Xiaomi MiMo · 5 records

dateidtitleauthorsvenue↑
2026-11-022610.40256When Requirements Interact: Scaling Long-Horizon Coding via Interdependent SpecificationsYishuo Cai et al.arXiv10
2026-10-092610.11959MiMo-V2.6: Scaling Reinforcement Learning Towards Self-ImprovementCore Team et al.arXiv87
2026-09-292609.32577Groupwise Agentic Grading and Advantage Redistribution for Code Agent RLJinhao Dong et al.arXiv45
2026-09-212609.22068CodeMidas: Scaling Agentic Coding RL Environments from Code ItselfBowen Ye et al.arXiv129
2026-07-012606.30406MOPD: Multi-Teacher On-Policy Distillation for Capability Integration in LLM Post-TrainingWenhan Ma et al.arXiv29