LLM action selection approximates but does not reliably preserve a reference first-order Markov policy in OSN simulations and runs several hundred times slower.
In: Companion Proceedings of The 2019 World Wide Web Conference
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CY 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Should LLM Agents Decide in Social Simulations? Comparing Finite-State and LLM-Based Decision Policies
LLM action selection approximates but does not reliably preserve a reference first-order Markov policy in OSN simulations and runs several hundred times slower.