AgentSense: Benchmarking Social Intelligence of Language Agents through Interactive Scenarios
This addresses the problem of insufficient evaluation for social intelligence in language agents, providing a more comprehensive benchmark for researchers, though it is incremental in building on existing evaluation methods.
The paper tackles the challenge of evaluating language agents' social intelligence by introducing AgentSense, a benchmark with 1,225 diverse social scenarios, and finds that LLMs struggle with complex goals, such as high-level growth needs, and even GPT-4o requires improvement in private information reasoning.
Large language models (LLMs) are increasingly leveraged to empower autonomous agents to simulate human beings in various fields of behavioral research. However, evaluating their capacity to navigate complex social interactions remains a challenge. Previous studies face limitations due to insufficient scenario diversity, complexity, and a single-perspective focus. To this end, we introduce AgentSense: Benchmarking Social Intelligence of Language Agents through Interactive Scenarios. Drawing on Dramaturgical Theory, AgentSense employs a bottom-up approach to create 1,225 diverse social scenarios constructed from extensive scripts. We evaluate LLM-driven agents through multi-turn interactions, emphasizing both goal completion and implicit reasoning. We analyze goals using ERG theory and conduct comprehensive experiments. Our findings highlight that LLMs struggle with goals in complex social scenarios, especially high-level growth needs, and even GPT-4o requires improvement in private information reasoning. Code and data are available at \url{https://github.com/ljcleo/agent_sense}.