AI๊ฐ ์์ง์ด๊ณ ๋ฏธ๋๊ฐ ์
๋ฐ์ดํธ๋ฉ๋๋ค.MiMo-V2.6-Pro-MOPD
> [!IMPORTANT] > **This is the MOPD upgrade of the MiMo-V2.6-Pro-RL checkpoint.** > > - **MOPD2** (๐ **Technical Report ยง5.6**) > Fuses several domain-specialized teachers into one model, extending to domains where reliable training-time verification is hard, such as long-horizon game development, scientific research and embodied intelligence. > - **Diagnosing and Mitigating Tool-Call Repetition in MiMo-V2.6** (๐ **Technical Blog**) > An easy-to-overlook failure mode in which the model keeps issuing the same or highly similar tool calls, appearing busy while making no progress. Nothing fails outright, so it tends to go unnoticed. The MOPD stage handles it efficiently, with a short specialized-teacher run that converges quickly. MOPD2 distills several domain-specialized teachers into the student on-policy. The teachers fall into two families: **mixRL teachers**, trained on verifiable tasks, and **SFT teachers**, trained on synthetic demonstrations for open-domain tasks where a reliable reward is hard to design. Three streams contribute to a single update: Following the release of MiMo-V2.6, tool-call repetition emerged as one of the most noticeable issues in agentic settings: the model would sometimes issue the same or highly similar tool calls repeatedly, consuming time and context without making progress. This checkpoint mitigates it.
๋ฒ์ญ ์ค๋น ์ค์ ๋๋ค. ์๋ฌธ์ ํ์ํฉ๋๋ค.
> [!IMPORTANT] > **This is the MOPD upgrade of the MiMo-V2.6-Pro-RL checkpoint.** > > - **MOPD2** (๐ **Technical Report ยง5.6**) > Fuses several domain-specialized teachers into one model, extending to domains where reliable training-time verification is hard, such as long-horizon game development, scientific research and embodied intelligence. > - **Diagnosing and Mitigating Tool-Call Repetition in MiMo-V2.6** (๐ **Technical Blog**) > An easy-to-overlook failure mode in which the model keeps issuing the same or highly similar tool calls, appearing busy while making no progress. Nothing fails outright, so it tends to go unnoticed. The MOPD stage handles it efficiently, with a short specialized-teacher run that converges quickly. MOPD2 distills several domain-specialized teachers into the student on-policy. The teachers fall into two families: **mixRL teachers**, trained on verifiable tasks, and **SFT teachers**, trained on synthetic demonstrations for open-domain tasks where a reliable reward is hard to design. Three streams contribute to a single update: Following the release of MiMo-V2.6, tool-call repetition emerged as one of the most noticeable issues in agentic settings: the model would sometimes issue the same or highly similar tool calls repeatedly, consuming time and context without making progress. This checkpoint mitigates it.