Yuefeng Ji

Yunjie Ji, Xiaoyu Tian, Sitong Zhao et al.

We present AM-Thinking-v1, a 32B dense language model that advances the frontier of reasoning, embodying the collaborative spirit of open-source innovation. Outperforming DeepSeek-R1 and rivaling leading Mixture-of-Experts (MoE) models like Qwen3-235B-A22B and Seed1.5-Thinking, AM-Thinking-v1 achieves impressive scores of 85.3 on AIME 2024, 74.4 on AIME 2025, and 70.3 on LiveCodeBench, showcasing state-of-the-art mathematical and coding capabilities among open-source models of similar scale. Built entirely from the open-source Qwen2.5-32B base model and publicly available queries, AM-Thinking-v1 leverages a meticulously crafted post-training pipeline - combining supervised fine-tuning and reinforcement learning - to deliver exceptional reasoning capabilities. This work demonstrates that the open-source community can achieve high performance at the 32B scale, a practical sweet spot for deployment and fine-tuning. By striking a balance between top-tier performance and real-world usability, we hope AM-Thinking-v1 inspires further collaborative efforts to harness mid-scale models, pushing reasoning boundaries while keeping accessibility at the core of innovation. We have open-sourced our model on \href{https://huggingface.co/a-m-team/AM-Thinking-v1}{Hugging Face}.

Yunjie Ji, Sitong Zhao, Xiaoyu Tian et al.

Enhancing the reasoning capabilities of Large Language Models (LLMs) with efficiency and scalability remains a fundamental challenge in artificial intelligence research. This paper presents a rigorous experimental investigation into how difficulty-aware staged reinforcement learning (RL) strategies can substantially improve LLM reasoning performance. Through systematic analysis, we demonstrate that strategically selecting training data according to well-defined difficulty levels markedly enhances RL optimization. Moreover, we introduce a staged training methodology, progressively exposing models to increasingly challenging tasks, further amplifying reasoning capabilities. Our findings reveal significant cross-domain benefits when simultaneously training models on mathematical reasoning and code generation tasks. Notably, our proposed approach enables a 1.5B parameter model to achieve an accuracy of 42.3\% on the AIME-2024 benchmark, 89.5\% on the MATH-500 benchmark. These results underscore the efficacy of our method in advancing the reasoning proficiency of LLMs. We will open-source our datasets on GitHub and Hugging Face.

Rentao Gu, Zeyuan Yang, Yuefeng Ji

With the rapid development of Internet and communication systems, both in services and technologies, communication networks have been suffering increasing complexity. It is imperative to improve intelligence in communication network, and several aspects have been incorporating with Artificial Intelligence (AI) and Machine Learning (ML). Optical network, which plays an important role both in core and access network in communication networks, also faces great challenges of system complexity and the requirement of manual operations. To overcome the current limitations and address the issues of future optical networks, it is essential to deploy more intelligence capability to enable autonomous and exible network operations. ML techniques are proved to have superiority on solving complex problems; and thus recently, ML techniques have been used for many optical network applications. In this paper, a detailed survey of existing applications of ML for intelligent optical networks is presented. The applications of ML are classified in terms of their use cases, which are categorized into optical network control and resource management, and optical networks monitoring and survivability. The use cases are analyzed and compared according to the used ML techniques. Besides, a tutorial for ML applications is provided from the aspects of the introduction of common ML algorithms, paradigms of ML, and motivations of applying ML. Lastly, challenges and possible solutions of ML application in optical networks are also discussed, which intends to inspire future innovations in leveraging ML to build intelligent optical networks.