Generating Planning Feedback for Open-Ended Programming Exercises with LLMs Article Swipe

PDF

Mehmet Arif Demirtaş , Claire Zheng , Max Fowler , Kathryn Cunningham ·

YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2504.08958

To complete an open-ended programming exercise, students need to both plan a high-level solution and implement it using the appropriate syntax. However, these problems are often autograded on the correctness of the final submission through test cases, and students cannot get feedback on their planning process. Large language models (LLM) may be able to generate this feedback by detecting the overall code structure even for submissions with syntax errors. To this end, we propose an approach that detects which high-level goals and patterns (i.e. programming plans) exist in a student program with LLMs. We show that both the full GPT-4o model and a small variant (GPT-4o-mini) can detect these plans with remarkable accuracy, outperforming baselines inspired by conventional approaches to code analysis. We further show that the smaller, cost-effective variant (GPT-4o-mini) achieves results on par with state-of-the-art (GPT-4o) after fine-tuning, creating promising implications for smaller models for real-time grading. These smaller models can be incorporated into autograders for open-ended code-writing exercises to provide feedback for students' implicit planning skills, even when their program is syntactically incorrect. Furthermore, LLMs may be useful in providing feedback for problems in other domains where students start with a set of high-level solution steps and iteratively compute the output, such as math and physics problems.

Related Topics

Production Planning

Metropolitan Planning Organization

Flight Planning

Environmental Planning

Enterprise Resource Planning

Three Mile Island Nuclear Generating Station

San Onofre Nuclear Generating Station

Vogtle Electric Generating Plant

Urban Planning

Palo Verde Nuclear Generating Station

Nintendo Entertainment Planning & Development

Positive Feedback

Concepts

No concepts available.

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2504.08958
PDF: https://arxiv.org/pdf/2504.08958
OA Status: green
OpenAlex ID: https://openalex.org/W4415154351

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4415154351

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2504.08958

Digital Object Identifier
Title: Generating Planning Feedback for Open-Ended Programming Exercises with LLMs

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2025

Year of publication
Publication date: 2025-04-11

Full publication date if available
Authors: Mehmet Arif Demirtaş, Claire Zheng, Max Fowler, Kathryn Cunningham

