LLM agent simulations show cooperation and mutual help drive survival, with universal and reciprocal morality most stable while selfishness is strongly disfavored, mediated by cognitive costs of judgment.
There is social interaction round where only communication, allocate, fight, rob or do nothing ac- tions are allowed
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.MA 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Why Are We Moral? An LLM-based Agent Simulation Approach to Study Moral Evolution
LLM agent simulations show cooperation and mutual help drive survival, with universal and reciprocal morality most stable while selfishness is strongly disfavored, mediated by cognitive costs of judgment.