12 papers
Deep Research Pretraining via Predictive Navigation
Jiang Zhou, Zhiyuan Fan, Xing Wu +3
Deep research agents are often trained on expensive, environment-grounded tool-use trajectories that require repeated retrieval, document inspection, and report evaluation. We intr…
From Blind Guess to Informed Judgment: Teaching LLMs to Evaluate Materials by Building Knowledge-Augmented Preference Signals
Yeyong Yu, Wenya Hu, Xing Wu +1
As candidate generation and high-throughput experimentation advance, the primary bottleneck in materials discovery is shifting from property prediction to making reliable evaluatio…
Toward Scalable Terminal Task Synthesis via Skill Graphs
Zhiyuan Fan, Tinghao Yu, Yuanjun Cai +8
Terminal agents have demonstrated strong potential for autonomous command-line execution, yet their training remains constrained by the scarcity of high-quality and diverse executi…
TOOLCAD: Exploring Tool-Using Large Language Models in Text-to-CAD Generation with Reinforcement Learning
Yifei Gong, Xing Wu, Wenda Liu +1
Computer-Aided Design (CAD) is an expert-level task that relies on long-horizon reasoning and coherent modeling actions. Large Language Models (LLMs) have shown remarkable advancem…
PolicyLong: Towards On-Policy Context Extension
Junlong Jia, Ziyang Chen, Xing Wu +4
Extending LLM context windows is hindered by scarce high-quality long-context data. Recent methods synthesize data with genuine long-range dependencies via information-theoretic ve…
WRAP++: Web discoveRy Amplified Pretraining
Jiang Zhou, Yunhao Wang, Xing Wu +2
Synthetic data rephrasing has emerged as a powerful technique for enhancing knowledge acquisition during large language model (LLM) pretraining. However, existing approaches operat…