MuSLR: Multimodal Symbolic Logical Reasoning Article Swipe
Jianyu Xu
,
Fei, Hao
,
Yuhui Zhang
,
Liangming Pan
,
Qijun Huang
,
Qian Liu
,
Preslav Nakov
,
Min‐Yen Kan
,
William Yang Wang
,
Mong Li Lee
,
Wynne Hsu
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2509.25851
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2509.25851
Multimodal symbolic logical reasoning, which aims to deduce new facts from multimodal input via formal logic, is critical in high-stakes applications such as autonomous driving and medical diagnosis, as its rigorous, deterministic reasoning helps prevent serious consequences. To evaluate such capabilities of current state-of-the-art vision language models (VLMs), we introduce the first benchmark MuSLR for multimodal symbolic logical reasoning grounded in formal logical rules. MuSLR comprises 1,093 instances across 7 domains, including 35 atomic symbolic logic and 976 logical combinations, with reasoning depths ranging from 2 to 9. We evaluate 7 state-of-the-art VLMs on MuSLR and find that they all struggle with multimodal symbolic reasoning, with the best model, GPT-4.1, achieving only 46.8%. Thus, we propose LogiCAM, a modular framework that applies formal logical rules to multimodal inputs, boosting GPT-4.1's Chain-of-Thought performance by 14.13%, and delivering even larger gains on complex logics such as first-order logic. We also conduct a comprehensive error analysis, showing that around 70% of failures stem from logical misalignment between modalities, offering key insights to guide future improvements. All data and code are publicly available at https://llm-symbol.github.io/MuSLR.
Related Topics
Concepts
No concepts available.
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2509.25851
- https://arxiv.org/pdf/2509.25851
- OA Status
- green
- OpenAlex ID
- https://openalex.org/W4415338263
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4415338263Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2509.25851Digital Object Identifier
- Title
-
MuSLR: Multimodal Symbolic Logical ReasoningWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-09-30Full publication date if available
- Authors
-
Jianyu Xu, Fei, Hao, Yuhui Zhang, Liangming Pan, Qijun Huang, Qian Liu, Preslav Nakov, Min‐Yen Kan, William Yang Wang, Mong Li Lee, Wynne HsuList of authors in order
- Landing page
-
https://arxiv.org/abs/2509.25851Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2509.25851Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2509.25851Direct OA link when available
- Cited by
-
0Total citation count in OpenAlex
Full payload
| id | https://openalex.org/W4415338263 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2509.25851 |
| ids.doi | https://doi.org/10.48550/arxiv.2509.25851 |
| ids.openalex | https://openalex.org/W4415338263 |
| fwci | |
| type | preprint |
| title | MuSLR: Multimodal Symbolic Logical Reasoning |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10181 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9991000294685364 |
| 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 | Natural Language Processing Techniques |
| topics[1].id | https://openalex.org/T10215 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9850000143051147 |
| 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 | Semantic Web and Ontologies |
| topics[2].id | https://openalex.org/T12031 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9732999801635742 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1702 |
| topics[2].subfield.display_name | Artificial Intelligence |
| topics[2].display_name | Speech and dialogue systems |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2509.25851 |
| 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 | cc-by-nc-nd |
| locations[0].pdf_url | https://arxiv.org/pdf/2509.25851 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | https://openalex.org/licenses/cc-by-nc-nd |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2509.25851 |
| locations[1].id | doi:10.48550/arxiv.2509.25851 |
| 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.2509.25851 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5101688362 |
| authorships[0].author.orcid | https://orcid.org/0009-0007-2821-7024 |
| authorships[0].author.display_name | Jianyu Xu |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Xu, Jundong |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | |
| authorships[1].author.orcid | https://orcid.org/0000-0003-3026-6347 |
| authorships[1].author.display_name | |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Fei, Hao |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5100624915 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-5158-0645 |
