Engagement in Code Review: Emotional, Behavioral, and Cognitive Dimensions in Peer vs. LLM Interactions

TL;DR

This study examines how software engineers engage in LLM-assisted versus peer code reviews, proposing an integrative model that links emotional self-regulation to behavioral engagement and resolution. Through a two-phase qualitative design with 20 engineers and a Phase II prompt-engineering enhancement, the authors show that LLM feedback can reduce emotional costs while shifting cognitive load, with alignment between user preferences and prompt design predicting higher adoption. The findings refine engagement theory by introducing social calibration as a relational control mechanism and highlighting an accountability shift in AI-assisted contexts. Practically, AI should function as a supportive partner that preserves human accountability and social meaning in code review, using hybrid workflows and governance to sustain team norms and learning.

Abstract

Code review is a socio-technical practice, yet how software engineers engage in Large Language Model (LLM)-assisted code reviews compared to human peer-led reviews is less understood. We report a two-phase qualitative study with 20 software engineers to understand this. In Phase I, participants exchanged peer reviews and were interviewed about their affective responses and engagement decisions. In Phase II, we introduced a new prompt matching engineers' preferences and probed how characteristics shaped their reactions. We develop an integrative account linking emotional self-regulation to behavioral engagement and resolution. We identify self-regulation strategies that engineers use to regulate their emotions in response to negative feedback: reframing, dialogic regulation, avoidance, and defensiveness. Engagement proceeds through social calibration; engineers align their responses and behaviors to the relational climate and team norms. Trajectories to resolution, in the case of peer-led review, vary by locus (solo/dyad/team) and an internal sense-making process. With the LLM-assisted review, emotional costs and the need for self-regulation seem lower. When LLM feedback aligned with engineers' cognitive expectations, participants reported reduced processing effort and a potentially higher tendency to adopt. We show that LLM-assisted review redirects engagement from emotion management to cognitive load management. We contribute an integrative model of engagement that links emotional self-regulation to behavioral engagement and resolution, showing how affective and cognitive processes influence feedback adoption in peer-led and LLM-assisted code reviews. We conclude that AI is best positioned as a supportive partner to reduce cognitive and emotional load while preserving human accountability and the social meaning of peer review and similar socio-technical activities.

Figures (6)

• Figure 1: An abstract presentation of the findings from Alami & Ernst alami2025human, capturing engagement and how engineers respond to feedback. The line from Reviewer Context to Peer and LLM indicates two type of reviewers, and the ovals inside the rectangles are elements of the reviewer contexts.
• Figure 2: Phase I Research Process.
• Figure 3: Phase II Research Process.
• Figure 4: High-level model (RQ1) of code-review engagement: emotional engagement $\leftrightarrow$ behavioral engagement $\rightarrow$ resolution and implementation (adoption, learning and team-norm codification); LLM content features moderate cognitive accessibility, improving adoption likelihood.
• Figure 5: RQ2 - Emotional Engagement.