SWE-Bench-CL: Continual Learning for Coding Agents

By Thomas T. Joshi, Shayan Chowdhury, Fatih Uysal. 2025

Subfields: LLM Agents & Tool Use, Meta & Continual Learning, Code Generation & Program Synthesis

Citations in the corpus

• Agentic Software Issue Resolution with Large Language Models: A Survey (2025, unknown): “Martinez et al. [111] analyze the SWE-bench Lite and SWE-bench Verified leaderboards to characterize the architectural choices and factors driving reported performance gains.”