Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.04791 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908756498972672 |
|---|---|
| author | Sui, Yuan Zhang, Yanming Liao, Yi Gu, Yu Tang, Guohua Sun, Zhongqian Yang, Wei Hooi, Bryan |
| author_facet | Sui, Yuan Zhang, Yanming Liao, Yi Gu, Yu Tang, Guohua Sun, Zhongqian Yang, Wei Hooi, Bryan |
| contents | LLMs struggle with decision-making in high-stakes environments like MOBA games, primarily due to a lack of proactive reasoning and limited understanding of complex game dynamics. To address this, we propose What-if Analysis LLM (WiA-LLM), a framework that trains an LLM as an explicit, language-based world model. Instead of representing the environment in latent vectors, WiA-LLM uses natural language to simulate how the game state evolves over time in response to candidate actions, and provides textual justifications for these predicted outcomes. WiA-LLM is trained in two stages: supervised fine-tuning on human-like reasoning traces, followed by reinforcement learning with outcome-based rewards based on the alignment between predicted and actual future states. In the Honor of Kings (HoK) environment, WiA-LLM attains 74.2\% accuracy (27\%$\uparrow$ vs. base model) in forecasting game-state changes. In addition, WiA-LLM demonstrate strategic behavior more closely aligned with expert players than purely reactive LLMs, indicating enhanced foresight and expert-like decision-making. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_04791 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | What-If Analysis of Large Language Models: Explore the Game World Using Proactive Thinking Sui, Yuan Zhang, Yanming Liao, Yi Gu, Yu Tang, Guohua Sun, Zhongqian Yang, Wei Hooi, Bryan Artificial Intelligence LLMs struggle with decision-making in high-stakes environments like MOBA games, primarily due to a lack of proactive reasoning and limited understanding of complex game dynamics. To address this, we propose What-if Analysis LLM (WiA-LLM), a framework that trains an LLM as an explicit, language-based world model. Instead of representing the environment in latent vectors, WiA-LLM uses natural language to simulate how the game state evolves over time in response to candidate actions, and provides textual justifications for these predicted outcomes. WiA-LLM is trained in two stages: supervised fine-tuning on human-like reasoning traces, followed by reinforcement learning with outcome-based rewards based on the alignment between predicted and actual future states. In the Honor of Kings (HoK) environment, WiA-LLM attains 74.2\% accuracy (27\%$\uparrow$ vs. base model) in forecasting game-state changes. In addition, WiA-LLM demonstrate strategic behavior more closely aligned with expert players than purely reactive LLMs, indicating enhanced foresight and expert-like decision-making. |
| title | What-If Analysis of Large Language Models: Explore the Game World Using Proactive Thinking |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2509.04791 |