STARLING: Self-supervised Training of Text-based Reinforcement Learning Agent with Large Language Models

Documenti analoghi

• Towards Aligning Language Models with Textual Feedback
  di: Lloret, Saüc Abadal, et al.
  Pubblicazione: (2024)
• CTBench: A Comprehensive Benchmark for Evaluating Language Model Capabilities in Clinical Trial Design
  di: Neehal, Nafis, et al.
  Pubblicazione: (2024)
• The Chameleon Nature of LLMs: Quantifying Multi-Turn Stance Instability in Search-Enabled Language Models
  di: Ratnakar, Shivam, et al.
  Pubblicazione: (2025)
• EfficientLLM: Efficiency in Large Language Models
  di: Yuan, Zhengqing, et al.
  Pubblicazione: (2025)
• Adversarial Reinforcement Learning for Large Language Model Agent Safety
  di: Wang, Zizhao, et al.
  Pubblicazione: (2025)