LLM agents can achieve 91% landing success on a simplified Jump-Jump game when prompts include step-by-step reasoning, few-shot examples, and calibration tips, per an unreproducible small study.
Artificial intelligence (ai) library services innovative conceptual framework for the digital transformation of university education
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Exploring Decision-Making Capabilities of LLM Agents: An Experimental Study on Jump-Jump Game
LLM agents can achieve 91% landing success on a simplified Jump-Jump game when prompts include step-by-step reasoning, few-shot examples, and calibration tips, per an unreproducible small study.