10 papers
LazyTrain: Limited-resource Allocation toward Zero-waste Yield Optimization in Large Language Model Training
Xiaojun Wu, Cehao Yang, Honghao Liu +5
Training large language models on limited hardware is increasingly a scheduling problem across GPU compute, host memory, PCIe transfer, and storage bandwidth. Existing offloading s…
Bayesian-Agent: Posterior-Guided Skill Evolution Across LLM Agent Harnesses
Xiaojun Wu, Cehao Yang, Honghao Liu +7
LLM agents increasingly rely on prompts, tools, memory, SOPs, skills, and harness feedback, yet current self-evolution pipelines often update these assets through heuristic reflect…
Memory as Action: Autonomous Context Curation for Long-Horizon Agentic Tasks
Yuxiang Zhang, Jiangming Shu, Ye Ma +3
Long-context Large Language Models, despite their expanded capacity, require careful working memory management to mitigate attention dilution during long-horizon tasks. Yet existin…
Prompt-R1: Collaborative Automatic Prompting Framework via End-to-end Reinforcement Learning
Wenjin Liu, Haoran Luo, Xueyuan Lin +5
Recently, advanced large language models (LLMs) have emerged at an increasingly rapid pace. However, when faced with complex problems, most users are often unable to provide accura…
Think-on-Graph 3.0: Efficient and Adaptive LLM Reasoning on Heterogeneous Graphs via Multi-Agent Dual-Evolving Context Retrieval
Xiaojun Wu, Cehao Yang, Xueyuan Lin +6
Graph-based Retrieval-Augmented Generation (GraphRAG) has become the important paradigm for enhancing Large Language Models (LLMs) with external knowledge. However, existing approa…
Select2Reason: Efficient Instruction-Tuning Data Selection for Long-CoT Reasoning
Cehao Yang, Xueyuan Lin, Xiaojun Wu +5
A practical approach to activate long chain-of-thoughts reasoning ability in pre-trained large language models is to perform supervised fine-tuning on instruction datasets synthesi…