Effort as Ceiling, Not Dial: Reasoning Budget Does Not Modulate Cognitive Cost Alignment Between Humans and Large Reasoning Models

• URL: http://arxiv.org/abs/2605.16938v1
• Date: Sat, 16 May 2026 11:20:01 GMT
• Title: Effort as Ceiling, Not Dial: Reasoning Budget Does Not Modulate Cognitive Cost Alignment Between Humans and Large Reasoning Models
• Abstract summary: Large Reasoning Models generate chain-of-thought traces whose length tracks human reaction times across cognitive tasks.<n>We test whether the alignment varies with inference-time reasoning effort.<n>A training-time achievement, Cognitive cost alignment between LRMs and humans appears to be a training-time achievement.
• Score: 0.4306164411864404
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Reasoning Models (LRMs) generate chain-of-thought traces whose length tracks human reaction times across cognitive tasks, but recent debate questions whether this alignment reflects genuine computational structure or surface verbosity. We test whether the alignment varies with inference-time reasoning effort. Across GPT-OSS-20B and GPT-OSS-120B, three effort levels, and six reasoning tasks, within-task and cross-task alignment remain invariant: Bayes Factors lean toward the null, and mean alignment is numerically near-identical across conditions. A manipulation check reveals that the effort parameter sets an upper budget on generation rather than driving real-time allocation, suggesting that the allocation policy is crystallized at training time. Arithmetic complexity contrasts further show that token allocation tracks fine-grained, format-dependent human difficulty patterns, with model scale improving the match. Cognitive cost alignment between LRMs and humans appears to be a training-time achievement, robust to inference-time perturbations, supporting a compiled rather than online account of LRM problem-solving.

Related papers

• Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions [59.21329728895449]
  We introduce an exam-style evaluation framework for studying this setting.<n>We find that models fail to allocate a shared budget strategically across questions of varying difficulties and values.<n>These findings establish global budget allocation as a distinct capability that is not captured by conventional per-question evaluation.
  arXiv  Detail & Related papers  (2026-08-08T07:04:28Z)
• Are More Tokens Rational? Inference-Time Scaling in Language Models as Adaptive Resource Rationality [1.5994376682356057]
  We introduce a Variable Attribution Task in which models infer which variables determine outcomes given candidate variables, input-output trials, and predefined logical functions.<n>Both models exhibit a transition from brute-force to analytic strategies as complexity increases.<n>These findings suggest that models can adjust their reasoning behavior in response to task complexity, even without explicit cost-based reward.
  arXiv  Detail & Related papers  (2026-02-10T22:07:05Z)
• Are Reasoning LLMs Robust to Interventions on Their Chain-of-Thought? [79.86483056611105]
  Reasoning LLMs generate step-by-step chains of thought before giving an answer.<n>How robust are these reasoning traces to disruptions that occur within them?<n>We introduce a controlled evaluation framework that perturbs a model's own CoT at fixed timesteps.
  arXiv  Detail & Related papers  (2026-02-07T10:02:58Z)
• On the Paradoxical Interference between Instruction-Following and Task Solving [50.75960598434753]
  Instruction following aims to align Large Language Models (LLMs) with human intent by specifying explicit constraints on how tasks should be performed.<n>We reveal a counterintuitive phenomenon: instruction following can paradoxically interfere with LLMs' task-solving capability.<n>We propose a metric, SUSTAINSCORE, to quantify the interference of instruction following with task solving.
  arXiv  Detail & Related papers  (2026-01-29T17:48:56Z)
• Understanding and Steering the Cognitive Behaviors of Reasoning Models at Test-Time [22.9491443902816]
  We study the structure of reasoning trajectories and uncover specialized attention heads that correlate with distinct cognitive behaviors.<n>We propose CREST, a training-free method for Cognitive REasoning Steering at Test-time.<n>CREST adaptively suppresses unproductive reasoning behaviors, yielding both higher accuracy and lower computational cost.
  arXiv  Detail & Related papers  (2025-12-31T02:46:04Z)
• e1: Learning Adaptive Control of Reasoning Effort [88.51897900019485]
  Increasing the thinking budget of AI models can significantly improve accuracy, but not all questions warrant the same amount of reasoning.<n>Users may prefer to allocate different amounts of reasoning effort depending on how they value output quality versus latency and cost.<n>We propose Adaptive Effort Control, a self-adaptive reinforcement learning method that trains models to use a user-specified fraction of tokens.
  arXiv  Detail & Related papers  (2025-10-30T23:12:21Z)
• CogniLoad: A Synthetic Natural Language Reasoning Benchmark With Tunable Length, Intrinsic Difficulty, and Distractor Density [2.4149105714758545]
  We introduce CogniLoad, a novel synthetic benchmark grounded in Cognitive Load Theory (CLT)<n>CogniLoad generates natural-language logic puzzles with independently tunable parameters that reflect CLT's core dimensions.<n>CogniLoad reveals distinct performance sensitivities, identifying task length as a dominant constraint.
  arXiv  Detail & Related papers  (2025-09-22T22:28:33Z)
• From Long to Short: LLMs Excel at Trimming Own Reasoning Chains [48.692414597960244]
  O1/R1 style large reasoning models (LRMs) signal a substantial leap forward over conventional instruction-following LLMs.<n>Recent studies show that LRMs are prone to suffer from overthinking.<n>We propose a test-time scaling method, EDIT, which efficiently guides LRMs to identify the shortest correct reasoning paths at test time.
  arXiv  Detail & Related papers  (2025-09-07T19:00:44Z)
• Mitigating Spurious Correlations Between Question and Answer via Chain-of-Thought Correctness Perception Distillation [25.195244084313114]
  Chain-of-Thought Correctness Perception Distillation (CoPeD) aims to improve the reasoning quality of the student model.<n>CoPeD encourages the student model to predict answers based on correct rationales and revise them when they are incorrect.
  arXiv  Detail & Related papers  (2025-09-06T05:33:17Z)
• Seeing is not Believing: Robust Reinforcement Learning against Spurious Correlation [57.351098530477124]
  We consider one critical type of robustness against spurious correlation, where different portions of the state do not have correlations induced by unobserved confounders. A model that learns such useless or even harmful correlation could catastrophically fail when the confounder in the test case deviates from the training one. Existing robust algorithms that assume simple and unstructured uncertainty sets are therefore inadequate to address this challenge.
  arXiv  Detail & Related papers  (2023-07-15T23:53:37Z)

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.