# EgoSocialArena: Benchmarking the Social Intelligence of Large Language Models from a First-person Perspective

arXiv: https://arxiv.org/abs/2410.06195 · HTML: https://mlsanity.com/paper/2410.06195/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 40 references that are in the map.
- First posted on arXiv 8 Oct 2024.

## Builds on (most cited first, 26 of 26)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [An Embodied Generalist Agent in 3D World](https://mlsanity.com/paper/2311.12871/) (2023)
- [Machine Theory of Mind](https://mlsanity.com/paper/1802.07740/) (2018)
- [Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMs](https://mlsanity.com/paper/2210.13312/) (2022)
- [Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedback](https://mlsanity.com/paper/2305.10142/) (2023)
- [Understanding Social Reasoning in Language Models with Language Models](https://mlsanity.com/paper/2306.15448/) (2023)
- [FANToM: A Benchmark for Stress-testing Machine Theory of Mind in Interactions](https://mlsanity.com/paper/2310.15421/) (2023)
- [The Earth is Flat because...: Investigating LLMs' Belief towards Misinformation via Persuasive Conversation](https://mlsanity.com/paper/2312.09085/) (2023)
- [How Well Can LLMs Negotiate? NegotiationArena Platform and Analysis](https://mlsanity.com/paper/2402.05863/) (2024)
- [EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real World](https://mlsanity.com/paper/2403.16182/) (2024)
- [Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimization](https://mlsanity.com/paper/2402.17574/) (2024)
- [Can Large Language Models Serve as Rational Players in Game Theory? A Systematic Analysis](https://mlsanity.com/paper/2312.05488/) (2023)
- [Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs](https://mlsanity.com/paper/2407.04694/) (2024)
- [Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4](https://mlsanity.com/paper/2309.17277/) (2023)
- [NormBank: A Knowledge Bank of Situational Social Norms](https://mlsanity.com/paper/2305.17008/) (2023)
- [NegotiationToM: A Benchmark for Stress-testing Machine Theory of Mind on Negotiation Surrounding](https://mlsanity.com/paper/2404.13627/) (2024)
- [AGENT: A Benchmark for Core Psychological Reasoning](https://mlsanity.com/paper/2102.12321/) (2021)
- [Baby Intuitions Benchmark (BIB): Discerning the goals, preferences, and actions of others](https://mlsanity.com/paper/2102.11938/) (2021)
- [RLCard: A Toolkit for Reinforcement Learning in Card Games](https://mlsanity.com/paper/1910.04376/) (2019)
- [TimeToM: Temporal Space is the Key to Unlocking the Door of Large Language Models' Theory-of-Mind](https://mlsanity.com/paper/2407.01455/) (2024)
- [Unlocking Exocentric Video-Language Data for Egocentric Video Representation Learning](https://mlsanity.com/paper/2408.03567/) (2024)
- [Social Intelligence Data Infrastructure: Structuring the Present and Navigating the Future](https://mlsanity.com/paper/2403.14659/) (2024)

## Built on by (most cited first, 10 of 10)

- [Agentic Large Language Models, a survey](https://mlsanity.com/paper/2503.23037/) (2025)
- [Generative to Agentic AI: Survey, Conceptualization, and Challenges](https://mlsanity.com/paper/2504.18875/) (2025)
- [Rethinking Theory of Mind Benchmarks for LLMs: Towards A User-Centered Perspective](https://mlsanity.com/paper/2504.10839/) (2025)
- [Deceive, Detect, and Disclose: Large Language Models Play Mini-Mafia](https://mlsanity.com/paper/2509.23023/) (2025)
- [One Model, All Roles: Multi-Turn, Multi-Agent Self-Play Reinforcement Learning for Conversational Social Intelligence](https://mlsanity.com/paper/2602.03109/) (2026)
- [Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence](https://mlsanity.com/paper/2608.31075/) (2026)
- [PRISON: Unmasking the Criminal Potential of Large Language Models](https://mlsanity.com/paper/2506.16150/) (2025)
- [Think Thrice Before You Speak: Dual knowledge-enhanced Theory-of-Mind Reasoning for Persuasive Agents](https://mlsanity.com/paper/2605.22602/) (2026)
- [Learning Dynamic Belief Graphs for Theory-of-mind Reasoning](https://mlsanity.com/paper/2603.20170/) (2026)
- [Belief Without Behavior: Measuring the Translation of Theory of Mind into Coordinated Social Action in Vision-Language Models](https://mlsanity.com/paper/2608.20975/) (2026)

## Abstract (arXiv)

Social intelligence is built upon three foundational pillars: cognitive intelligence, situational intelligence, and behavioral intelligence. As large language models (LLMs) become increasingly integrated into our social lives, understanding, evaluating, and developing their social intelligence are becoming increasingly important. While multiple existing works have investigated the social intelligence of LLMs, (1) most focus on a specific aspect, and the social intelligence of LLMs has yet to be systematically organized and studied; (2) position LLMs as passive observers from a third-person perspective, such as in Theory of Mind (ToM) tests. Compared to the third-person perspective, ego-centric first-person perspective evaluation can align well with actual LLM-based Agent use scenarios. (3) a lack of comprehensive evaluation of behavioral intelligence, with specific emphasis on incorporating critical human-machine interaction scenarios. In light of this, we present EgoSocialArena, a novel framework grounded in the three pillars of social intelligence: cognitive, situational, and behavioral intelligence, aimed to systematically evaluate the social intelligence of LLMs from a first-person perspective. With EgoSocialArena, we conduct a comprehensive evaluation of eight prominent foundation models, even the most advanced LLMs like O1-preview lag behind human performance.