← Search

Danlong Yuan

2 accepted papers

2026

SWE-MiniSandbox: Container-Free Reinforcement Learning for Building Software Engineering Agents

ICML 2026poster

Reinforcement learning (RL) has become a key paradigm for training software engineering (SWE) agents, yet its practical accessibility and scalability is often constrained by container-based execution frameworks used for environment isolation. As the number of task instances increases, pre-cached con…

Cited by 0SourceScholar
2025

ReMamba: Equip Mamba with Effective Long-Sequence Modeling

EMNLP 2025

While the Mamba architecture demonstrates superior inference efficiency and competitive performance on short-context natural language processing (NLP) tasks, empirical evidence suggests its capacity to comprehend long contexts is limited compared to transformer-based models. In this study, we invest