12 papers
DataFoundry: Evolving Data Preparators via Recursive Self-Improvement
Cehao Yang, Xiaojun Wu, Xueyuan Lin +4
Domain adaptation of large language models increasingly depends on constructing high-quality training data, yet existing data-preparation pipelines typically address quality only a…
Envs-FORGE: Frontier-Optimized Reward-Grounded Environment Synthesis for Agent RL
Xiaojun Wu, Cehao Yang, Honghao Liu +7
Reinforcement learning (RL) for terminal agents needs executable training environments with reliable rewards and useful difficulty. Fixed recipes such as few-shot, Self-Instruct, a…
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…
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…
RETuning: Upgrading Inference-Time Scaling for Stock Movement Prediction with Large Language Models
Xueyuan Lin, Cehao Yang, Ye Ma +7
Recently, large language models (LLMs) have demonstrated outstanding reasoning capabilities on mathematical and coding tasks. However, their application to financial tasks-especial…
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…
GraphSearch: An Agentic Deep Searching Workflow for Graph Retrieval-Augmented Generation
Cehao Yang, Xiaojun Wu, Xueyuan Lin +6
Graph Retrieval-Augmented Generation (GraphRAG) enhances factual reasoning in LLMs by structurally modeling knowledge through graph-based representations. However, existing GraphRA…
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…
Financial Wind Tunnel: A Retrieval-Augmented Market Simulator
Bokai Cao, Xueyuan Lin, Yiyan Qi +3
Market simulator tries to create high-quality synthetic financial data that mimics real-world market dynamics, which is crucial for model development and robust assessment. Despite…
LongFaith: Enhancing Long-Context Reasoning in LLMs with Faithful Synthetic Data
Cehao Yang, Xueyuan Lin, Chengjin Xu +5
Despite the growing development of long-context large language models (LLMs), data-centric approaches relying on synthetic data have been hindered by issues related to faithfulness…