If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agents

Documenti analoghi

• Executable Code Actions Elicit Better LLM Agents
  di: Wang, Xingyao, et al.
  Pubblicazione: (2024)
• The Law of Knowledge Overshadowing: Towards Understanding, Predicting, and Preventing LLM Hallucination
  di: Zhang, Yuji, et al.
  Pubblicazione: (2025)
• WizardCoder: Empowering Code Large Language Models with Evol-Instruct
  di: Luo, Ziyang, et al.
  Pubblicazione: (2023)
• EVEDIT: Event-based Knowledge Editing with Deductive Editing Boundaries
  di: Liu, Jiateng, et al.
  Pubblicazione: (2024)
• LocAgent: Graph-Guided LLM Agents for Code Localization
  di: Chen, Zhaoling, et al.
  Pubblicazione: (2025)