3 papers
cs.AI2026
OPE: Overcoming Information Saturation in Parallel Thinking via Outline-Guided Path Exploration
Qi Guo, Jianing Wang, Deyang Kong +7
Parallel thinking has emerged as a new paradigm for large reasoning models (LRMs) in tackling complex problems. Recent methods leverage Reinforcement Learning (RL) to enhance paral…
cs.LG2026
Rethinking the Sampling Criteria in Reinforcement Learning for LLM Reasoning: A Competence-Difficulty Alignment Perspective
Deyang Kong, Qi Guo, Xiangyu Xi +5
Reinforcement learning exhibits potential in enhancing the reasoning abilities of large language models, yet it is hard to scale for the low sample efficiency during the rollout ph…
cs.CL2025
SampleMix: A Sample-wise Pre-training Data Mixing Strategey by Coordinating Data Quality and Diversity
Xiangyu Xi, Deyang Kong, Jian Yang +7
Existing pretraining data mixing methods for large language models (LLMs) typically follow a domain-wise methodology, a top-down process that first determines domain weights and th…