List of authors in order
Landing page: https://arxiv.org/abs/2504.08958

Publisher landing page
PDF URL: https://arxiv.org/pdf/2504.08958

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: green

Open access status per OpenAlex
OA URL: https://arxiv.org/pdf/2504.08958

Direct OA link when available
Cited by: 0

Total citation count in OpenAlex

Full payload

id	https://openalex.org/W4415154351
doi	https://doi.org/10.48550/arxiv.2504.08958
ids.doi	https://doi.org/10.48550/arxiv.2504.08958
ids.openalex	https://openalex.org/W4415154351
fwci
type	preprint
title	Generating Planning Feedback for Open-Ended Programming Exercises with LLMs
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
topics[0].id	https://openalex.org/T11902
topics[0].field.id	https://openalex.org/fields/17
topics[0].field.display_name	Computer Science
topics[0].score	0.9781000018119812
topics[0].domain.id	https://openalex.org/domains/3
topics[0].domain.display_name	Physical Sciences
topics[0].subfield.id	https://openalex.org/subfields/1702
topics[0].subfield.display_name	Artificial Intelligence
topics[0].display_name	Intelligent Tutoring Systems and Adaptive Learning
topics[1].id	https://openalex.org/T10906
topics[1].field.id	https://openalex.org/fields/17
topics[1].field.display_name	Computer Science
topics[1].score	0.9677000045776367
topics[1].domain.id	https://openalex.org/domains/3
topics[1].domain.display_name	Physical Sciences
topics[1].subfield.id	https://openalex.org/subfields/1702
topics[1].subfield.display_name	Artificial Intelligence
topics[1].display_name	AI-based Problem Solving and Planning
topics[2].id	https://openalex.org/T10533
topics[2].field.id	https://openalex.org/fields/17
topics[2].field.display_name	Computer Science
topics[2].score	0.9463000297546387
topics[2].domain.id	https://openalex.org/domains/3
topics[2].domain.display_name	Physical Sciences
topics[2].subfield.id	https://openalex.org/subfields/1706
topics[2].subfield.display_name	Computer Science Applications
topics[2].display_name	Teaching and Learning Programming
is_xpac	False
apc_list
apc_paid
language	en
locations[0].id	pmh:oai:arXiv.org:2504.08958
locations[0].is_oa	True
locations[0].source.id	https://openalex.org/S4306400194
locations[0].source.issn
locations[0].source.type	repository
locations[0].source.is_oa	True
locations[0].source.issn_l
locations[0].source.is_core	False
locations[0].source.is_in_doaj	False
locations[0].source.display_name	arXiv (Cornell University)
locations[0].source.host_organization	https://openalex.org/I205783295
locations[0].source.host_organization_name	Cornell University
locations[0].source.host_organization_lineage	https://openalex.org/I205783295
locations[0].license
locations[0].pdf_url	https://arxiv.org/pdf/2504.08958
locations[0].version	submittedVersion
locations[0].raw_type	text
locations[0].license_id
locations[0].is_accepted	False
locations[0].is_published	False
locations[0].raw_source_name
locations[0].landing_page_url	http://arxiv.org/abs/2504.08958
locations[1].id	doi:10.48550/arxiv.2504.08958
locations[1].is_oa	True
locations[1].source.id	https://openalex.org/S4306400194
locations[1].source.issn
locations[1].source.type	repository
locations[1].source.is_oa	True
locations[1].source.issn_l
locations[1].source.is_core	False
locations[1].source.is_in_doaj	False
locations[1].source.display_name	arXiv (Cornell University)
locations[1].source.host_organization	https://openalex.org/I205783295
locations[1].source.host_organization_name	Cornell University
locations[1].source.host_organization_lineage	https://openalex.org/I205783295
locations[1].license
locations[1].pdf_url
locations[1].version
locations[1].raw_type	article
locations[1].license_id
locations[1].is_accepted	False
locations[1].is_published
locations[1].raw_source_name
locations[1].landing_page_url	https://doi.org/10.48550/arxiv.2504.08958
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5011668727
authorships[0].author.orcid	https://orcid.org/0000-0001-5674-5878
authorships[0].author.display_name	Mehmet Arif Demirtaş
authorships[0].author_position	first
authorships[0].raw_author_name	Demirtaş, Mehmet Arif
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5089769413
authorships[1].author.orcid
authorships[1].author.display_name	Claire Zheng
authorships[1].author_position	middle
authorships[1].raw_author_name	Zheng, Claire
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5091001653
