3 papers
cs.AI2025
Improving LLM-Generated Code Quality with GRPO
Maxime Robeyns, Laurence Aitchison
Large Language Models (LLMs) are gaining widespread use for code generation. Recent training procedures use execution feedback as a reward signal, typically focusing on the functio…
cs.AI2025
A Self-Improving Coding Agent
Maxime Robeyns, Martin Szummer, Laurence Aitchison
Recent advancements in Large Language Models (LLMs) have spurred interest in deploying LLM agents to undertake tasks in the world. LLMs are often deployed in agent systems: code th…
cs.CL2024
Instruction Tuning With Loss Over Instructions
Zhengyan Shi, Adam X. Yang, Bin Wu +3
Instruction tuning plays a crucial role in shaping the outputs of language models (LMs) to desired styles. In this work, we propose a simple yet effective method, Instruction Model…