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

• URL: http://arxiv.org/abs/2607.09743v1
• Date: Fri, 03 Jul 2026 10:23:31 GMT
• Title: Scaffolding the Strategist: Architecture-Dependent Reasoning Interventions in Hotelling Spatial Markets
• Abstract summary: We investigate whether structured reasoning interventions improve the strategic economic reasoning of large language models.<n>We evaluate GPT-4.1-mini (a standard instruction-following model) and GPT-5-mini (a reasoning-optimized model) under five conditions.<n>We find a statistically significant crossover interaction between scaffolding type and model architecture.
• Score: 0.01269104766024433
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 $2.6\times$ greater degradation for the reasoning model ($-1.47$ vs. $-0.57$; $p = 0.038$), and the damage correlates negatively with baseline difficulty ($R^2 = 0.36$, $p = 0.014$). 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.

Related papers

• $p$-Body $\simeq$ Range $p-1$: Exact Order-Range Mapping and Dual-Unitarity [0.0]
  We study a periodically kicked version of a one-dimensional spin-$1/2$ Ising model with contiguous $p$-body interactions.<n>At specific interaction strengths, we establish an exact Floquet interaction $textitorder-range$ mapping.<n>We then determine exact entanglement dynamics of the $p$-body model for a class of solvable initial states at all times.
  arXiv  Detail & Related papers  (2026-07-18T05:06:25Z)
• Lying Is Just a Phase: The Hidden Alignment Transition in Language Model Scaling [0.0]
  We measure the coupling between reasoning and truthfulness across 63 base models from 16 families.<n>We find a regime change invisible to loss curves below a family-dependent critical scale $N_c$, capabilities anticorrelate; above it, they cooperate.
  arXiv  Detail & Related papers  (2026-05-13T03:14:09Z)
• Persona-Model Collapse in Emergent Misalignment [0.0]
  Fine-tuning large language models on narrow data with harmful content produces broadly misaligned behavior on unrelated prompts.<n>We test this hypothesis using two metrics: moral susceptibility (S) and moral robustness (R)<n>These metrics formalize the model's ability to differentiate characters (S) and its consistency when simulating a given one (R)
  arXiv  Detail & Related papers  (2026-05-13T00:48:57Z)
• What Do EEG Foundation Models Capture from Human Brain Signals? [64.48249643001402]
  Modern EEG foundation models learn directly from raw signals via self-supervised pretraining.<n>We decompose into three sub-questions: emphwhat does the model learn, emphwhat does the model use, and emphhow much can be explained<n>The audit covers three foundation models (CSBrain, CBraMod, LaBraM), five clinical tasks (MDD, Stress, ISRUC-Sleep, TUSL, Siena), and a 6-family 63-feature lexicon.
  arXiv  Detail & Related papers  (2026-05-12T01:57:53Z)
• One Token Away from Collapse: The Fragility of Instruction-Tuned Helpfulness [12.183451602438753]
  We show that simple lexical constraints (banning a single punctuation character or common word) cause instruction-tuned LLMs to collapse their responses.<n>We show that base models show no systematic collapse under identical constraints, with effects that are small, noisy, and bidirectional.
  arXiv  Detail & Related papers  (2026-04-14T17:40:01Z)
• When Self-Reference Fails to Close: Matrix-Level Dynamics in Large Language Models [0.0]
  Self-referential statements and meta-cognitive prompts are more stable than paradoxical self-reference on key collapse-related metrics.<n>We propose, as a conjecture, that NCTR forces finite-depth transformers toward dynamical regimes where these problems concentrate.
  arXiv  Detail & Related papers  (2026-04-13T23:23:02Z)
• Model Agreement via Anchoring [31.113945168635656]
  We prove disagreement bounds for four commonly used machine learning algorithms.<n>For clarity, we work out our initial bounds in the setting of one-dimensional regression with squared error loss.<n>All of our results generalize to multi-dimensional regression with any strongly convex loss.
  arXiv  Detail & Related papers  (2026-02-26T18:59:32Z)
• Towards a Comprehensive Scaling Law of Mixture-of-Experts [54.117786590884776]
  We propose a comprehensive and precise joint MoE scaling law that considers all essential factors.<n>Our results demonstrate that the optimal settings for $G$ and $S$ are independent of both the model architecture and data size.<n>Our proposed MoE scaling law could function as an accurate and insightful guidance to facilitate future MoE model design and training.
  arXiv  Detail & Related papers  (2025-09-28T06:35:34Z)
• Think Smarter not Harder: Adaptive Reasoning with Inference Aware Optimization [48.5702580429946]
  In this work, we propose a way to allow models to be aware of inference budgets by formulating it as utility with respect to an inference budget constraint.<n>In a nutshell, models fine-tuned through IBPO learn to understand'' the difficulty of queries and allocate inference budgets to harder ones.<n>These improvements are approximately $2$x those of self-consistency under the same budgets.
  arXiv  Detail & Related papers  (2025-01-29T20:20:48Z)
• Misspecification in Inverse Reinforcement Learning [80.91536434292328]
  The aim of Inverse Reinforcement Learning (IRL) is to infer a reward function $R$ from a policy $pi$. One of the primary motivations behind IRL is to infer human preferences from human behaviour. This means that they are misspecified, which raises the worry that they might lead to unsound inferences if applied to real-world data.
  arXiv  Detail & Related papers  (2022-12-06T18:21:47Z)
• Exploring Sparse Expert Models and Beyond [51.90860155810848]
  Mixture-of-Experts (MoE) models can achieve promising results with outrageous large amount of parameters but constant computation cost. We propose a simple method called expert prototyping that splits experts into different prototypes and applies $k$ top-$1$ routing. This strategy improves the model quality but maintains constant computational costs, and our further exploration on extremely large-scale models reflects that it is more effective in training larger models.
  arXiv  Detail & Related papers  (2021-05-31T16:12:44Z)
• Adversarial robustness against multiple $l_p$-threat models at the price of one and how to quickly fine-tune robust models to another threat model [79.05253587566197]
  Adrial training (AT) in order to achieve adversarial robustness wrt single $l_p$-threat models has been discussed extensively. In this paper we develop a simple and efficient training scheme to achieve adversarial robustness against the union of $l_p$-threat models.
  arXiv  Detail & Related papers  (2021-05-26T12:20:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.