Select-then-Solve: Paradigm Routing as Inference-Time Optimization for LLM Agents

Documenti analoghi

• CoEnv: Driving Embodied Multi-Agent Collaboration via Compositional Environment
  di: Kang, Li, et al.
  Pubblicazione: (2026)
• Reading $\neq$ Seeing: Diagnosing and Closing the Typography Gap in Vision-Language Models
  di: Zhou, Heng, et al.
  Pubblicazione: (2026)
• Ego to World: Collaborative Spatial Reasoning in Embodied Systems via Reinforcement Learning
  di: Zhou, Heng, et al.
  Pubblicazione: (2026)
• VIKI-R: Coordinating Embodied Multi-Agent Cooperation via Reinforcement Learning
  di: Kang, Li, et al.
  Pubblicazione: (2025)
• RoboFactory: Exploring Embodied Agent Collaboration with Compositional Constraints
  di: Qin, Yiran, et al.
  Pubblicazione: (2025)