14 papers
Rethinking Data Curation in LLM Training: Online Reweighting Offers Better Generalization than Offline Methods
Wanru Zhao, Yihong Chen, Yuzhi Tang +6
Data curation is a critical yet under-explored area in large language model (LLM) training. Existing methods, such as data selection and mixing, operate in an offline paradigm, det…
HELP: HyperNode Expansion and Logical Path-Guided Evidence Localization for Accurate and Efficient GraphRAG
Yuqi Huang, Ning Liao, Kai Yang +4
Large Language Models (LLMs) often struggle with inherent knowledge boundaries and hallucinations, limiting their reliability in knowledge-intensive tasks. While Retrieval-Augmente…
REDSearcher: A Scalable and Cost-Efficient Framework for Long-Horizon Search Agents
Zheng Chu, Xiao Wang, Jack Hong +11
Large language models are transitioning from generalpurpose knowledge engines to realworld problem solvers, yet optimizing them for deep search tasks remains challenging. The centr…
Why Self-Rewarding Works: Theoretical Guarantees for Iterative Alignment of Language Models
Shi Fu, Yingjie Wang, Shengchao Hu +2
Self-Rewarding Language Models (SRLMs) achieve notable success in iteratively improving alignment without external feedback. Yet, despite their striking empirical progress, the cor…
Rethinking the Role of Dynamic Sparse Training for Scalable Deep Reinforcement Learning
Guozheng Ma, Lu Li, Zilin Wang +4
Scaling neural networks has driven breakthrough advances in machine learning, yet this paradigm fails in deep reinforcement learning (DRL), where larger models often degrade perfor…
Analytic Energy-Guided Policy Optimization for Offline Reinforcement Learning
Jifeng Hu, Sili Huang, Zhejian Yang +6
Conditional decision generation with diffusion models has shown powerful competitiveness in reinforcement learning (RL). Recent studies reveal the relation between energy-function-…