{"id":"https://openalex.org/W7162579440","doi":"https://doi.org/10.48550/arxiv.2605.26520","title":"InterSketch: An Interleaved Reasoning Model with Self-correcting Visual Sketch and Stepwise Reward","display_name":"InterSketch: An Interleaved Reasoning Model with Self-correcting Visual Sketch and Stepwise Reward","publication_year":2026,"publication_date":"2026-05-26","ids":{"openalex":"https://openalex.org/W7162579440","doi":"https://doi.org/10.48550/arxiv.2605.26520"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.26520","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.26520","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.26520","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137135710","display_name":"Zhiwei Ning","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ning, Zhiwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137085162","display_name":"Wenwen Tong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tong, Wenwen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136018883","display_name":"Xiangli Kong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kong, Xiangli","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110652078","display_name":"Shengnan Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Shengnan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137088265","display_name":"Ziyi Shang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shang, Ziyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137151108","display_name":"Jingcheng Ni","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ni, Jingcheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137117802","display_name":"Tao Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Tao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137142787","display_name":"Yong Xien Chng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chng, Yong Xien","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117113485","display_name":"Jixuan Ying","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ying, Jixuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137159605","display_name":"Zehuan Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Zehuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137129088","display_name":"Hanming Deng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deng, Hanming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137177297","display_name":"Jie Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Jie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137173954","display_name":"Yuanjie Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Yuanjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137128938","display_name":"Wei Liu","orcid":"https://orcid.org/0009-0001-1052-7741"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137108237","display_name":"Lewei Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Lewei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":15,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9832000136375427,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9832000136375427,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0019000000320374966,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.0012000000569969416,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.8349999785423279},{"id":"https://openalex.org/keywords/sketch","display_name":"Sketch","score":0.6471999883651733},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.5839999914169312},{"id":"https://openalex.org/keywords/opportunistic-reasoning","display_name":"Opportunistic reasoning","score":0.5604000091552734},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5224999785423279},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.5074999928474426},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.48080000281333923},{"id":"https://openalex.org/keywords/reflection","display_name":"Reflection (computer programming)","score":0.47279998660087585},{"id":"https://openalex.org/keywords/reasoning-system","display_name":"Reasoning system","score":0.4465999901294708}],"concepts":[{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.8349999785423279},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7908999919891357},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.6471999883651733},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6266999840736389},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.5839999914169312},{"id":"https://openalex.org/C86827895","wikidata":"https://www.wikidata.org/wiki/Q7098582","display_name":"Opportunistic reasoning","level":4,"score":0.5604000091552734},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5224999785423279},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.5074999928474426},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.48080000281333923},{"id":"https://openalex.org/C65682993","wikidata":"https://www.wikidata.org/wiki/Q1056451","display_name":"Reflection (computer programming)","level":2,"score":0.47279998660087585},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.4465999901294708},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.42899999022483826},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.40450000762939453},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.37459999322891235},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.37059998512268066},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35370001196861267},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.34860000014305115},{"id":"https://openalex.org/C97364631","wikidata":"https://www.wikidata.org/wiki/Q484284","display_name":"Deductive reasoning","level":2,"score":0.3474000096321106},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3271999955177307},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.30079999566078186},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C166088908","wikidata":"https://www.wikidata.org/wiki/Q308495","display_name":"Abductive reasoning","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2904999852180481},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2703000009059906},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C43971567","wikidata":"https://www.wikidata.org/wiki/Q3142865","display_name":"Logical reasoning","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C2777055276","wikidata":"https://www.wikidata.org/wiki/Q7936580","display_name":"Visual approach","level":2,"score":0.25429999828338623},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.26520","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.26520","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.26520","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.26520","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"While":[0],"vision-language":[1],"models":[2,163],"(VLMs)":[3],"have":[4],"exhibited":[5],"multi-turn":[6,117],"visual":[7,28,70,89,152],"reasoning":[8,11,37,53,86,119,153],"capabilities,":[9],"their":[10,24],"trajectories":[12],"remain":[13],"relatively":[14],"shallow":[15],"and":[16,62,75,84,106,120],"are":[17],"dominated":[18],"by":[19],"a":[20,100,108,131],"text-centric":[21],"paradigm,":[22],"limiting":[23],"applicability":[25],"to":[26,55,111,135],"complex":[27],"challenges.":[29],"In":[30,122],"contrast,":[31],"human-like":[32],"thought":[33],"typically":[34],"involves":[35],"long-horizon":[36,88,147],"with":[38,78],"an":[39,51],"interleaved":[40,52,103,118],"visual-textual":[41],"chain-of-thought":[42],"(VT-CoT).":[43],"To":[44],"bridge":[45],"this":[46],"gap,":[47],"we":[48,98,129],"introduce":[49],"InterSketch,":[50,159],"model":[54],"enhance":[56],"the":[57,94,113,123,137,156],"VT-CoT":[58,104],"capability":[59,115],"via":[60],"self-correcting":[61],"stepwise":[63,132],"reward":[64,133,140],"mechanisms.":[65],"InterSketch":[66],"dynamically":[67],"generates":[68],"intermediate":[69],"sketches":[71],"using":[72],"external":[73],"tools":[74],"interleaves":[76],"them":[77],"textual":[79],"reasoning,":[80],"enabling":[81],"effective":[82],"perception":[83],"logical":[85],"over":[87,146],"understanding":[90],"tasks.":[91],"Specifically,":[92],"in":[93,116,143],"first":[95],"cold-start":[96],"stage,":[97,128],"propose":[99],"synthesized":[101],"high-quality":[102],"dataset":[105],"include":[107],"reflection":[109],"mechanism":[110,134],"enable":[112],"model's":[114],"self-correction.":[121],"subsequent":[124],"reinforcement":[125],"learning":[126],"(RL)":[127],"design":[130],"mitigate":[136],"sparsity":[138],"of":[139,158],"signals":[141],"inherent":[142],"end-only":[144],"supervision":[145],"reasoning.":[148],"Extensive":[149],"experiments":[150],"on":[151],"benchmarks":[154],"demonstrate":[155],"effectiveness":[157],"even":[160],"outperforming":[161],"proprietary":[162],"such":[164],"as":[165],"Gemini-3-Pro.":[166]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-28T00:00:00"}