C2C is a new testbed where LM agents negotiate differently from humans and targeted prompting raises their win rate from 22.2% to 32.7% across 1,100+ games.
Magic: Investigation of large language model powered multi-agent in cognition, adaptability, rationality and collaboration
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Cooperate to Compete: Strategic Coordination in Multi-Agent Conquest
C2C is a new testbed where LM agents negotiate differently from humans and targeted prompting raises their win rate from 22.2% to 32.7% across 1,100+ games.