# AnthroDial: Benchmarking LLM Anthropomorphism in Autonomous Social Interaction

arXiv: https://arxiv.org/abs/2609.37853 · HTML: https://mlsanity.com/paper/2609.37853/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 35 references that are in the map.
- First posted on arXiv 29 Sep 2026.

## Builds on (most cited first, 23 of 23)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [Role-Play with Large Language Models](https://mlsanity.com/paper/2305.16367/) (2023)
- [PersonaGym: Evaluating Persona Agents and LLMs](https://mlsanity.com/paper/2407.18416/) (2024)
- [SimBench: Benchmarking the Ability of Large Language Models to Simulate Human Behaviors](https://mlsanity.com/paper/2510.17516/) (2025)
- [SocialBench: Sociality Evaluation of Role-Playing Conversational Agents](https://mlsanity.com/paper/2403.13679/) (2024)
- [Know You First and Be You Better: Modeling Human-Like User Simulators via Implicit Profiles](https://mlsanity.com/paper/2502.18968/) (2025)
- [CharacterBox: Evaluating the Role-Playing Capabilities of LLMs in Text-Based Virtual Worlds](https://mlsanity.com/paper/2412.05631/) (2024)
- [HumanLM: Simulating Users with State Alignment Beats Response Imitation](https://mlsanity.com/paper/2603.03303/) (2026)
- [Proactive Conversational Agents with Inner Thoughts](https://mlsanity.com/paper/2501.00383/) (2024)
- [AI Companions Reduce Loneliness](https://mlsanity.com/paper/2407.19096/) (2024)
- [Can LLM Agents Simulate Multi-Turn Human Behavior? Evidence from Real Online Customer Behavior Data](https://mlsanity.com/paper/2503.20749/) (2025)
- [Multi-turn Evaluation of Anthropomorphic Behaviours in Large Language Models](https://mlsanity.com/paper/2502.07077/) (2025)
- [How Far are LLMs from Being Our Digital Twins? A Benchmark for Persona-Based Behavior Chain Simulation](https://mlsanity.com/paper/2502.14642/) (2025)
- [Human Simulacra: Benchmarking the Personification of Large Language Models](https://mlsanity.com/paper/2402.18180/) (2024)
- [TwinVoice: A Multi-dimensional Benchmark Towards Digital Twins via LLM Persona Simulation](https://mlsanity.com/paper/2510.25536/) (2025)
- [OdysSim: Building Foundation Models for Human Behavior Simulation](https://mlsanity.com/paper/2606.14199/) (2026)
- [SPASM: Stable Persona-driven Agent Simulation for Multi-turn Dialogue Generation](https://mlsanity.com/paper/2604.09212/) (2026)
- [Reinforcing Human Behavior Simulation via Verbal Feedback](https://mlsanity.com/paper/2605.20506/) (2026)
- [HumanLLM: Benchmarking and Improving LLM Anthropomorphism via Human Cognitive Patterns](https://mlsanity.com/paper/2601.10198/) (2026)
- [Beyond Static Personas: Situational Personality Steering for Large Language Models](https://mlsanity.com/paper/2604.13846/) (2026)
- [Your LLM, Your Style: Behavioral Mode Axes for LLM Behavioral Control](https://mlsanity.com/paper/2608.10703/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are increasingly deployed as social agents, yet credible human-like interaction requires more than fluent responses or persona consistency. Agents must autonomously decide whether, when, and how to communicate while adapting to evolving contexts, goals, and relationships. Existing research, however, lacks a unified approach to enabling, evaluating, and improving such capabilities in continuous, open-ended interaction. We introduce AnthroDial, a unified framework for developing anthropomorphic social agents from three complementary aspects: MindFlow, a lightweight interaction harness that enables autonomous, asynchronous, and adaptive communication through a dynamic Mind Buffer; CAPS-Eval, a theory-grounded framework for evaluating cognitive, affective, and behavioral dimensions of anthropomorphic interaction; and a scalable training paradigm that combines SEEDS for environment expansion with DiAPO for adaptive capability optimization. We further construct evaluation datasets covering everyday communication, game interaction, and long-horizon character interaction. Extensive experiments across diverse models and scenarios demonstrate improved interaction autonomy and naturalness, validate the reliability, discriminativeness, and agreement with human rankings of CAPS-Eval, and confirm the effectiveness of our training paradigm. Together, these components provide a unified framework for developing credible human-like social agents in open-ended interaction.