{"id":"https://openalex.org/W7157066314","doi":"https://doi.org/10.48550/arxiv.2604.24443","title":"PhysNote: Self-Knowledge Notes for Evolvable Physical Reasoning in Vision-Language Model","display_name":"PhysNote: Self-Knowledge Notes for Evolvable Physical Reasoning in Vision-Language Model","publication_year":2026,"publication_date":"2026-04-27","ids":{"openalex":"https://openalex.org/W7157066314","doi":"https://doi.org/10.48550/arxiv.2604.24443"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.24443","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.24443","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.2604.24443","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134758364","display_name":"Sinin Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhang, Sinin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134796967","display_name":"Yunfei Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Yunfei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134785978","display_name":"Yuxuan Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Yuxuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134750068","display_name":"Haoyu Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Haoyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134761748","display_name":"Tong Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Tong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5134758364"],"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":0.9729999899864197,"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":0.9729999899864197,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.003800000064074993,"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"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0026000000070780516,"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/perception","display_name":"Perception","score":0.6097000241279602},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.5763999819755554},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5426999926567078},{"id":"https://openalex.org/keywords/causal-reasoning","display_name":"Causal reasoning","score":0.49950000643730164},{"id":"https://openalex.org/keywords/physical-system","display_name":"Physical system","score":0.48809999227523804},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.44130000472068787},{"id":"https://openalex.org/keywords/qualitative-reasoning","display_name":"Qualitative reasoning","score":0.40369999408721924},{"id":"https://openalex.org/keywords/causal-model","display_name":"Causal model","score":0.38830000162124634}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6323999762535095},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6097000241279602},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.5763999819755554},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5426999926567078},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49959999322891235},{"id":"https://openalex.org/C115086926","wikidata":"https://www.wikidata.org/wiki/Q17004651","display_name":"Causal reasoning","level":3,"score":0.49950000643730164},{"id":"https://openalex.org/C116672817","wikidata":"https://www.wikidata.org/wiki/Q1454986","display_name":"Physical system","level":2,"score":0.48809999227523804},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.44130000472068787},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.40369999408721924},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.4000999927520752},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.38830000162124634},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.33320000767707825},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.3321000039577484},{"id":"https://openalex.org/C103057564","wikidata":"https://www.wikidata.org/wiki/Q4751139","display_name":"Analytic reasoning","level":3,"score":0.33180001378059387},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3091999888420105},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.3043000102043152},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C163504300","wikidata":"https://www.wikidata.org/wiki/Q2364925","display_name":"Causal structure","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.290800005197525},{"id":"https://openalex.org/C97364631","wikidata":"https://www.wikidata.org/wiki/Q484284","display_name":"Deductive reasoning","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.24443","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.24443","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.2604.24443","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.24443","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":{"Vision-Language":[0],"Models":[1],"(VLMs)":[2],"have":[3],"demonstrated":[4],"strong":[5],"performance":[6],"on":[7,132],"textbook-style":[8],"physics":[9],"problems,":[10],"yet":[11],"they":[12],"frequently":[13],"fail":[14],"when":[15],"confronted":[16],"with":[17,149],"dynamic":[18,102],"real-world":[19],"scenarios":[20],"that":[21,87,121,135],"require":[22],"temporal":[23],"consistency":[24],"and":[25,51,55,92,115],"causal":[26,53],"reasoning":[27,69,119,156],"across":[28,48,152],"frames.":[29],"We":[30],"identify":[31],"two":[32],"fundamental":[33],"challenges":[34],"underlying":[35],"these":[36,79],"failures:":[37],"(1)":[38],"spatio-temporal":[39,105],"identity":[40,47],"drift,":[41],"where":[42,61],"objects":[43],"lose":[44],"their":[45],"physical":[46,68,94,155],"successive":[49],"frames":[50],"break":[52],"chains,":[54],"(2)":[56],"volatility":[57],"of":[58],"inference-time":[59],"insights,":[60],"a":[62,111,141],"model":[63],"may":[64],"occasionally":[65],"produce":[66],"correct":[67],"but":[70],"never":[71],"consolidates":[72],"it":[73],"for":[74],"future":[75],"reuse.":[76],"To":[77],"address":[78],"challenges,":[80],"we":[81],"propose":[82],"PhysNote,":[83],"an":[84,117],"agentic":[85],"framework":[86],"enables":[88],"VLMs":[89],"to":[90],"externalize":[91],"refine":[93],"knowledge":[95,113],"through":[96,104],"self-generated":[97,108],"\"Knowledge":[98],"Notes.\"":[99],"PhysNote":[100,136],"stabilizes":[101],"perception":[103],"canonicalization,":[106],"organizes":[107],"insights":[109],"into":[110],"hierarchical":[112],"repository,":[114],"drives":[116],"iterative":[118],"loop":[120],"grounds":[122],"hypotheses":[123],"in":[124],"visual":[125],"evidence":[126],"before":[127],"consolidating":[128],"verified":[129],"knowledge.":[130],"Experiments":[131],"PhysBench":[133],"demonstrate":[134],"achieves":[137],"56.68%":[138],"overall":[139],"accuracy,":[140],"4.96%":[142],"improvement":[143],"over":[144],"the":[145],"best":[146],"multi-agent":[147],"baseline,":[148],"consistent":[150],"gains":[151],"all":[153],"four":[154],"domains.":[157]},"counts_by_year":[],"updated_date":"2026-04-29T06:16:36.941037","created_date":"2026-04-29T00:00:00"}