10 papers
DRIFT: Difficulty Routing Self-DIstillation with Rhythm-Gated Exploration and Success BuFfer Training
Haisen Luo, Yiwei Liu, Haoning Wang +13
Enabling large language models to achieve stable self-improvement without external expert supervision remains a central challenge in complex reasoning tasks. Existing self-distilla…
ASTRA: Automated Synthesis of agentic Trajectories and Reinforcement Arenas
Xiaoyu Tian, Haotian Wang, Shuaiting Chen +12
Large language models (LLMs) are increasingly used as tool-augmented agents for multi-step decision making, yet training robust tool-using agents remains challenging. Existing meth…
AM-Thinking-v1: Advancing the Frontier of Reasoning at 32B Scale
Yunjie Ji, Xiaoyu Tian, Sitong Zhao +5
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-…
Not All Correct Answers Are Equal: Why Your Distillation Source Matters
Xiaoyu Tian, Yunjie Ji, Haotian Wang +5
Distillation has emerged as a practical and effective approach to enhance the reasoning capabilities of open-source language models. In this work, we conduct a large-scale empirica…
DeepDistill: Enhancing LLM Reasoning Capabilities via Large-Scale Difficulty-Graded Data Training
Xiaoyu Tian, Sitong Zhao, Haotian Wang +5
Although large language models (LLMs) have recently achieved remarkable performance on various complex reasoning benchmarks, the academic community still lacks an in-depth understa…
Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study
Xiaoyu Tian, Sitong Zhao, Haotian Wang +5
Despite significant advances in long-context reasoning by large language models (LLMs), primarily through Online Reinforcement Learning (RL) methods, these approaches incur substan…