authorships[2].author.orcid	https://orcid.org/0000-0002-4730-447X
authorships[2].author.display_name	Max Fowler
authorships[2].author_position	middle
authorships[2].raw_author_name	Fowler, Max
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5011238152
authorships[3].author.orcid	https://orcid.org/0000-0002-9702-2796
authorships[3].author.display_name	Kathryn Cunningham
authorships[3].author_position	last
authorships[3].raw_author_name	Cunningham, Kathryn
authorships[3].is_corresponding	False
has_content.pdf	False
has_content.grobid_xml	False
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://arxiv.org/pdf/2504.08958
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-14T00:00:00
display_name	Generating Planning Feedback for Open-Ended Programming Exercises with LLMs
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T06:51:31.235846
primary_topic.id	https://openalex.org/T11902
primary_topic.field.id	https://openalex.org/fields/17
primary_topic.field.display_name	Computer Science
primary_topic.score	0.9781000018119812
primary_topic.domain.id	https://openalex.org/domains/3
primary_topic.domain.display_name	Physical Sciences
primary_topic.subfield.id	https://openalex.org/subfields/1702
primary_topic.subfield.display_name	Artificial Intelligence
primary_topic.display_name	Intelligent Tutoring Systems and Adaptive Learning
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2504.08958
best_oa_location.is_oa	True
best_oa_location.source.id	https://openalex.org/S4306400194
best_oa_location.source.issn
best_oa_location.source.type	repository
best_oa_location.source.is_oa	True
best_oa_location.source.issn_l
best_oa_location.source.is_core	False
best_oa_location.source.is_in_doaj	False
best_oa_location.source.display_name	arXiv (Cornell University)
best_oa_location.source.host_organization	https://openalex.org/I205783295
best_oa_location.source.host_organization_name	Cornell University
best_oa_location.source.host_organization_lineage	https://openalex.org/I205783295
best_oa_location.license
best_oa_location.pdf_url	https://arxiv.org/pdf/2504.08958
best_oa_location.version	submittedVersion
best_oa_location.raw_type	text
best_oa_location.license_id
best_oa_location.is_accepted	False
best_oa_location.is_published	False
best_oa_location.raw_source_name
best_oa_location.landing_page_url	http://arxiv.org/abs/2504.08958
primary_location.id	pmh:oai:arXiv.org:2504.08958
primary_location.is_oa	True
primary_location.source.id	https://openalex.org/S4306400194
primary_location.source.issn
primary_location.source.type	repository
primary_location.source.is_oa	True
primary_location.source.issn_l
primary_location.source.is_core	False
primary_location.source.is_in_doaj	False
primary_location.source.display_name	arXiv (Cornell University)
primary_location.source.host_organization	https://openalex.org/I205783295
primary_location.source.host_organization_name	Cornell University
primary_location.source.host_organization_lineage	https://openalex.org/I205783295
primary_location.license
primary_location.pdf_url	https://arxiv.org/pdf/2504.08958
primary_location.version	submittedVersion
primary_location.raw_type	text
primary_location.license_id
primary_location.is_accepted	False
primary_location.is_published	False
primary_location.raw_source_name
primary_location.landing_page_url	http://arxiv.org/abs/2504.08958
publication_date	2025-04-11
publication_year	2025
referenced_works_count	0
abstract_inverted_index.a	11, 88, 102, 193
abstract_inverted_index.To	0, 69
abstract_inverted_index.We	93, 122
abstract_inverted_index.an	2, 74
abstract_inverted_index.as	205
abstract_inverted_index.be	51, 153, 179
abstract_inverted_index.by	57, 116
abstract_inverted_index.in	87, 181, 186
abstract_inverted_index.is	173
abstract_inverted_index.it	16
abstract_inverted_index.of	30, 195
abstract_inverted_index.on	27, 42, 133
abstract_inverted_index.to	8, 53, 119, 161
abstract_inverted_index.we	72
abstract_inverted_index.and	14, 37, 81, 101, 199, 207
abstract_inverted_index.are	24
abstract_inverted_index.can	106, 152
abstract_inverted_index.for	64, 143, 146, 157, 164, 184
abstract_inverted_index.get	40
abstract_inverted_index.may	50, 178
abstract_inverted_index.par	134
abstract_inverted_index.set	194
abstract_inverted_index.the	18, 28, 31, 59, 97, 126, 202
abstract_inverted_index.LLMs	177
abstract_inverted_index.able	52
abstract_inverted_index.both	9, 96
abstract_inverted_index.code	61, 120
