5 papers
Relax: An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale
Liujie Zhang, Benzhe Ning, Rui Yang +8
Reinforcement learning (RL) post-training has proven effective at unlocking reasoning, self-reflection, and tool-use capabilities in large language models. As models extend to omni…
Towards Compositional Generalization of LLMs via Skill Taxonomy Guided Data Synthesis
Yifan Wei, Li Du, Xiaoyan Yu +2
Large Language Models (LLMs) and agent-based systems often struggle with compositional generalization due to a data bottleneck in which complex skill combinations follow a long-tai…
AutoTIR: Autonomous Tools Integrated Reasoning via Reinforcement Learning
Yifan Wei, Xiaoyan Yu, Yixuan Weng +3
Large Language Models (LLMs), when enhanced through reasoning-oriented post-training, evolve into powerful Large Reasoning Models (LRMs). Tool-Integrated Reasoning (TIR) further ex…
Structural Entropy Guided Agent for Detecting and Repairing Knowledge Deficiencies in LLMs
Yifan Wei, Xiaoyan Yu, Tengfei Pan +2
Large language models (LLMs) have achieved unprecedented performance by leveraging vast pretraining corpora, yet their performance remains suboptimal in knowledge-intensive domains…
SetKE: Knowledge Editing for Knowledge Elements Overlap
Yifan Wei, Xiaoyan Yu, Ran Song +2
Large Language Models (LLMs) excel in tasks such as retrieval and question answering but require updates to incorporate new knowledge and reduce inaccuracies and hallucinations. Tr…