LLMs act as static level-k players in behavioral games with k set by model scale, showing no within-game updating or backward induction unlike humans.
J., Bethge, M., & Schulz, E
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
econ.GN 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
LLM Agents as Static Level-k Players in Behavioural Games
LLMs act as static level-k players in behavioral games with k set by model scale, showing no within-game updating or backward induction unlike humans.