{"id":"https://openalex.org/W7163190624","doi":"https://doi.org/10.48550/arxiv.2606.00579","title":"Sandboxed Coding Agents are Competitive Omni-modal Task Solvers","display_name":"Sandboxed Coding Agents are Competitive Omni-modal Task Solvers","publication_year":2026,"publication_date":"2026-05-30","ids":{"openalex":"https://openalex.org/W7163190624","doi":"https://doi.org/10.48550/arxiv.2606.00579"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.00579","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.00579","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.00579","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137707814","display_name":"Dongping Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Dongping","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137649466","display_name":"Xuanao Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Xuanao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124958028","display_name":"Zhihan Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Zhihan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129543738","display_name":"Qingyuan Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Qingyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077530975","display_name":"Dianqi Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Dianqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137680462","display_name":"Tianyi Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Tianyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.8966000080108643,"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":0.8966000080108643,"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":0.032999999821186066,"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/T10028","display_name":"Topic Modeling","score":0.011300000362098217,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/coding","display_name":"Coding (social sciences)","score":0.5952000021934509},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5112000107765198},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5011000037193298},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4424999952316284},{"id":"https://openalex.org/keywords/trace","display_name":"TRACE (psycholinguistics)","score":0.43799999356269836},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.3587000072002411},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.3569999933242798}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8284000158309937},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5952000021934509},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5112000107765198},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5011000037193298},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4659000039100647},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4424999952316284},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.43799999356269836},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40540000796318054},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3587000072002411},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3569999933242798},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34950000047683716},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.34599998593330383},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.322299987077713},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.3208000063896179},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.2915000021457672},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2581000030040741},{"id":"https://openalex.org/C2778571376","wikidata":"https://www.wikidata.org/wiki/Q1355821","display_name":"Frontier","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.00579","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.00579","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.00579","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.00579","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8150075078010559,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"As":[0],"multimodal":[1,52],"LLMs":[2],"increasingly":[3],"target":[4],"video":[5],"and":[6,34,41,50,70,80,90,108,112,120,141,144,149,161],"audio,":[7],"it":[8],"is":[9,23,158],"often":[10],"assumed":[11],"that":[12,21,63,114,154],"such":[13],"tasks":[14,87],"require":[15],"native":[16,47],"omnimodal":[17,48,86,169],"models.":[18],"We":[19,99],"show":[20,113],"this":[22],"not":[24],"always":[25],"the":[26,137,155],"case:":[27],"coding":[28],"agents":[29],"with":[30,136],"only":[31],"text+image":[32],"access":[33],"a":[35,105,133,164],"sandboxed":[36],"tool-use":[37],"interface":[38],"can":[39],"match,":[40],"in":[42],"several":[43],"settings":[44],"outperform,":[45],"SOTA":[46],"models":[49],"predefined":[51],"agent":[53],"scaffolds":[54],"across":[55],"multiple":[56],"audio-video":[57],"benchmarks.":[58],"Our":[59],"trajectory":[60,139],"analysis":[61],"suggests":[62],"their":[64,102],"strength":[65],"comes":[66],"from":[67,77],"writing":[68],"code":[69],"orchestrating":[71],"tools":[72],"to":[73],"extract":[74],"relevant":[75],"evidence":[76],"transcripts,":[78],"frames,":[79],"other":[81],"modality":[82],"signals,":[83],"thereby":[84],"converting":[85],"into":[88],"retrieval":[89],"information-processing":[91],"problems":[92],"rather":[93],"than":[94],"ingesting":[95],"entire":[96],"media":[97],"streams.":[98],"further":[100],"characterize":[101],"limitations":[103],"through":[104],"failure":[106],"taxonomy":[107],"process-level":[109,165],"trace":[110],"analysis,":[111],"simple":[115],"skill":[116],"injection,":[117],"including":[118],"human-written":[119],"self-distilled":[121],"skills,":[122],"substantially":[123],"improves":[124],"performance.":[125],"To":[126],"explore":[127],"open-source":[128],"elicitation,":[129],"we":[130,152],"introduce":[131,162],"Code-X,":[132],"training":[134],"recipe":[135],"OmniCoding":[138],"dataset":[140],"verifiable":[142],"reward,":[143],"provide":[145],"baselines":[146],"on":[147],"Qwen-3.5-9B":[148],"Qwen-3.6-27B.":[150],"Finally,":[151],"argue":[153],"next":[156],"frontier":[157],"many-modality":[159],"processing,":[160],"TerminalBench-O,":[163],"benchmark":[166],"for":[167],"real-world":[168],"processing":[170],"tasks.":[171],"Code":[172],"will":[173],"be":[174],"available":[175],"at":[176],"https://github.com/Dongping-Chen/OmniCoding.":[177]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-03T00:00:00"}