9 papers
SWE-Ladder: Learning to Localize, Reproduce, and Patch via Progressive Privileged Self-Distillation
Xudong Cai, Zhengxi Lu, Yuchen Yan +4
Resolving a repository-level issue typically requires a software-engineering (SWE) agent to localize the faulty code, reproduce the failure, and patch the code. Reinforcement learn…
Scalable Training of Mixture-of-Experts Models with Megatron Core
Zijie Yan, Hongxiao Bai, Xin Yao +42
Scaling Mixture-of-Experts (MoE) training introduces systems challenges absent in dense models. Because each token activates only a subset of experts, this sparsity allows total pa…
InftyThink+: Effective and Efficient Infinite-Horizon Reasoning via Reinforcement Learning
Yuchen Yan, Liang Jiang, Jin Jiang +7
Large reasoning models achieve strong performance by scaling inference-time chain-of-thought, but this paradigm suffers from quadratic cost, context length limits, and degraded rea…
LAPO: Internalizing Reasoning Efficiency via Length-Adaptive Policy Optimization
Xingyu Wu, Yuchen Yan, Shangke Lyu +7
Large reasoning models have achieved remarkable performance through extended chain-of-thought sequences, yet this computational freedom leads to excessive token generation even for…
VerifyBench: Benchmarking Reference-based Reward Systems for Large Language Models
Yuchen Yan, Jin Jiang, Zhenbang Ren +9
Large reasoning models such as OpenAI o1 and DeepSeek-R1 have demonstrated remarkable performance in complex reasoning tasks. A critical component of their training is the incorpor…
Let LRMs Break Free from Overthinking via Self-Braking Tuning
Haoran Zhao, Yuchen Yan, Yongliang Shen +7
Large reasoning models (LRMs), such as OpenAI o1 and DeepSeek-R1, have significantly enhanced their reasoning capabilities by generating longer chains of thought, demonstrating out…
InftyThink: Breaking the Length Limits of Long-Context Reasoning in Large Language Models
Yuchen Yan, Yongliang Shen, Yang Liu +4
Advanced reasoning in large language models has achieved remarkable performance on challenging tasks, but the prevailing long-context reasoning paradigm faces critical limitations:…
MathFimer: Enhancing Mathematical Reasoning by Expanding Reasoning Steps through Fill-in-the-Middle Task
Yuchen Yan, Yongliang Shen, Yang Liu +5
Mathematical reasoning represents a critical frontier in advancing large language models (LLMs). While step-by-step approaches have emerged as the dominant paradigm for mathematica…
S^3cMath: Spontaneous Step-level Self-correction Makes Large Language Models Better Mathematical Reasoners
Yuchen Yan, Jin Jiang, Yang Liu +5
Self-correction is a novel method that can stimulate the potential reasoning abilities of large language models (LLMs). It involves detecting and correcting errors during the infer…