abstract_inverted_index.end,	71
abstract_inverted_index.even	63, 169
abstract_inverted_index.full	98
abstract_inverted_index.into	155
abstract_inverted_index.math	206
abstract_inverted_index.need	7
abstract_inverted_index.plan	10
abstract_inverted_index.show	94, 124
abstract_inverted_index.such	204
abstract_inverted_index.test	35
abstract_inverted_index.that	76, 95, 125
abstract_inverted_index.this	55, 70
abstract_inverted_index.when	170
abstract_inverted_index.with	66, 91, 110, 135, 192
abstract_inverted_index.(LLM)	49
abstract_inverted_index.(i.e.	83
abstract_inverted_index.LLMs.	92
abstract_inverted_index.Large	46
abstract_inverted_index.These	149
abstract_inverted_index.after	138
abstract_inverted_index.exist	86
abstract_inverted_index.final	32
abstract_inverted_index.goals	80
abstract_inverted_index.model	100
abstract_inverted_index.often	25
abstract_inverted_index.other	187
abstract_inverted_index.plans	109
abstract_inverted_index.small	103
abstract_inverted_index.start	191
abstract_inverted_index.steps	198
abstract_inverted_index.their	43, 171
abstract_inverted_index.these	22, 108
abstract_inverted_index.using	17
abstract_inverted_index.where	189
abstract_inverted_index.which	78
abstract_inverted_index.GPT-4o	99
abstract_inverted_index.cannot	39
abstract_inverted_index.cases,	36
abstract_inverted_index.detect	107
abstract_inverted_index.models	48, 145, 151
abstract_inverted_index.plans)	85
abstract_inverted_index.syntax	67
abstract_inverted_index.useful	180
abstract_inverted_index.compute	201
abstract_inverted_index.detects	77
abstract_inverted_index.domains	188
abstract_inverted_index.errors.	68
abstract_inverted_index.further	123
abstract_inverted_index.output,	203
abstract_inverted_index.overall	60
abstract_inverted_index.physics	208
abstract_inverted_index.program	90, 172
abstract_inverted_index.propose	73
abstract_inverted_index.provide	162
abstract_inverted_index.results	132
abstract_inverted_index.skills,	168
abstract_inverted_index.smaller	144, 150
abstract_inverted_index.student	89
abstract_inverted_index.syntax.	20
abstract_inverted_index.through	34
abstract_inverted_index.variant	104, 129
abstract_inverted_index.(GPT-4o)	137
abstract_inverted_index.However,	21
abstract_inverted_index.achieves	131
abstract_inverted_index.approach	75
abstract_inverted_index.complete	1
abstract_inverted_index.creating	140
abstract_inverted_index.feedback	41, 56, 163, 183
abstract_inverted_index.generate	54
abstract_inverted_index.grading.	148
abstract_inverted_index.implicit	166
abstract_inverted_index.inspired	115
abstract_inverted_index.language	47
abstract_inverted_index.patterns	82
abstract_inverted_index.planning	44, 167
abstract_inverted_index.problems	23, 185
abstract_inverted_index.process.	45
abstract_inverted_index.smaller,	127
abstract_inverted_index.solution	13, 197
abstract_inverted_index.students	6, 38, 190
abstract_inverted_index.accuracy,	112
abstract_inverted_index.analysis.	121
abstract_inverted_index.baselines	114
abstract_inverted_index.detecting	58
abstract_inverted_index.exercise,	5
abstract_inverted_index.exercises	160
abstract_inverted_index.implement	15
abstract_inverted_index.problems.	209
abstract_inverted_index.promising	141
abstract_inverted_index.providing	182
abstract_inverted_index.real-time	147
abstract_inverted_index.structure	62
abstract_inverted_index.students'	165
abstract_inverted_index.approaches	118
abstract_inverted_index.autograded	26
abstract_inverted_index.high-level	12, 79, 196
abstract_inverted_index.incorrect.	175
abstract_inverted_index.open-ended	3, 158
abstract_inverted_index.remarkable	111
abstract_inverted_index.submission	33
abstract_inverted_index.appropriate	19
abstract_inverted_index.autograders	156
abstract_inverted_index.correctness	29
abstract_inverted_index.iteratively	200
abstract_inverted_index.programming	4, 84
abstract_inverted_index.submissions	65
abstract_inverted_index.Furthermore,	176
abstract_inverted_index.code-writing	159
abstract_inverted_index.conventional	117
abstract_inverted_index.fine-tuning,	139
abstract_inverted_index.implications	142
abstract_inverted_index.incorporated	154
abstract_inverted_index.(GPT-4o-mini)	105, 130
abstract_inverted_index.outperforming	113
abstract_inverted_index.syntactically	174
abstract_inverted_index.cost-effective	128
abstract_inverted_index.state-of-the-art	136
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	4
citation_normalized_percentile