO 🔌, a modular framework for agentic Bayesian optimization (BO) https://t.co/ZaHWiCT8s6 In a standard BO routine, we usually declare the surrogate family, the acquisition function, and the search bounds before the first evaluation, and we keep them fixed after that. What if, instead, we treat those choices as live slots that an LLM agent can inspect and swap?

Richard C. Suwandi

@richardcsuwandi

AI PhD @cuhksz. Co-Founder @AIDDA_institute. Co-developed OpenEvolve, Kai @driaforall for automated research & discovery. Dev ambassador @Alibaba_Qwen

参加 February 2020

422 フォロー中 1.2K ファン

Richard C. Suwandi@richardcsuwandi

2026.08.20 16:46

Excited to share PlugBO 🔌, a modular framework for agentic Bayesian optimization (BO) In a standard BO routine, we usually declare the surrogate family, the acquisition function, and the search bounds before the first evaluation, and we keep them fixed after that. What if, instead, we treat those choices as live slots that an LLM agent can inspect and swap?