An LLM agent that identifies its opponent's strategy and then searches a learned strategy-evaluation network for the best response substantially outperforms prompt-only LLM planners in MicroRTS.
Game theory-based opponent modeling in large imperfect-information games,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Strategy-Augmented Planning for Large Language Models via Opponent Exploitation
An LLM agent that identifies its opponent's strategy and then searches a learned strategy-evaluation network for the best response substantially outperforms prompt-only LLM planners in MicroRTS.