arXiv (All)
open access
MiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement
Reinforcement learning (RL) is the central training paradigm for advancing large foundation models towards self-improvement. This report introduces the MiMo-V2.6 series, an omni-modal family that pushes the frontier of model intelligence by scaling RL compute. Prior to RL, we conduct mid-training on
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- ACCRUE: Continual Off-Policy Reinforcement Learning for Robot Foundation Models#1344096
- Model-based Bootstrap for Offline Policy Evaluation in Tabular Reinforcement Learning#1034150
- Model-based Bootstrap for Offline Policy Evaluation in Tabular Reinforcement Learning#978449
- HiRE: Hindsight Reward Editing for Policy Finetuning#1063279
- Adaptive Expert Guidance for Efficient On-Policy Reinforcement Learning#1202438
Record · ID 1249239
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive