# Scaffolding the Strategist: Architecture-Dependent Reasoning Interventions in Hotelling Spatial Markets

arXiv: https://arxiv.org/abs/2607.09743 · HTML: https://mlsanity.com/paper/2607.09743/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 10 of its 22 references that are in the map.
- First posted on arXiv 3 Jul 2026.

## 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, 10 of 10)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning](https://mlsanity.com/paper/2409.12183/) (2024)
- [Playing repeated games with Large Language Models](https://mlsanity.com/paper/2305.16867/) (2023)
- [GTBench: Uncovering the Strategic Reasoning Limitations of LLMs via Game-Theoretic Evaluations](https://mlsanity.com/paper/2402.12348/) (2024)
- [Strategic Reasoning with Language Models](https://mlsanity.com/paper/2305.19165/) (2023)
- [Algorithmic Collusion by Large Language Models](https://mlsanity.com/paper/2404.00806/) (2024)
- [Strategic Collusion of LLM Agents: Market Division in Multi-Commodity Competitions](https://mlsanity.com/paper/2410.00031/) (2024)
- [Economics Arena for Large Language Models](https://mlsanity.com/paper/2401.01735/) (2024)
- [Comprehension Without Competence: Architectural Limits of LLMs in Symbolic Computation and Reasoning](https://mlsanity.com/paper/2507.10624/) (2025)

## Abstract (arXiv)

We investigate whether structured reasoning interventions improve the strategic economic reasoning of large language models, and whether their effects depend on model architecture. Using Hotelling's linear city model as a diagnostic vehicle, we evaluate GPT-4.1-mini (a standard instruction-following model) and GPT-5-mini (a reasoning-optimized model) under five conditions - an unscaffolded baseline and four reasoning interventions - across eight questions spanning deductive and abductive reasoning, three prompt framings, and three repetitions per condition, yielding 720 individually judged responses. We find a statistically significant crossover interaction between scaffolding type and model architecture (t(7) = 4.79, p = 0.002, d = 1.69): commitment scaffolding improves the standard model (+0.21) while degrading the reasoning model (-0.63), and principled separation shows the opposite pattern (-0.40 vs. +0.31). Both crossovers are individually significant (commitment: p = 0.040; separation: p = 0.002) and hold across all eight questions with 7/8 directional consistency. Adversarial stress-testing harms both models, with 2.6× greater degradation for the reasoning model (-1.47 vs. -0.57; p = 0.038), and the damage correlates negatively with baseline difficulty (R2 = 0.36, p = 0.014). We further document a persistent declarative-procedural gap in which both models identify correct strategies at rates far exceeding their ability to execute them; separation fully closes this gap for the reasoning model while no intervention helps the standard model.