Testing and Understanding Erroneous Planning in LLM Agents through Synthesized User Inputs

Documenti analoghi

• STShield: Single-Token Sentinel for Real-Time Jailbreak Detection in Large Language Models
  di: Wang, Xunguang, et al.
  Pubblicazione: (2025)
• IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems
  di: Wang, Liwen, et al.
  Pubblicazione: (2025)
• Split and Merge: Aligning Position Biases in LLM-based Evaluators
  di: Li, Zongjie, et al.
  Pubblicazione: (2023)
• Digging Into the Internal: Causality-Based Analysis of LLM Function Calling
  di: Ji, Zhenlan, et al.
  Pubblicazione: (2025)
• Measuring and Augmenting Large Language Models for Solving Capture-the-Flag Challenges
  di: Ji, Zimo, et al.
  Pubblicazione: (2025)