# The Fragility of Strategic Thinking in Large Language Models

arXiv: https://arxiv.org/abs/2510.10813 · HTML: https://mlsanity.com/paper/2510.10813/

## Key facts

- Cited by 2 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 13 of its 42 references that are in the map.
- First posted on arXiv 12 Oct 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, 13 of 13)

- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity](https://mlsanity.com/paper/2506.06941/) (2025)
- [Why Language Models Hallucinate](https://mlsanity.com/paper/2509.04664/) (2025)
- [TradingAgents: Multi-Agents LLM Financial Trading Framework](https://mlsanity.com/paper/2412.20138/) (2024)
- [GTBench: Uncovering the Strategic Reasoning Limitations of LLMs via Game-Theoretic Evaluations](https://mlsanity.com/paper/2402.12348/) (2024)
- [Cognitive Bias in Decision-Making with LLMs](https://mlsanity.com/paper/2403.00811/) (2024)
- [Do Large Language Models Show Decision Heuristics Similar to Humans? A Case Study Using GPT-3.5](https://mlsanity.com/paper/2305.04400/) (2023)
- [Emergent Hierarchical Reasoning in LLMs through Reinforcement Learning](https://mlsanity.com/paper/2509.03646/) (2025)
- [K-Level Reasoning: Establishing Higher Order Beliefs in Large Language Models for Strategic Reasoning](https://mlsanity.com/paper/2402.01521/) (2024)
- [Beyond Nash Equilibrium: Bounded Rationality of LLMs and humans in Strategic Decision-making](https://mlsanity.com/paper/2506.09390/) (2025)
- [Heuristics and Biases in AI Decision-Making: Implications for Responsible AGI](https://mlsanity.com/paper/2410.02820/) (2024)
- [Do LLMs Know When to Flip a Coin? Strategic Randomization through Reasoning and Experience](https://mlsanity.com/paper/2506.18928/) (2025)
- [What Would an LLM Do? Evaluating Large Language Models for Policymaking to Alleviate Homelessness](https://mlsanity.com/paper/2509.03827/) (2025)

## Built on by (most cited first, 2 of 2)

- [Counterparty Modeling is Not Strategy: The Limits of LLM Negotiators](https://mlsanity.com/paper/2605.16575/) (2026)
- [To Nuke or Not to Nuke: LLMs' (Missing) Ethical Reasoning and Actions in a High-Stakes Decision-Making Simulation](https://mlsanity.com/paper/2606.08310/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) are increasingly applied to domains that require reasoning about other agents' behavior, such as negotiation, policy design, and market simulation. However, can we trust LLMs to think strategically in complex situations? Existing research mostly evaluates LLMs' adherence to equilibrium play or their exhibited depth of reasoning, leaving open whether they display strategic thinking meant as the ability to form coherent conjectures about other agents, to evaluate possible actions conditional on those conjectures, and to best respond to them. We develop a framework to identify this ability by disentangling belief formation, evaluation, and choice in static complete-information games across a series of non-cooperative environments. By jointly analyzing models' revealed choices and reasoning traces, and introducing a new context-free game to rule out imitation from memorization, we show that strategic thinking in current frontier LLMs is real but fragile: models execute best responses to exogenous conjectures and form opponent-contingent conjectures when left unconstrained. Yet under increasing complexity explicit recursion gives way to model-specific logic shifts and heuristic rules of choice, both within and outside equilibrium reasoning. Further, these heuristics do not map directly onto the systematic biases typically observed in human strategic behavior. These findings, already emerging in noiseless settings, warrant caution in the application of LLMs as strategic agents in complex environments.