---
id: "lib-2026-10-07-the-long-road-to-the-same-answer-cognitive-bias"
type: "library"
title: "The Long Road to the Same Answer: Cognitive Bias Under Escalating Reasoning Budgets"
lang: "EN"
org: "arXiv"
source_type: "Paper"
date: "2026-10-07"
week: "2026-W41"
url: "https://nosov.ai/library/lib-2026-10-07-the-long-road-to-the-same-answer-cognitive-bias/"
original_url: "https://arxiv.org/abs/2610.10049"
tier: "A"
tier_name: "Strong evidence"
tier_reason: "Controlled dose-response experiment (12,350 API calls, seven models, matched reasoning and non-reasoning pairs) accepted at IEEE CogMI 2026 with released data and code; single author and only five items per bias."
summary_basis: "full-text"
original_minutes: "35"
tags: ["ai technology", "bias", "hr decisions"]
---

# The Long Road to the Same Answer: Cognitive Bias Under Escalating Reasoning Budgets

Tier A (Strong evidence): Controlled dose-response experiment (12,350 API calls, seven models, matched reasoning and non-reasoning pairs) accepted at IEEE CogMI 2026 with released data and code; single author and only five items per bias.

Summary based on the full text.

## In short

A paper by Obada Kraishan (Texas Tech University), accepted at the 2026 IEEE Conference on Cognitive Machine Intelligence and posted on arXiv on 7 October 2026. It tests whether letting reasoning models "think longer" reduces classic decision biases, as the human dual-process analogy predicts. It does not: reasoning models were no less biased than matched non-reasoning siblings, and bias did not fall as realized thinking grew. Anchoring was the one bias present in the human direction, and a single prompt line asking the model to restate the anchor lowered it where extra thinking did not.

## Key numbers

- 12,350: API calls across seven models, four families and four thinking budgets
- +0.031 (p = .157): pooled bias-magnitude difference, reasoning minus non-reasoning models; reasoning models were not less biased
- d = 1.89: effect size of anchoring, the only bias that runs in the human direction in all seven models
- 79% / 52%: share of DeepSeek-R1 and Qwen3 calls that exceeded a requested 1,024-token thinking ceiling

## What it reports

- 30 decision vignettes covering six biases (anchoring, framing, loss aversion, escalation of commitment, availability, confirmation), five items each, from the Malberg et al. benchmark.
- Seven models: Claude Haiku 4.5 (thinking and instruct), GPT-5.1, DeepSeek-R1 and V3, Qwen3 thinking and instruct; requested thinking ceilings 0, 1,024, 4,096, 8,192 tokens.
- RQ1: reasoning models leaned more biased in every family (Claude +0.027, DeepSeek +0.026, OpenAI +0.056, Qwen +0.015), none significant after correction; pooled +0.031, t(29) = 1.45, p = .157.
- RQ2: no model's bias magnitude declined with realized reasoning tokens. Claude and GPT-5.1 signed scores drifted further from the human direction (p = .018 and .010).
- Budgets were not what they seemed: Claude honoured ceilings (mean 437, 575, 620 tokens); GPT-5.1 used 116-118 tokens at every ceiling; DeepSeek-R1 and Qwen3 thought 1,074-1,617 tokens even at budget 0.
- RQ3: anchoring present (M = +0.163, d = 1.89). Framing reliably reversed (M = -0.336, d = -2.35). Loss aversion, escalation and confirmation reversed in all seven models but not significant at item level; availability absent.
- RQ4: asking the model to restate every number lowered anchoring on all five items (pooled -0.015), p = .057.

## How they got it

Each vignette has a control and a bias-manipulated version answered on a fixed 7- or 11-point scale; the bias score is the normalised shift between them, signed so positive means human-like. Each cell was sampled ten times at temperature 1.0 through OpenRouter. Reasoning tokens actually consumed were logged and used as the dose. Tests are at item level with Holm correction.

## Limits

- Five items per bias limit construct-level claims; several reversals do not reach significance.
- For DeepSeek and Qwen the reasoning contrast crosses sibling models, so weights differ.
- Realized thinking ranges were narrow for three of four reasoning models.

## Why it matters for companies

Firms using reasoning models for judgment calls such as estimates, risk choices or option comparisons should not assume a "thinking" tier gives more neutral answers. Models in this test did not frame like people; they deviated in the opposite direction, so a human bias checklist would miss the problem. Anchoring on numbers in the prompt persisted at every thinking level. The paper's advice is concrete: audit each deployed model bias by bias and direction, log actual reasoning usage, and test cheap prompt changes before buying more compute.

Original: https://arxiv.org/abs/2610.10049