SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2312.09397 · 2023

Personalized Autonomous Driving with Large Language Models: Field Experiments

arXiv · PDF · Open in the Atlas

Code that ran

3 of 6 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; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 0 failures of our instrument; 3 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/2312.09397.json · badge: /api/ran/2312.09397.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
purduedigitaltwin/talk2drive community (classifier label)
classifier basis not recorded on the link
3 ran · 3 no recorded run
FunctionStatusWhere it lives
have_word_in_list Ran
ran on a synthesized input
purduedigitaltwin/talk2drive/utils/baseline.py
code served (permissive licence) · get_code("f577c6d7aa23ba3e")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned bool, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

# Analyze the function: have_word_in_list(word_list, sentence)
# - word_list: iterable of words, each checked with 'in' operator against sentence
# - sentence: string that supports 'in' operator for substring matching

# Create simple test data
word_list = ["hello", "world", "python"]
sentence = "hello there, this is a test"

ARGS = {
    "word_list": word_list,
    "sentence": sentence
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bool, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
record_timestamp Ran
ran on a synthesized input
purduedigitaltwin/talk2drive/utils/log_gen.py
code served (permissive licence) · get_code("ae11bcc2d7c1a436")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned float, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import time

def record_timestamp(name, previous_time=None):
    current_time = time.time()
    print(f"{name} at {time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(current_time))}", end='')
    if previous_time is not None:
        interval = current_time - previous_time
        print(f', lasted {interval:.2f} seconds')
    else:
        print()
    return current_time

# Setup code
import time

# First call to get a previous_time value
first_timestamp = time.time()
time.sleep(0.01)  # Small sleep to ensure time difference

ARGS = {
    "name": "test_operation",
    "previous_time": first_timestamp
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
rule_based_action Ran
ran on a synthesized input
purduedigitaltwin/talk2drive/utils/baseline.py
code served (permissive licence) · get_code("7fe56ae5724e363c")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

# Set seed for reproducibility
torch.manual_seed(0)

# The function rule_based_action takes two parameters:
# 1. template_name: a string that determines which rule template to use ('highway', 'intersection', or 'parking')
# 2. command: a string containing the user's command/instruction

# The function uses these parameters as follows:
# - template_name: compared against string literals ('highway', 'intersection', 'parking')
# - command: passed to have_word_in_list which checks if any word from word_list is in command

# Create valid test arguments
ARGS = {
    'template_name': 'highway',
    'command': 'speed up and overtake on the left lane'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_speed_limit Not yet run
unverified (harvested, no recorded run)
purduedigitaltwin/talk2drive/utils/get_driving_context.py
code served (permissive licence) · get_code("9648cebc40330cfd")
How it ran

no invocation recorded.

get_traffic_info Not yet run
unverified (harvested, no recorded run)
purduedigitaltwin/talk2drive/utils/get_driving_context.py
code served (permissive licence) · get_code("d95aa52626555363")
How it ran

no invocation recorded.

get_weather_info Not yet run
unverified (harvested, no recorded run)
purduedigitaltwin/talk2drive/utils/get_driving_context.py
code served (permissive licence) · get_code("9d07bbb0d97c2642")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 6 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.

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

Integrating large language models (LLMs) in autonomous vehicles enables conversation with AI systems to drive the vehicle. However, it also emphasizes the requirement for such systems to comprehend commands accurately and achieve higher-level personalization to adapt to the preferences of drivers or passengers over a more extended period. In this paper, we introduce an LLM-based framework, Talk2Drive, capable of translating natural verbal commands into executable controls and learning to satisfy personal preferences for safety, efficiency, and comfort with a proposed memory module. This is the first-of-its-kind multi-scenario field experiment that deploys LLMs on a real-world autonomous vehicle. Experiments showcase that the proposed system can comprehend human intentions at different intuition levels, ranging from direct commands like "can you drive faster" to indirect commands like "I am really in a hurry now". Additionally, we use the takeover rate to quantify the trust of human drivers in the LLM-based autonomous driving system, where Talk2Drive significantly reduces the takeover rate in highway, intersection, and parking scenarios. We also validate that the proposed memory module considers personalized preferences and further reduces the takeover rate by up to 65.2% compared with those without a memory module. The experiment video can be watched at https://www.youtube.com/watch?v=4BWsfPaq1Ro

For agents

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

get_harvested_code_for_paper("2312.09397")
get_code_for_paper("2312.09397")
have("2312.09397")

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

curl https://syntology.ai/api/ran/2312.09397.json

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

[![Syntology run record](https://syntology.ai/api/ran/2312.09397.svg)](https://syntology.ai/paper/2312.09397)

Connect an agent — have() is free.