Runaway is Ashamed, But Helpful: On the Early-Exit Behavior of Large Language Model-based Agents in Embodied Environments

Documenti analoghi

• The Bitter Lesson of Diffusion Language Models for Agentic Workflows: A Comprehensive Reality Check
  di: Lu, Qingyu, et al.
  Pubblicazione: (2026)
• MQM-APE: Toward High-Quality Error Annotation Predictors with Automatic Post-Editing in LLM Translation Evaluators
  di: Lu, Qingyu, et al.
  Pubblicazione: (2024)
• Error Analysis Prompting Enables Human-Like Translation Evaluation in Large Language Models
  di: Lu, Qingyu, et al.
  Pubblicazione: (2023)
• Self-Powered LLM Modality Expansion for Large Speech-Text Models
  di: Yu, Tengfei, et al.
  Pubblicazione: (2024)
• Exploring and Enhancing the Transfer of Distribution in Knowledge Distillation for Autoregressive Language Models
  di: Rao, Jun, et al.
  Pubblicazione: (2024)