A systematic literature review on large language models for automated program repair

Q Zhang, C Fang, Y **e, YX Ma, W Sun, Y Yang… - arxiv preprint arxiv …, 2024 - arxiv.org
Automated Program Repair (APR) attempts to patch software bugs and reduce manual
debugging efforts. Very recently, with the advances in Large Language Models (LLMs), an …

[PDF][PDF] Stable and safe human-aligned reinforcement learning through neural ordinary differential equations

L Zhao, K Miao, K Gatsis… - arxiv preprint arxiv …, 2024 - harlworkshop.github.io
Reinforcement learning (RL) excels in applications such as video games, but ensuring
safety as well as the ability to achieve the specified goals remains challenging when using …

Can LLMs plan paths with extra hints from solvers?

E Wu, S Mitra - arxiv preprint arxiv:2410.05045, 2024 - arxiv.org
Large Language Models (LLMs) have shown remarkable capabilities in natural language
processing, mathematical problem solving, and tasks related to program synthesis …