SWE-Effi: Re-Evaluating Software AI Agent System Effectiveness Under Resource Constraints

Documenti analoghi

• Watson: A Cognitive Observability Framework for the Reasoning of LLM-Powered Agents
  di: Rombaut, Benjamin, et al.
  Pubblicazione: (2024)
• SPICE: An Automated SWE-Bench Labeling Pipeline for Issue Clarity, Test Coverage, and Effort Estimation
  di: Oliva, Gustavo A., et al.
  Pubblicazione: (2025)
• RepoForge: Training a SOTA Fast-thinking SWE Agent with an End-to-End Data Curation Pipeline Synergizing SFT and RL at Scale
  di: Chen, Zhilong, et al.
  Pubblicazione: (2025)
• Rethinking Software Engineering in the Foundation Model Era: From Task-Driven AI Copilots to Goal-Driven AI Pair Programmers
  di: Hassan, Ahmed E., et al.
  Pubblicazione: (2024)
• Towards AI-Native Software Engineering (SE 3.0): A Vision and a Challenge Roadmap
  di: Hassan, Ahmed E., et al.
  Pubblicazione: (2024)