Personality and emotion profiles substantially change multi-agent LLM team pass rates, review scores, revision behavior, and token cost on code generation and code review, with mixed profiles often beating shared ones.
Humaneval pro and mbpp pro: Evaluating large language models on self-invoking code generation task,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Agents with Feelings? Personality and Emotion in Multi-Agent Software Teams
Personality and emotion profiles substantially change multi-agent LLM team pass rates, review scores, revision behavior, and token cost on code generation and code review, with mixed profiles often beating shared ones.