Agents with Feelings? Personality and Emotion in Multi-Agent Software Teams

arXiv 2607.05659 ↗First posted 6 Jul 2026cs.SEcited by 0

On the map: LLM agents and tool use → Software engineering coding agents

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 39 of its 73 references that are in the map. First posted on arXiv 6 Jul 2026.

Builds on

39 of 73 references.

Closest ancestors · 3

Same direction, newest first

Other references · 36

2024The Llama 3 Herd of Modelscited by 14,715
2021Evaluating Large Language Models Trained on Codecited by 8,320
2024Qwen2.5 Technical Reportcited by 4,942
2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
2021Program Synthesis with Large Language Modelscited by 3,637
2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
2023Code Llama: Open Foundation Models for Codecited by 2,139
2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 2,004
2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,808
2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,395
2023Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generationcited by 1,391

24 more

2023AWQ: Activation-aware Weight Quantization for LLM Compression and Accelerationcited by 1,298
2022CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesiscited by 885
2023StarCoder: may the source be with you!cited by 799
2022Out of One, Many: Using Language Models to Simulate Human Samplescited by 752
2024A Survey on Large Language Models for Code Generationcited by 658
2023AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviorscited by 598
2024BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructionscited by 546
2023Large Language Models for Software Engineering: A Systematic Literature Reviewcited by 399
2024Scaling Large Language Model-based Multi-Agent Collaborationcited by 241
2023PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traitscited by 234
2023Large Language Models for Software Engineering: Survey and Open Problemscited by 181
2023Personality Traits in Large Language Modelscited by 169
2023Large Language Models Understand and Can be Enhanced by Emotional Stimulicited by 146
2022Evaluating and Inducing Personality in Pre-trained Language Modelscited by 123
2022Automating Code Review Activities by Large-Scale Pre-trainingcited by 98
2024MAgICoRe: Multi-Agent, Iterative, Coarse-to-Fine Refinement for Reasoningcited by 41
2025CodeIF: Benchmarking the Instruction-Following Capabilities of Large Language Models for Code Generationcited by 19
2025Can LLMs Generate High-Quality Test Cases for Algorithm Problems? TestCase-Eval: A Systematic Evaluation of Fault Coverage and Exposurecited by 10
2025The Power of Personality: A Human Simulation Perspective to Investigate Large Language Model Agentscited by 8
2025Automated Code Review Using Large Language Models at Ericsson: An Experience Reportcited by 5
2026How Many Tries Does It Take? Iterative Self-Repair in LLM Code Generation Across Model Scales and Benchmarkscited by 5
2024Personality-Guided Code Generation Using Large Language Modelscited by 3
2025MIMIC: Integrating Diverse Personality Traits for Better Game Testing Using Large Language Modelcited by 1
2026Towards Automated Crowdsourced Testing via Personified-LLMcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way