6 papers
The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence
MiniMax, :, Aili Chen +219
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…
In-Context Reinforcement Learning for Tool Use in Large Language Models
Yaoqi Ye, Yiran Zhao, Keyu Duan +4
While large language models (LLMs) exhibit strong reasoning abilities, their performance on complex tasks is often constrained by the limitations of their internal knowledge. A com…
GEM: A Gym for Agentic LLMs
Zichen Liu, Anya Sims, Keyu Duan +16
The training paradigm for large language models (LLMs) is moving from static datasets to experience-based learning, where agents acquire skills via interacting with complex environ…
Unnatural Languages Are Not Bugs but Features for LLMs
Keyu Duan, Yiran Zhao, Zhili Feng +9
Large Language Models (LLMs) have been observed to process non-human-readable text sequences, such as jailbreak prompts, often viewed as a bug for aligned LLMs. In this work, we pr…
Efficient Process Reward Model Training via Active Learning
Keyu Duan, Zichen Liu, Xin Mao +5
Process Reward Models (PRMs) provide step-level supervision to large language models (LLMs), but scaling up training data annotation remains challenging for both humans and LLMs. T…
Novelty-based Sample Reuse for Continuous Robotics Control
Ke Duan, Kai Yang, Houde Liu +1
In reinforcement learning, agents collect state information and rewards through environmental interactions, essential for policy refinement. This process is notably time-consuming,…