| authorships[2].author.display_name | Yuhui Zhang |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Zhang, Yuhui |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5011007223 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-4636-397X |
| authorships[3].author.display_name | Liangming Pan |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Pan, Liangming |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5055120491 |
| authorships[4].author.orcid | https://orcid.org/0000-0001-9679-5191 |
| authorships[4].author.display_name | Qijun Huang |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Huang, Qijun |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5100318611 |
| authorships[5].author.orcid | https://orcid.org/0000-0003-4658-6361 |
| authorships[5].author.display_name | Qian Liu |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Liu, Qian |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5012055259 |
| authorships[6].author.orcid | https://orcid.org/0000-0002-3600-1510 |
| authorships[6].author.display_name | Preslav Nakov |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Nakov, Preslav |
| authorships[6].is_corresponding | False |
| authorships[7].author.id | https://openalex.org/A5066305082 |
| authorships[7].author.orcid | https://orcid.org/0000-0001-8507-3716 |
| authorships[7].author.display_name | Min‐Yen Kan |
| authorships[7].author_position | middle |
| authorships[7].raw_author_name | Kan, Min-Yen |
| authorships[7].is_corresponding | False |
| authorships[8].author.id | https://openalex.org/A5079022009 |
| authorships[8].author.orcid | https://orcid.org/0000-0001-6938-0361 |
| authorships[8].author.display_name | William Yang Wang |
| authorships[8].author_position | middle |
| authorships[8].raw_author_name | Wang, William Yang |
| authorships[8].is_corresponding | False |
| authorships[9].author.id | https://openalex.org/A5019988958 |
| authorships[9].author.orcid | https://orcid.org/0000-0002-9636-388X |
| authorships[9].author.display_name | Mong Li Lee |
| authorships[9].author_position | middle |
| authorships[9].raw_author_name | Lee, Mong-Li |
| authorships[9].is_corresponding | False |
| authorships[10].author.id | https://openalex.org/A5023595339 |
| authorships[10].author.orcid | |
| authorships[10].author.display_name | Wynne Hsu |
| authorships[10].author_position | last |
| authorships[10].raw_author_name | Hsu, Wynne |
| authorships[10].is_corresponding | False |
| has_content.pdf | True |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2509.25851 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-19T00:00:00 |
| display_name | MuSLR: Multimodal Symbolic Logical Reasoning |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10181 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9991000294685364 |
| 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 | Natural Language Processing Techniques |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2509.25851 |
| 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 | cc-by-nc-nd |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2509.25851 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by-nc-nd |
| 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/2509.25851 |
| primary_location.id | pmh:oai:arXiv.org:2509.25851 |
| 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 | cc-by-nc-nd |
| primary_location.pdf_url | https://arxiv.org/pdf/2509.25851 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | https://openalex.org/licenses/cc-by-nc-nd |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2509.25851 |
| publication_date | 2025-09-30 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.2 | 85 |
| abstract_inverted_index.7 | 69, 90 |
| abstract_inverted_index.a | 117, 149 |
| abstract_inverted_index.35 | 72 |
| abstract_inverted_index.9. | 87 |
| abstract_inverted_index.To | 37 |
| abstract_inverted_index.We | 88, 146 |
| abstract_inverted_index.as | 22, 28, 143 |
| abstract_inverted_index.at | 179 |
| abstract_inverted_index.by | 132 |
| abstract_inverted_index.in | 18, 60 |
| abstract_inverted_index.is | 16 |
| abstract_inverted_index.of | 41, 157 |
| abstract_inverted_index.on | 93, 139 |
| abstract_inverted_index.to | 6, 86, 125, 168 |
| abstract_inverted_index.we | 48, 114 |
| abstract_inverted_index.70% | 156 |
| abstract_inverted_index.976 | 77 |
| abstract_inverted_index.All | 172 |
| abstract_inverted_index.all | 99 |
| abstract_inverted_index.and | 25, 76, 95, 134, 174 |
| abstract_inverted_index.are | 176 |
| abstract_inverted_index.for | 54 |
| abstract_inverted_index.its | 29 |
| abstract_inverted_index.key | 166 |
| abstract_inverted_index.new | 8 |
| abstract_inverted_index.the | 50, 106 |
| abstract_inverted_index.via | 13 |
