FAMA: Failure-Aware Meta-Agentic Framework for Open-Source LLMs in Interactive Tool Use Environments

Documenti analoghi

• How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on $τ$-bench
  di: Mishra, Venkatesh, et al.
  Pubblicazione: (2025)
• Investigating the Shortcomings of LLMs in Step-by-Step Legal Reasoning
  di: Mishra, Venkatesh, et al.
  Pubblicazione: (2025)
• Investigating and Addressing Hallucinations of LLMs in Tasks Involving Negation
  di: Varshney, Neeraj, et al.
  Pubblicazione: (2024)
• Insights into Alignment: Evaluating DPO and its Variants Across Multiple Tasks
  di: Saeidi, Amir, et al.
  Pubblicazione: (2024)
• When "Competency" in Reasoning Opens the Door to Vulnerability: Jailbreaking LLMs via Novel Complex Ciphers
  di: Handa, Divij, et al.
  Pubblicazione: (2024)