# The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence

arXiv: https://arxiv.org/abs/2605.26494 · HTML: https://mlsanity.com/paper/2605.26494/

## Key facts

- Cited by 61 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 31 of its 45 references that are in the map.
- First posted on arXiv 26 May 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)
- Mixture-of-experts / [MoE in reinforcement learning and robotics](https://mlsanity.com/moe/moe-in-reinforcement-learning-and-robotics/)

## Builds on (most cited first, 30 of 31)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://mlsanity.com/paper/2406.01574/) (2024)
- [Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them](https://mlsanity.com/paper/2210.09261/) (2022)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints](https://mlsanity.com/paper/2305.13245/) (2023)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023)
- [DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models](https://mlsanity.com/paper/2401.06066/) (2024)
- [BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents](https://mlsanity.com/paper/2504.12516/) (2025)
- [τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environment](https://mlsanity.com/paper/2506.07982/) (2025)
- [Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces](https://mlsanity.com/paper/2601.11868/) (2026)
- [Better & Faster Large Language Models via Multi-token Prediction](https://mlsanity.com/paper/2404.19737/) (2024)
- [Auxiliary-Loss-Free Load Balancing Strategy for Mixture-of-Experts](https://mlsanity.com/paper/2408.15664/) (2024)
- [Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving](https://mlsanity.com/paper/2504.02605/) (2025)
- [HELMET: How to Evaluate Long-Context Language Models Effectively and Thoroughly](https://mlsanity.com/paper/2410.02694/) (2024)
- [WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents](https://mlsanity.com/paper/2509.06501/) (2025)
- [A Benchmark for Learning to Translate a New Language from One Grammar Book](https://mlsanity.com/paper/2309.16575/) (2023)
- [KOR-Bench: Benchmarking Language Models on Knowledge-Orthogonal Reasoning Tasks](https://mlsanity.com/paper/2410.06526/) (2024)
- [Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models](https://mlsanity.com/paper/2401.04658/) (2024)
- [DIVE: Scaling Diversity in Agentic Task Synthesis for Generalizable Tool Use](https://mlsanity.com/paper/2603.11076/) (2026)

## Built on by (most cited first, 30 of 61)

- [RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillation](https://mlsanity.com/paper/2606.11709/) (2026)
- [Loop the Loopies!](https://mlsanity.com/paper/2607.16051/) (2026)
- [Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization](https://mlsanity.com/paper/2607.22334/) (2026)
- [Beyond Function Calling: Benchmarking Tool-Using Agents under Tool-Environment Unreliability](https://mlsanity.com/paper/2606.25819/) (2026)
- [ICAE-Bench: Evaluating Coding Agents as Interactive Project Builders](https://mlsanity.com/paper/2607.21217/) (2026)
- [SHE: Trajectory-driven Safety Harness Evolution for LLM Agents](https://mlsanity.com/paper/2608.09885/) (2026)
- [HiMPO: Hindsight-Informed Memory Policy Optimization for Less-Entangled Credit in Long-Horizon Agents](https://mlsanity.com/paper/2606.16285/) (2026)
- [Self-Authored Verification Is Unreliable in Heuristic Self-Improving Agents](https://mlsanity.com/paper/2607.24300/) (2026)
- [SKT: Skill-Use Training at Scale via Verified Synthetic Data Generation](https://mlsanity.com/paper/2608.02287/) (2026)
- [LoopMTP: A looped transformer guided by latent multi-token prediction](https://mlsanity.com/paper/2608.03624/) (2026)
- [Ask Now, Use Later: Benchmarking the Proactivity Gap in Long-Lived LLM Agents](https://mlsanity.com/paper/2605.28108/) (2026)
- [VibeThinker-3B: Exploring the Frontier of Verifiable Reasoning in Small Language Models](https://mlsanity.com/paper/2606.16140/) (2026)
- [ACE: Pluggable Adaptive Context Elasticizer across Agents](https://mlsanity.com/paper/2606.31564/) (2026)
- [Antares: Foundation Models for Agentic Vulnerability Localization](https://mlsanity.com/paper/2608.02407/) (2026)
- [Knowledge-Verified Emergent Deception in LLM Agents Under Conflicting Incentives](https://mlsanity.com/paper/2608.26372/) (2026)
- [Astar: Learning to Propose Evolution Directions for Self-Evolving Industrial AI Systems](https://mlsanity.com/paper/2608.27287/) (2026)
- [RingMoClaw: An Experience-Inspired Multi-Agent Framework for Self-Evolving Research in Remote Sensing](https://mlsanity.com/paper/2609.00814/) (2026)
- [Vortex: Efficient and Programmable Sparse Attention Serving for AI Agents](https://mlsanity.com/paper/2606.06453/) (2026)
- [Interactor: Agentic RL oriented Iterative Creation for Ad Description Generation in Sponsored Search](https://mlsanity.com/paper/2606.15911/) (2026)
- [ReasoningLens: Hierarchical Visualization and Diagnostic Auditing for Large Reasoning Models](https://mlsanity.com/paper/2606.23404/) (2026)
- [ExpertPlex: A High-Goodput Disaggregated Serving System for MoE LLMs with Adaptive Persistent Kernels](https://mlsanity.com/paper/2607.18002/) (2026)
- [SyncPlan: Long-Horizon LLM Coordination with Explicit Synchronization and Adaptive Correction](https://mlsanity.com/paper/2608.01652/) (2026)
- [Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports](https://mlsanity.com/paper/2608.04682/) (2026)
- [SemaPLC: A Project-Grounded, Verification-Gated Agent Harness for PLC Code Generation](https://mlsanity.com/paper/2608.18565/) (2026)
- [QATFactory: A Versatile, Deployment-Aligned Framework for Quantization-aware Training and Distillation of LLMs](https://mlsanity.com/paper/2609.39223/) (2026)
- [OCELOT: Inference-Leakage Budgets for Privacy-Preserving LLM Agents](https://mlsanity.com/paper/2606.12341/) (2026)
- [Are LLMs Ready to Assist Physicians? PhysAssistBench for Interactive Doctor-Patient-EHR Assistance](https://mlsanity.com/paper/2606.18613/) (2026)
- [Token-Operations-Oriented Inference Optimization Techniques for Large Models](https://mlsanity.com/paper/2606.20295/) (2026)
- [Beyond a Single Judge: The Evidence-Grounded, Social-Weighted Persona Panel for Generative UI Evaluation](https://mlsanity.com/paper/2607.28439/) (2026)
- [Would You Walk to the Car Wash? Revealing the Salience Bias of Large Language Models in Commonsense Reasoning](https://mlsanity.com/paper/2607.28478/) (2026)

## Abstract (arXiv)

We introduce the MiniMax-M2 series, a family of Mixture-of-Experts language models built around the principle that mini activations can unleash maximum real-world intelligence. The flagship M2 contains 229.9B total parameters with only 9.8B activated per token. Designed end-to-end for agentic deployment, the M2 series rests on three components: (i) agent-driven data pipelines producing large-scale, verifiable trajectories across agentic coding and agentic cowork, each grounded in an executable workspace and an artifact-aligned reward; (ii) Forge, a scalable agent-native RL system that adapts to long-horizon agent trajectories, paired with windowed-FIFO scheduling, prefix-tree merging, inference optimization, and a clean training-inference-agent decoupling that supports both white-box and black-box agents; (iii) the latest M2.7 checkpoint takes an early step toward self-evolution -- autonomously debugging training runs and modifying its own scaffold. Across M2 through M2.7, this combination translates a mini-activation footprint into frontier-tier performance on agentic coding, deep search, office-task, and reasoning benchmarks.