Qi Deng, Yunzhe Tao, Heng Wang, Xintao Wang, Jiawei Wang, Jen-Tse Huang, Minghao Zhu, Sirui Zheng, Xiaojian Wu, Hongqiu Wu, Qianyu He, Weiyuan Li, and 1 more
We lifted 8 functions out of this paper's own repositories and ran 8 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| Neph0s/Agentopia | canonical | 8 of 8 |
| Function | Status | Where it lives |
|---|---|---|
| build_god_generate_encounter_events_prompt | Ran | Neph0s/Agentopia/src/agents/prompts.py pointer only (licence: NONE) · get_code("556bc8ef821c23a9") |
| build_god_generate_public_events_prompt | Ran | Neph0s/Agentopia/src/agents/prompts.py pointer only (licence: NONE) · get_code("6f10c72b5f05a3ed") |
| dedupe_tool_calls | Ran | Neph0s/Agentopia/src/agents/functions.py pointer only (licence: NONE) · get_code("28cc89d7e126ac5f") |
| load_config | Ran | Neph0s/Agentopia/src/config.py pointer only (licence: NONE) · get_code("fd1f2fb99c1682d5") |
| split_response_by_visible_blocks | Ran | Neph0s/Agentopia/src/world/god.py pointer only (licence: NONE) · get_code("9057eb213b911ec2") |
| strip_roleplay_instructions | Ran | Neph0s/Agentopia/src/agents/response_validator.py pointer only (licence: NONE) · get_code("04dbfdb281faa49c") |
| validate_activity_tags | Ran | Neph0s/Agentopia/src/agents/response_validator.py pointer only (licence: NONE) · get_code("c9c5c57705882aea") |
| validate_solo_activity_format | Ran | Neph0s/Agentopia/src/agents/response_validator.py pointer only (licence: NONE) · get_code("6543f413c07f0517") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Humans learn from social life. Simulating this process with LLM-powered agents represents a promising research direction, raising a natural question: whether LLMs can learn from such simulated social experience to better understand and replicate human behavior. However, prior agent society simulations typically operate at the scale of days, limiting the depth of social interactions and long-term growth. In this paper, we study long-term life simulation and LLM learning in agent societies, with two goals: (1) investigating social behaviors that emerge from life-long simulation, and (2) developing anthropomorphic capabilities in LLMs, particularly intelligence in social life, through years of simulated social experience. Specifically, we present Agentopia, a comprehensive framework for long-term life simulation in multi-agent societies, where 100 agents autonomously pursue personal growth, develop social relationships, and fulfill their needs and goals over 10 simulated years. We define life reward to mirror human well-being, and leverage this reward to train LLMs via rejection sampling. Extensive experiments show that agents exhibit rich emergent social behaviors. Furthermore, life reward training effectively enhances the underlying LLM, which leads to improved agent well-being in simulation, and generalizes to downstream role-playing benchmarks with +15.6% improvement. Our code is available at https://github.com/Neph0s/Agentopia. Figure 1: Illustration of emergent behaviors observed in Agentopia simulations. Each scene depicts a real behavioral pattern documented in our case studies (Tables 22232425262728293031323334). Without explicit scripting, agents autonomously develop diverse behavioral patterns reflecting agents' intelligence in social life.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2606.07513")
get_code_for_paper("2606.07513")
have("2606.07513")
Connect an agent — have() is free.