DSGBench is a benchmark platform with six customizable strategic games, five-dimensional scoring, and automated trajectory tracking for evaluating LLM agents.
The completion of Warpgate research and the ongoing Blink research suggest a plan to transition to more advanced units and tactics
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
DSGBench: A Diverse Strategic Game Benchmark for Evaluating LLM-based Agents in Complex Decision-Making Environments
DSGBench is a benchmark platform with six customizable strategic games, five-dimensional scoring, and automated trajectory tracking for evaluating LLM agents.