collaborators

11 papers

cs.AI2026

ANDES: Agent Native Data Evolving Synthesis Tool for Autonomous Instruction Alignment

Zhengyang Zhao, Shengjie Ye, Lu Ma +3

AI agents are increasingly being tasked with automating AI research itself, particularly the critical post-training phase that transforms base LLMs into aligned assistants. However…

cs.CL2026

Training with Harnesses: On-Policy Harness Self-Distillation for Complex Reasoning

Zhengyang Zhao, Lu Ma, Wentao Zhang

Inference-time harnesses substantially improve large language models on complex reasoning tasks. However, the intrinsic capabilities of the underlying model remain unchanged by the…

cs.LG2026

DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models

Hao Liang, Zhengyang Zhao, Meiyi Qiang +22

Data-centric training has emerged as a promising direction for improving large language models (LLMs) by optimizing not only model parameters but also the selection, composition, a…

cs.LG2026

GIFT: Reconciling Post-Training Objectives via Finite-Temperature Gibbs Initialization

Zhengyang Zhao, Lu Ma, Yizhen Jiang +7

The prevailing post-training paradigm for Large Reasoning Models (LRMs) - Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL) - suffers from an intrinsic optimizat…

cs.AI2026

Learning What Reinforcement Learning Can't: Interleaved Online Fine-Tuning for Hardest Questions

Lu Ma, Hao Liang, Meiyi Qiang +9

Recent advances in large language model (LLM) reasoning have shown that sophisticated behaviors such as planning and self-reflection can emerge through reinforcement learning (RL).…

cs.CL2026

Thinking by Subtraction: Confidence-Driven Contrastive Decoding for LLM Reasoning

Lexiang Tang, Weihao Gao, Bingchen Zhao +4

Recent work on test-time scaling for large language model (LLM) reasoning typically assumes that allocating more inference-time computation uniformly improves correctness. However,…