{"id":"https://openalex.org/W7139933176","doi":"https://doi.org/10.48550/arxiv.2603.18627","title":"Agentic Flow Steering and Parallel Rollout Search for Spatially Grounded Text-to-Image Generation","display_name":"Agentic Flow Steering and Parallel Rollout Search for Spatially Grounded Text-to-Image Generation","publication_year":2026,"publication_date":"2026-03-19","ids":{"openalex":"https://openalex.org/W7139933176","doi":"https://doi.org/10.48550/arxiv.2603.18627"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.18627","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.18627","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.2603.18627","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130239817","display_name":"Ping Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Ping","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130222855","display_name":"Daoxuan Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Daoxuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130252878","display_name":"Xiangming Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xiangming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052653569","display_name":"Y. Liu","orcid":"https://orcid.org/0000-0001-5968-3932"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yungeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130240628","display_name":"Haijin Zeng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeng, Haijin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130239496","display_name":"Yongyong Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Yongyong","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":0.8256999850273132,"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":0.8256999850273132,"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":0.13030000030994415,"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":0.0071000000461936,"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/trajectory","display_name":"Trajectory","score":0.7412999868392944},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.5690000057220459},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5383999943733215},{"id":"https://openalex.org/keywords/flow","display_name":"Flow (mathematics)","score":0.5098999738693237},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.49000000953674316},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.3603000044822693},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3553999960422516}],"concepts":[{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.7412999868392944},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6985999941825867},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.5690000057220459},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5383999943733215},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.5098999738693237},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.49000000953674316},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4212000072002411},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.3603000044822693},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3553999960422516},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3424000144004822},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.33000001311302185},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.32899999618530273},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.30709999799728394},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3041999936103821},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.29910001158714294},{"id":"https://openalex.org/C79487989","wikidata":"https://www.wikidata.org/wiki/Q934680","display_name":"Vehicle dynamics","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.2953000068664551},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.2896000146865845},{"id":"https://openalex.org/C51955184","wikidata":"https://www.wikidata.org/wiki/Q1545585","display_name":"Stochastic differential equation","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27070000767707825},{"id":"https://openalex.org/C91188154","wikidata":"https://www.wikidata.org/wiki/Q186247","display_name":"Vector field","level":2,"score":0.2508000135421753},{"id":"https://openalex.org/C51544822","wikidata":"https://www.wikidata.org/wiki/Q465274","display_name":"Ordinary differential equation","level":3,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.18627","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.18627","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.2603.18627","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.18627","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/16","display_name":"Peace, Justice and strong institutions","score":0.7598331570625305}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Precise":[0],"Text-to-Image":[1],"(T2I)":[2],"generation":[3,108,171],"has":[4],"achieved":[5],"great":[6],"success":[7],"but":[8],"is":[9],"hindered":[10],"by":[11],"the":[12,21,34,97,122,149,152],"limited":[13],"relational":[14],"reasoning":[15],"of":[16,151],"static":[17],"text":[18],"encoders":[19],"and":[20,57,76,94,120,136],"error":[22],"accumulation":[23],"in":[24],"open-loop":[25],"sampling.":[26],"Without":[27],"real-time":[28],"feedback,":[29],"initial":[30],"semantic":[31,88],"ambiguities":[32],"during":[33],"Ordinary":[35],"Differential":[36],"Equation":[37],"trajectory":[38],"inevitably":[39],"escalate":[40],"into":[41],"stochastic":[42],"deviations":[43],"from":[44],"spatial":[45,102],"constraints.":[46],"To":[47],"bridge":[48],"this":[49],"gap,":[50],"we":[51,105,130],"introduce":[52],"AFS-Search":[53,68],"(Agentic":[54],"Flow":[55],"Steering":[56],"Parallel":[58],"Rollout":[59],"Search),":[60],"a":[61,70,82,87,110],"training-free":[62,71],"closed-loop":[63,72],"framework":[64],"built":[65],"upon":[66],"FLUX.1-dev.":[67],"incorporates":[69],"parallel":[73],"rollout":[74],"search":[75],"flow":[77],"steering":[78],"mechanism,":[79],"which":[80],"leverages":[81],"Vision-Language":[83],"Model":[84],"(VLM)":[85],"as":[86,109],"critic":[89],"to":[90],"diagnose":[91],"intermediate":[92],"latents":[93],"dynamically":[95],"steer":[96],"velocity":[98],"field":[99],"via":[100],"precise":[101],"grounding.":[103],"Complementarily,":[104],"formulate":[106],"T2I":[107],"sequential":[111],"decision-making":[112],"process,":[113],"exploring":[114],"multiple":[115],"trajectories":[116],"through":[117],"lookahead":[118],"simulations":[119],"selecting":[121],"optimal":[123],"path":[124],"based":[125],"on":[126],"VLM-guided":[127],"rewards.":[128],"Further,":[129],"provide":[131],"AFS-Search-Pro":[132,146],"for":[133,138],"higher":[134],"performance":[135,150,167],"AFS-Search-Fast":[137,163],"quicker":[139],"generation.":[140],"Experimental":[141],"results":[142,157],"show":[143],"that":[144],"our":[145],"greatly":[147],"boosts":[148],"original":[153],"FLUX.1-dev,":[154],"achieving":[155],"state-of-the-art":[156],"across":[158],"three":[159],"different":[160],"benchmarks.":[161],"Meanwhile,":[162],"also":[164],"significantly":[165],"enhances":[166],"while":[168],"maintaining":[169],"fast":[170],"speed.":[172]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-21T00:00:00"}