Agents with Feelings? Personality and Emotion in Multi-Agent Software Teams
For developers of multi-agent LLM systems, this paper identifies agent behavioral profiles as a critical design dimension affecting both task outcomes and collaboration efficiency.
This paper investigates how personality and emotion profiles affect the performance and collaboration dynamics of multi-agent LLM systems in software engineering tasks. Results show that profile choice can cause up to 11.3 percentage point differences in pass@1 for code generation, and mixed profiles often outperform shared profiles, while certain profiles increase cost without performance gains.
Multi-agent LLM systems for Software Engineering (SE) typically differentiate agents through roles and workflows, but little is known about how agents' behavioral profiles affect team performance. We investigate the impact of personality and emotion profiles on LLM agent teams using a psychology-informed framework that combines Big Five personality traits, basic emotions, SE-relevant work styles, and task roles. We evaluate 78 team-profile configurations across code generation and code review using four LLMs and 659 task instances. Results show that profile choice substantially affects both performance and team behavior. For code generation, the gap between the best and worst shared-profile configurations reaches 7.1-11.3 percentage points in pass@1 across models, while the best mixed-profile configuration outperforms the best shared-profile configuration in six of eight model-task settings. Profiles also influence collaboration dynamics and cost: fear and high-conscientiousness profiles increase revision activity, over-revision, and token usage without consistent performance gains. These findings identify agent profiles as an important design dimension in multi-agent SE systems, affecting not only task outcomes but also the efficiency of collaboration.