# What-If Analysis of Large Language Models: Explore the Game World Using Proactive Thinking

arXiv: https://arxiv.org/abs/2509.04791 · HTML: https://mlsanity.com/paper/2509.04791/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 30 of its 43 references that are in the map.
- First posted on arXiv 5 Sep 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 30 of 30)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism](https://mlsanity.com/paper/1909.08053/) (2019)
- [Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them](https://mlsanity.com/paper/2210.09261/) (2022)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [Instruction-Following Evaluation for Large Language Models](https://mlsanity.com/paper/2311.07911/) (2023)
- [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://mlsanity.com/paper/2405.14734/) (2024)
- [C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models](https://mlsanity.com/paper/2305.08322/) (2023)
- [Time-LLM: Time Series Forecasting by Reprogramming Large Language Models](https://mlsanity.com/paper/2310.01728/) (2023)
- [StarCraft II: A New Challenge for Reinforcement Learning](https://mlsanity.com/paper/1708.04782/) (2017)
- [CharacterEval: A Chinese Benchmark for Role-Playing Conversational Agent Evaluation](https://mlsanity.com/paper/2401.01275/) (2024)
- [A Survey on Large Language Model-Based Game Agents](https://mlsanity.com/paper/2404.02039/) (2024)
- [Ape210K: A Large-Scale and Template-Rich Dataset of Math Word Problems](https://mlsanity.com/paper/2009.11506/) (2020)
- [CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction](https://mlsanity.com/paper/2502.07316/) (2025)
- [Time Series Forecasting with LLMs: Understanding and Enhancing Model Capabilities](https://mlsanity.com/paper/2402.10835/) (2024)
- [Meta-Reasoner: Dynamic Guidance for Optimized Inference-time Reasoning in Large Language Models](https://mlsanity.com/paper/2502.19918/) (2025)
- [Honor of Kings Arena: an Environment for Generalization in Competitive Reinforcement Learning](https://mlsanity.com/paper/2209.08483/) (2022)
- [PokeLLMon: A Human-Parity Agent for Pokemon Battles with Large Language Models](https://mlsanity.com/paper/2402.01118/) (2024)
- [Exploring the impact of low-rank adaptation on the performance, efficiency, and regularization of RLHF](https://mlsanity.com/paper/2309.09055/) (2023)
- [CharPoet: A Chinese Classical Poetry Generation System Based on Token-free LLM](https://mlsanity.com/paper/2401.03512/) (2024)
- [Enabling Self-Improving Agents to Learn at Test Time With Human-In-The-Loop Guidance](https://mlsanity.com/paper/2507.17131/) (2025)
- [Hokoff: Real Game Dataset from Honor of Kings and its Offline Reinforcement Learning Benchmarks](https://mlsanity.com/paper/2408.10556/) (2024)
- [Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models](https://mlsanity.com/paper/2508.21365/) (2025)
- [Time Series Forecasting (TSF) Using Various Deep Learning Models](https://mlsanity.com/paper/2204.11115/) (2022)
- [Augmenting Decision Making via Interactive What-If Analysis](https://mlsanity.com/paper/2109.06160/) (2021)

## Built on by (most cited first, 3 of 3)

- [TACT: Mitigating Overthinking and Overacting in Coding Agents via Activation Steering](https://mlsanity.com/paper/2605.05980/) (2026)
- [Composable Crystals: Controllable Materials Discovery via Concept Learning](https://mlsanity.com/paper/2605.14769/) (2026)
- [World Agent: Can Language Models Keep a World Running?](https://mlsanity.com/paper/2609.32692/) (2026)

## Abstract (arXiv)

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.