← Search

Simon Karasik

2 accepted papers

2025

Guided Search Strategies in Non-Serializable Environments with Applications to Software Engineering Agents

ICML 2025poster

Large language models (LLMs) have recently achieved remarkable results in complex multi-step tasks, such as mathematical reasoning and agentic software engineering. However, they often struggle to maintain consistent performance across multiple solution attempts. One effective approach to narrow the…

Cited by 0SourcePDFScholar
2025

SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents

NeurIPS 2025poster

LLM-based agents have shown promising capabilities in a growing range of software engineering (SWE) tasks. However, advancing this field faces two critical challenges. First, high-quality training data is scarce, especially data that reflects real-world SWE scenarios, where agents must interact with…

Cited by 0SourcecodeScholar