🎉 Our paper “𝐻𝑜𝑤 𝑡𝑜 𝑇𝑟𝑎𝑖𝑛 𝑌𝑜𝑢𝑟 𝐿𝐿𝑀 𝑊𝑒𝑏 𝐴𝑔𝑒𝑛𝑡: 𝐴 𝑆𝑡𝑎𝑡𝑖𝑠𝑡𝑖𝑐𝑎𝑙 𝐷𝑖𝑎𝑔𝑛𝑜𝑠𝑖𝑠” got an 𝐨𝐫𝐚𝐥 at next week’s 𝗜𝗖𝗠𝗟 𝗪𝗼𝗿𝗸𝘀𝗵𝗼𝗽 𝗼𝗻 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿 𝗨𝘀𝗲 𝗔𝗴𝗲𝗻𝘁𝘀! 🖥️🧠 We present the 𝐟𝐢𝐫𝐬𝐭 𝐥𝐚𝐫𝐠𝐞-𝐬𝐜𝐚𝐥𝐞 𝐬𝐭𝐮𝐝𝐲 𝐨𝐟 𝐜𝐨𝐦𝐩𝐮𝐭𝐞 𝐭𝐫𝐚𝐝𝐞-𝐨𝐟𝐟𝐬 between pure SFT, pure RL, and hybrid SFT+RL for multi-step agents. SFT ➡️ RL pushes the Pareto front — and it's the 𝐨𝐧𝐥𝐲 strategy that closes the gap with closed models! 👇🧵