13 papers
PracRepair: LLM-Empowered Automated Program Repair Inspired by Human-Like Debugging Practices
Yu Cheng, Zhongxin Liu, Zhenchang Xing +3
As software systems grow in scale and complexity, debugging and repair remain costly and time-consuming. Large language models (LLMs) have advanced automated program repair (APR),…
Let the Abyss Stare Back Adaptive Falsification for Autonomous Scientific Discovery
Peiran Li, Fangzhou Lin, Shuo Xing +5
Autonomous scientific discovery is entering a more dangerous regime: once the evaluator is frozen, a sufficiently strong search process can learn to win the exam without learning t…
Pretraining Large Language Models with NVFP4
NVIDIA, Felix Abecassis, Anjulie Agrusa +87
Large Language Models (LLMs) today are powerful problem solvers across many domains, and they continue to get stronger as they scale in model size, training set size, and training…
Traversal-as-Policy: Log-Distilled Gated Behavior Trees as Externalized, Verifiable Policies for Safe, Robust, and Efficient Agents
Peiran Li, Jiashuo Sun, Fangzhou Lin +5
Autonomous LLM agents fail because long-horizon policy remains implicit in model weights and transcripts, while safety is retrofitted post hoc. We propose Traversal-as-Policy: dist…
SolAgent: A Specialized Multi-Agent Framework for Solidity Code Generation
Wei Chen, Zhiyuan Peng, Xin Yin +4
Smart contracts are the backbone of the decentralized web, yet ensuring their functional correctness and security remains a critical challenge. While Large Language Models (LLMs) h…
Learning to Align Human Code Preferences
Xin Yin, Chao Ni, Xiaohu Yang
Large Language Models (LLMs) have demonstrated remarkable potential in automating software development tasks. While recent advances leverage Supervised Fine-Tuning (SFT) and Direct…