SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.14744 · NeurIPS · 2024

Large Language Models as Urban Residents: An LLM Agent Framework for Personal Mobility Generation

Jiawei Wang, Renhe Jiang, Chuang Yang, Zengqing Wu, Makoto Onizuka, Ryosuke Shibasaki, Noboru Koshizuka, Chuan Xiao

arXiv · PDF · Open in the Atlas

Code that ran

10 of 12 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 8 failures of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2402.14744.json · badge: /api/ran/2402.14744.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
wangjw6/llmob canonical (classifier label)
classifier basis: census
10 ran · 0 no recorded run
Wangjw6/LLMob canonical (classifier label)
classifier basis: classifier_2025
0 ran · 2 no recorded run
FunctionStatusWhere it lives
ChatGPT_request Ran
ran; our contract draft was wrong, not the code
wangjw6/llmob/engine/llm_configs/gpt_structure.py
pointer only (licence: NONE) · get_code("85856236ef6f0624")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wangjw6/llmob when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

ChatGPT_single_request Ran
ran; our contract draft was wrong, not the code
wangjw6/llmob/engine/llm_configs/gpt_structure.py
pointer only (licence: NONE) · get_code("ad92b5546638d198")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wangjw6/llmob when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

GPT4_request Ran
ran; our contract draft was wrong, not the code
wangjw6/llmob/engine/llm_configs/gpt_structure.py
pointer only (licence: NONE) · get_code("39510c770844add0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wangjw6/llmob when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

find_detail_weekday Ran
ran; our contract draft was wrong, not the code
wangjw6/llmob/engine/utilities/process_tools.py
pointer only (licence: NONE) · get_code("2f5358a7c8fffbd3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wangjw6/llmob when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

first2second Ran
ran; our contract draft was wrong, not the code
wangjw6/llmob/engine/utilities/process_tools.py
pointer only (licence: NONE) · get_code("1f0ddf8359ccad0f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wangjw6/llmob when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

geodistance Ran
ran, honoured the contract we drafted
wangjw6/llmob/evaluate.py
pointer only (licence: NONE) · get_code("b51adc90fd1dd17a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wangjw6/llmob when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

invert_dict Ran
ran; our contract draft was wrong, not the code
wangjw6/llmob/evaluate.py
pointer only (licence: NONE) · get_code("b79ee975818fce6c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wangjw6/llmob when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

is_weekday_or_weekend Ran
ran, honoured the contract we drafted
wangjw6/llmob/engine/utilities/process_tools.py
pointer only (licence: NONE) · get_code("c5cfde42861aeb3d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wangjw6/llmob when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

load_pickle Ran
ran; our contract draft was wrong, not the code
wangjw6/llmob/evaluate.py
pointer only (licence: NONE) · get_code("c00a46bf6fd37d6d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wangjw6/llmob when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

retry Ran
ran; our contract draft was wrong, not the code
wangjw6/llmob/engine/llm_configs/openai_api.py
pointer only (licence: NONE) · get_code("a2c73a26b755a80f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, wangjw6/llmob when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

identify Not yet run
unverified (harvested, no recorded run)
Wangjw6/LLMob/engine/persona_identify.py
pointer only (licence: NONE) · get_code("4654058fd184bc08")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Wangjw6/LLMob when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

score_from_rating Not yet run
unverified (harvested, no recorded run)
Wangjw6/LLMob/engine/persona_identify.py
pointer only (licence: NONE) · get_code("d62b41f423b0831d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Wangjw6/LLMob when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 11 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
load_pickle 1 other paper
1 dated earlier
1702.08359 (2017-02)
Dynamic Word Embeddings

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

This paper introduces a novel approach using Large Language Models (LLMs) integrated into an agent framework for flexible and effective personal mobility generation. LLMs overcome the limitations of previous models by effectively processing semantic data and offering versatility in modeling various tasks. Our approach addresses three research questions: aligning LLMs with real-world urban mobility data, developing reliable activity generation strategies, and exploring LLM applications in urban mobility. The key technical contribution is a novel LLM agent framework that accounts for individual activity patterns and motivations, including a self-consistency approach to align LLMs with real-world activity data and a retrieval-augmented strategy for interpretable activity generation. We evaluate our LLM agent framework and compare it with state-of-the-art personal mobility generation approaches, demonstrating the effectiveness of our approach and its potential applications in urban mobility. Overall, this study marks the pioneering work of designing an LLM agent framework for activity generation based on realworld human activity data, offering a promising tool for urban mobility analysis. Source codes are available at https://github.com/Wangjw6/LLMob/ .

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2402.14744")
get_code_for_paper("2402.14744")
have("2402.14744")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2402.14744.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2402.14744.svg)](https://syntology.ai/paper/2402.14744)

Connect an agent — have() is free.