8 papers
Document Reconstruction Unlocks Scalable Long-Context RLVR
Yao Xiao, Lei Wang, Yue Deng +6
Reinforcement Learning with Verifiable Rewards~(RLVR) has become a prominent paradigm to enhance the capabilities (i.e.\ long-context) of Large Language Models~(LLMs). However, it…
From Perception to Action: An Interactive Benchmark for Vision Reasoning
Yuhao Wu, Maojia Song, Yihuai Lan +8
Understanding the physical structure is essential for real-world applications such as embodied agents, interactive design, and long-horizon manipulation. Yet, prevailing Vision-Lan…
DeepResearchEval: An Automated Framework for Deep Research Task Construction and Agentic Evaluation
Yibo Wang, Lei Wang, Yue Deng +7
Deep research systems are widely used for multi-step web research, analysis, and cross-source synthesis, yet their evaluation remains challenging. Existing benchmarks often require…
First Try Matters: Revisiting the Role of Reflection in Reasoning Models
Liwei Kang, Yue Deng, Yao Xiao +3
Large language models have recently demonstrated significant gains in reasoning ability, often attributed to their capacity to generate longer chains of thought and engage in refle…
Revisiting Self-Play Preference Optimization: On the Role of Prompt Difficulty
Yao Xiao, Jung-jae Kim, Roy Ka-wei Lee +1
Self-play preference optimization has emerged as a prominent paradigm for aligning large language models (LLMs). It typically involves a language model to generate on-policy respon…
MiroMind-M1: An Open-Source Advancement in Mathematical Reasoning via Context-Aware Multi-Stage Policy Optimization
Xingxuan Li, Yao Xiao, Dianwen Ng +15
Large language models have recently evolved from fluent text generation to advanced reasoning across diverse domains, giving rise to reasoning language models. Among these domains,…
100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Models
Chong Zhang, Yue Deng, Xiang Lin +8
The recent development of reasoning language models (RLMs) represents a novel evolution in large language models. In particular, the recent release of DeepSeek-R1 has generated wid…
Finding the Sweet Spot: Preference Data Construction for Scaling Preference Optimization
Yao Xiao, Hai Ye, Linyao Chen +4
Iterative data generation and model retraining are widely used to align large language models (LLMs). It typically involves a policy model to generate on-policy responses and a rew…