Tweet by ZhangWeiHong9

December 30, 2025

🚀 Single-agent coding assistants hit a wall on long-horizon tasks. Even frontier AI IDEs like Claude Code rely on manual sub-agent design—which is tedious and suboptimal. What if we could discover the optimal agent hierarchy automatically? Introducing BOAD: Bandit Optimization for Agent Design. 🔥 Outperforms GPT-4 & Claude-3.7-Sonnet (36B model) 🤖 Uses Multi-Armed Bandits for principled agent discovery Stop guessing prompts. Start optimizing. 🧵👇 This work is led by @iris_j_xu during her internship at MIT-IBM Watson AI Lab. Paper: https://t.co/U576P0979m Code: https://t.co/R2FfcBoSKu #LLM #RL #AIagents #CodingAgents #MultiArmedBandit

Author
ZhangWeiHong9
Date
December 30, 2025
Open on X