| abstract_inverted_index.VLMs | 92 |
| abstract_inverted_index.aims | 5 |
| abstract_inverted_index.also | 147 |
| abstract_inverted_index.best | 107 |
| abstract_inverted_index.code | 175 |
| abstract_inverted_index.data | 173 |
| abstract_inverted_index.even | 136 |
| abstract_inverted_index.find | 96 |
| abstract_inverted_index.from | 10, 84, 160 |
| abstract_inverted_index.only | 111 |
| abstract_inverted_index.stem | 159 |
| abstract_inverted_index.such | 21, 39, 142 |
| abstract_inverted_index.that | 97, 120, 154 |
| abstract_inverted_index.they | 98 |
| abstract_inverted_index.with | 80, 101, 105 |
| abstract_inverted_index.1,093 | 66 |
| abstract_inverted_index.MuSLR | 53, 64, 94 |
| abstract_inverted_index.Thus, | 113 |
| abstract_inverted_index.error | 151 |
| abstract_inverted_index.facts | 9 |
| abstract_inverted_index.first | 51 |
| abstract_inverted_index.gains | 138 |
| abstract_inverted_index.guide | 169 |
| abstract_inverted_index.helps | 33 |
| abstract_inverted_index.input | 12 |
| abstract_inverted_index.logic | 75 |
| abstract_inverted_index.rules | 124 |
| abstract_inverted_index.which | 4 |
| abstract_inverted_index.46.8%. | 112 |
| abstract_inverted_index.across | 68 |
| abstract_inverted_index.around | 155 |
| abstract_inverted_index.atomic | 73 |
| abstract_inverted_index.deduce | 7 |
| abstract_inverted_index.depths | 82 |
| abstract_inverted_index.formal | 14, 61, 122 |
| abstract_inverted_index.future | 170 |
| abstract_inverted_index.larger | 137 |
| abstract_inverted_index.logic, | 15 |
| abstract_inverted_index.logic. | 145 |
| abstract_inverted_index.logics | 141 |
| abstract_inverted_index.model, | 108 |
| abstract_inverted_index.models | 46 |
| abstract_inverted_index.rules. | 63 |
| abstract_inverted_index.vision | 44 |
| abstract_inverted_index.(VLMs), | 47 |
| abstract_inverted_index.14.13%, | 133 |
| abstract_inverted_index.applies | 121 |
| abstract_inverted_index.between | 163 |
| abstract_inverted_index.complex | 140 |
| abstract_inverted_index.conduct | 148 |
| abstract_inverted_index.current | 42 |
| abstract_inverted_index.driving | 24 |
| abstract_inverted_index.inputs, | 127 |
| abstract_inverted_index.logical | 2, 57, 62, 78, 123, 161 |
| abstract_inverted_index.medical | 26 |
| abstract_inverted_index.modular | 118 |
| abstract_inverted_index.prevent | 34 |
| abstract_inverted_index.propose | 115 |
| abstract_inverted_index.ranging | 83 |
| abstract_inverted_index.serious | 35 |
| abstract_inverted_index.showing | 153 |
| abstract_inverted_index.GPT-4.1, | 109 |
| abstract_inverted_index.LogiCAM, | 116 |
| abstract_inverted_index.boosting | 128 |
| abstract_inverted_index.critical | 17 |
| abstract_inverted_index.domains, | 70 |
| abstract_inverted_index.evaluate | 38, 89 |
| abstract_inverted_index.failures | 158 |
| abstract_inverted_index.grounded | 59 |
| abstract_inverted_index.insights | 167 |
| abstract_inverted_index.language | 45 |
| abstract_inverted_index.offering | 165 |
| abstract_inverted_index.publicly | 177 |
| abstract_inverted_index.struggle | 100 |
| abstract_inverted_index.symbolic | 1, 56, 74, 103 |
| abstract_inverted_index.GPT-4.1's | 129 |
| abstract_inverted_index.achieving | 110 |
| abstract_inverted_index.analysis, | 152 |
| abstract_inverted_index.available | 178 |
| abstract_inverted_index.benchmark | 52 |
| abstract_inverted_index.comprises | 65 |
| abstract_inverted_index.framework | 119 |
| abstract_inverted_index.including | 71 |
| abstract_inverted_index.instances | 67 |
| abstract_inverted_index.introduce | 49 |
| abstract_inverted_index.reasoning | 32, 58, 81 |
| abstract_inverted_index.rigorous, | 30 |
| abstract_inverted_index.Multimodal | 0 |
| abstract_inverted_index.autonomous | 23 |
| abstract_inverted_index.delivering | 135 |
| abstract_inverted_index.diagnosis, | 27 |
| abstract_inverted_index.multimodal | 11, 55, 102, 126 |
| abstract_inverted_index.reasoning, | 3, 104 |
| abstract_inverted_index.first-order | 144 |
| abstract_inverted_index.high-stakes | 19 |
| abstract_inverted_index.modalities, | 164 |
| abstract_inverted_index.performance | 131 |
| abstract_inverted_index.applications | 20 |
| abstract_inverted_index.capabilities | 40 |
| abstract_inverted_index.misalignment | 162 |
| abstract_inverted_index.combinations, | 79 |
| abstract_inverted_index.comprehensive | 150 |
| abstract_inverted_index.consequences. | 36 |
| abstract_inverted_index.deterministic | 31 |
| abstract_inverted_index.improvements. | 171 |
| abstract_inverted_index.Chain-of-Thought | 130 |
| abstract_inverted_index.state-of-the-art | 43, 91 |
| abstract_inverted_index.https://llm-symbol.github.io/MuSLR. | 180 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 11 |
| citation_normalized_percentile |