Papers › Generative Agents: Interactive Simulacra of Human Behavior

Generative Agents: Interactive Simulacra of Human Behavior

7 Apr 2023arXiv:2304.03442archive 2025-07-28

Joon Sung Park, Joseph C. O'Brien, Carrie J. Cai, Meredith Ringel Morris, Percy Liang, Michael S. Bernstein

Believable proxies of human behavior can empower interactive applications ranging from immersive environments to rehearsal spaces for interpersonal communication to prototyping tools. In this paper, we introduce generative agents--computational software agents that simulate believable human behavior. Generative agents wake up, cook breakfast, and head to work; artists paint, while authors write; they form opinions, notice each other, and initiate conversations; they remember and reflect on days past as they plan the next day. To enable generative agents, we describe an architecture that extends a large language model to store a complete record of the agent's experiences using natural language, synthesize those memories over time into higher-level reflections, and retrieve them dynamically to plan behavior. We instantiate generative agents to populate an interactive sandbox environment inspired by The Sims, where end users can interact with a small town of twenty five agents using natural language. In an evaluation, these generative agents produce believable individual and emergent social behaviors: for example, starting with only a single user-specified notion that one agent wants to throw a Valentine's Day party, the agents autonomously spread invitations to the party over the next two days, make new acquaintances, ask each other out on dates to the party, and coordinate to show up for the party together at the right time. We demonstrate through ablation that the components of our agent architecture--observation, planning, and reflection--each contribute critically to the believability of agent behavior. By fusing large language models with computational, interactive agents, this work introduces architectural and interaction patterns for enabling believable simulations of human behavior.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2304.03442")

Code

Syntology Ran 5 of 12 code samples harvested from 4 repositories linked to this paper; 7 have no recorded run. Of those that ran: 5 ran with no contract checked.

By repository: official repository: 3 samples from 1 repository, 3 ran; community (archive-listed): 9 samples from 3 repositories, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

joonspk-research/generative_agents officialmentioned in papermentioned on GitHubApache-2.0 report
ZhangYiqun018/StickerConv mentioned on GitHubpytorch report
a16z-infra/ai-town mentioned on GitHubMIT report
ejunprung/llm-agents mentioned on GitHub report
jina-ai/thinkgpt mentioned on GitHubApache-2.0 report
litanlitudan/skyagi mentioned on GitHubApache-2.0 report
nickm980/smallville mentioned on GitHubMIT report
renmengjie7/aisimutoolkit mentioned on GitHubApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

12 samples harvested; 5 ran; 0 honoured the contract we drafted; 7 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

5ran
7unverified

Licence: 0 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 4 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

create_folder_if_not_there joonspk-research/generative_agents/environment/frontend_server/global_methods.py official repository ran Apache-2.0 (permissive) · 04d3df25d420010e · report
read_file_to_list joonspk-research/generative_agents/environment/frontend_server/global_methods.py official repository ran Apache-2.0 (permissive) · 48476b17bdfd0043 · report
read_file_to_set joonspk-research/generative_agents/environment/frontend_server/global_methods.py official repository ran Apache-2.0 (permissive) · 219bfa7864169c24 · report
relevance_score_fn litanlitudan/skyagi/skyagi/src/skyagi/simulation/simulation.py community (archive-listed) ran fingerprinted Apache-2.0 (permissive) · 545ba72b86f890f5 · report
verify_pinecone_token litanlitudan/skyagi/skyagi/src/skyagi/util.py community (archive-listed) ran fingerprinted Apache-2.0 (permissive) · 2d779390d2d954c2 · report
fit_context jina-ai/thinkgpt/thinkgpt/helper.py community (archive-listed) unverified Apache-2.0 (permissive) · ea817e6b698cf08e · report
format_options jina-ai/thinkgpt/thinkgpt/gpt_select.py community (archive-listed) unverified Apache-2.0 (permissive) · d52b33b77d35e4ed · report
get_file_stream renmengjie7/aisimutoolkit/AISimuToolKit/utils/utils.py community (archive-listed) unverified Apache-2.0 (permissive) · 2793537d25115ebc · report
get_fromat_len renmengjie7/aisimutoolkit/AISimuToolKit/utils/utils.py community (archive-listed) unverified Apache-2.0 (permissive) · 56a62d76a2e1fb94 · report
get_n_tokens jina-ai/thinkgpt/thinkgpt/helper.py community (archive-listed) unverified Apache-2.0 (permissive) · 4c2c52a526fb9a29 · report
parse_yaml_config renmengjie7/aisimutoolkit/AISimuToolKit/utils/utils.py community (archive-listed) unverified Apache-2.0 (permissive) · ff183b964718e88e · report
verify_openai_ litanlitudan/skyagi/skyagi/src/skyagi/util.py community (archive-listed) unverified Apache-2.0 (permissive) · f1c5580780f0e534 · report

Tasks

Language ModellingLarge Language Model

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections