Sharing the Cost of Success: A Game for Evaluating and Learning Collaborative Multi-Agent Instruction Giving and Following Policies

Documenti analoghi

• Learning Communication Policies for Different Follower Behaviors in a Collaborative Reference Game
  di: Sadler, Philipp, et al.
  Pubblicazione: (2024)
• The Image Reconstruction Game: Drawing Common Ground Through Iterative Multimodal Dialogue
  di: Hakimov, Sherzod, et al.
  Pubblicazione: (2026)
• A Third Paradigm for LLM Evaluation: Dialogue Game-Based Evaluation using clembench
  di: Schlangen, David, et al.
  Pubblicazione: (2025)
• Multi-Turn Multi-Agent Dialogue for Collaborative Reconstruction Improves VLM Performance on Spatial Reasoning, But Only Barely
  di: Kranti, Chalamalasetti, et al.
  Pubblicazione: (2026)
• Ad-hoc Concept Forming in the Game Codenames as a Means for Evaluating Large Language Models
  di: Hakimov, Sherzod, et al.
  Pubblicazione: (2025)