LLMs May Not Be Human-Level Players, But They Can Be Testers: Measuring Game Difficulty with LLM Agents

Documenti analoghi

• Advancing DRL Agents in Commercial Fighting Games: Training, Integration, and Agent-Human Alignment
  di: Zhang, Chen, et al.
  Pubblicazione: (2024)
• AI Agents for Inventory Control: Human-LLM-OR Complementarity
  di: Baek, Jackie, et al.
  Pubblicazione: (2026)
• When the Loop Closes: Architectural Limits of In-Context Isolation, Metacognitive Co-option, and the Two-Target Design Problem in Human-LLM Systems
  di: Cheng, Z., et al.
  Pubblicazione: (2026)
• LLMs as Policy-Agnostic Teammates: A Case Study in Human Proxy Design for Heterogeneous Agent Teams
  di: Justus, Aju Ani, et al.
  Pubblicazione: (2025)
• Streaming, Fast and Slow: Cognitive Load-Aware Streaming for Efficient LLM Serving
  di: Xiao, Chang, et al.
  Pubblicazione: (2025)