AGENTIF: Benchmarking Instruction Following of Large Language Models in Agentic Scenarios

Documenti analoghi

• Constraint Back-translation Improves Complex Instruction Following of Large Language Models
  di: Qi, Yunjia, et al.
  Pubblicazione: (2024)
• VerIF: Verification Engineering for Reinforcement Learning in Instruction Following
  di: Peng, Hao, et al.
  Pubblicazione: (2025)
• Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems
  di: Peng, Hao, et al.
  Pubblicazione: (2025)
• On the Paradoxical Interference between Instruction-Following and Task Solving
  di: Qi, Yunjia, et al.
  Pubblicazione: (2026)
• ADELIE: Aligning Large Language Models on Information Extraction
  di: Qi, Yunjia, et al.
  Pubblicazione: (2024)