6 papers
OpenTinker: Separating Concerns in Agentic Reinforcement Learning
Siqi Zhu, Jiaxuan You
We introduce \textsc{OpenTinker}, an open infrastructure for training large language model (LLM) agents with many LoRA-backed policies over shared execution resources. Modern agent…
Probing the Knowledge Boundary: An Interactive Agentic Framework for Deep Knowledge Extraction
Yuheng Yang, Siqi Zhu, Tao Feng +2
Large Language Models (LLMs) can be seen as compressed knowledge bases, but it remains unclear what knowledge they truly contain and how far their knowledge boundary extends. Exist…
Federated Learning and Class Imbalances
Siqi Zhu, Joshua D. Kaggie
Federated Learning (FL) enables collaborative model training across decentralized devices while preserving data privacy. However, real-world FL deployments face critical challenges…
GTAlign: Game-Theoretic Alignment of LLM Assistants for Social Welfare
Siqi Zhu, David Zhang, Pedro Cisneros-Velarde +1
Large Language Models (LLMs) have achieved remarkable progress in reasoning, yet sometimes produce responses that are suboptimal for users in tasks such as writing, information see…
Multi-Agent Evolve: LLM Self-Improve through Co-evolution
Yixing Chen, Yiding Wang, Siqi Zhu +5
Reinforcement Learning (RL) has demonstrated significant potential in enhancing the reasoning capabilities of large language models (LLMs). However, the success of RL for LLMs heav…
LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs
Yushi Bai, Jiajie Zhang, Xin Lv +6
Current long context large language models (LLMs) can process inputs up to 100,000 tokens, yet struggle to generate outputs exceeding even a modest length of 2,000 words. Through c…