Jen-Tse Huang, Xuhui Zhou, Sherry Wu, Zhe Su, Svitlana Volkova, Hao, Sophie Feng, Jiaxu Zhou, Hsien-Te Kao, Spencer Lynch, ♣ Tongshuang, Anita Woolley, and 1 more
We lifted 4 functions out of this paper's own repositories and ran 2 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 |
|---|---|---|
| sotopia-lab/sotopia | canonical | 2 of 4 |
| Function | Status | Where it lives |
|---|---|---|
| ainput | Ran | sotopia-lab/sotopia/sotopia/agents/llm_agent.py code served (permissive licence) · get_code("ef0e21681fe7834d") |
| rewrite_gin_args | Ran | sotopia-lab/sotopia/sotopia_conf/gin_utils.py code served (permissive licence) · get_code("5865dbb2f5a0a7fb") |
| add_local_storage_methods | Not yet run | sotopia-lab/sotopia/sotopia/database/base_models.py code served (permissive licence) · get_code("3ef7d1c35e5c2efa") |
| patch_model_for_local_storage | Not yet run | sotopia-lab/sotopia/sotopia/database/base_models.py code served (permissive licence) · get_code("9cc85d7b201f9236") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Social simulation through large language model (LLM) agents is a promising approach to explore and validate hypotheses related to social science questions and LLM agents behavior. We present SOTOPIA-S 4 , a fast, flexible, and scalable social simulation system that addresses the technical barriers of current frameworks while enabling practitioners to generate multi-turn and multi-party LLM-based interactions with customizable evaluation metrics for hypothesis testing. SOTOPIA-S 4 comes as a pip package that contains a simulation engine, an API server with flexible RESTful APIs for simulation management, and a web interface that enables both technical and non-technical users to design, run, and analyze simulations without programming. We demonstrate the usefulness of SOTOPIA-S 4 with two use cases involving dyadic hiring negotiation and multiparty planning scenarios.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2504.16122")
get_code_for_paper("2504.16122")
have("2504.16122")
Connect an agent — have() is free.