{"id":"https://openalex.org/W7160432063","doi":"https://doi.org/10.48550/arxiv.2605.04036","title":"OpenSeeker-v2: Pushing the Limits of Search Agents with Informative and High-Difficulty Trajectories","display_name":"OpenSeeker-v2: Pushing the Limits of Search Agents with Informative and High-Difficulty Trajectories","publication_year":2026,"publication_date":"2026-05-05","ids":{"openalex":"https://openalex.org/W7160432063","doi":"https://doi.org/10.48550/arxiv.2605.04036"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2605.04036","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.04036","pdf_url":"https://arxiv.org/pdf/2605.04036","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2605.04036","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135451265","display_name":"Yuwen Du","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Du, Yuwen","raw_affiliation_strings":["Equal Core Contributions ,","Shanghai Jiao Tong University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Equal Core Contributions ,","institution_ids":[]},{"raw_affiliation_string":"Shanghai Jiao Tong University ,","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036249850","display_name":"Rui Ye","orcid":"https://orcid.org/0000-0002-6621-9000","observed_orcids":["https://orcid.org/0000-0002-6621-9000"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ye, Rui","raw_affiliation_strings":["Equal Core Contributions ,","Shanghai Jiao Tong University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Equal Core Contributions ,","institution_ids":[]},{"raw_affiliation_string":"Shanghai Jiao Tong University ,","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109690954","display_name":"Shuo Tang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tang, Shuo","raw_affiliation_strings":["Shanghai Jiao Tong University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University ,","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110728563","display_name":"K. Huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huang, Keduan","raw_affiliation_strings":["Shanghai Jiao Tong University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University ,","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159833701","display_name":"Xinyu Zhu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhu, Xinyu","raw_affiliation_strings":["Shanghai Jiao Tong University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University ,","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125578227","display_name":"Yuzhu Cai","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cai, Yuzhu","raw_affiliation_strings":["Shanghai Jiao Tong University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University ,","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135593960","display_name":"Siheng Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Siheng","raw_affiliation_strings":["Shanghai Jiao Tong University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University ,","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":9,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9110999703407288,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9110999703407288,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.06970000267028809,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.0035000001080334187,"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/search-agents","display_name":"search agents","score":0.8320000171661377},{"id":"https://openalex.org/keywords/llm-based-agents","display_name":"LLM agents","score":0.7990000247955322},{"id":"https://openalex.org/keywords/supervised-fine-tuning","display_name":"supervised fine-tuning","score":0.9350000023841858},{"id":"https://openalex.org/keywords/data-synthesis","display_name":"data synthesis","score":0.5540000200271606},{"id":"https://openalex.org/keywords/knowledge-graphs","display_name":"knowledge graphs","score":0.8169999718666077},{"id":"https://openalex.org/keywords/tool-use","display_name":"tool use","score":0.5889999866485596}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6704000234603882},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.6198999881744385},{"id":"https://openalex.org/C2778571376","wikidata":"https://www.wikidata.org/wiki/Q1355821","display_name":"Frontier","level":2,"score":0.5917999744415283},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5834000110626221},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5656999945640564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5651999711990356},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5250999927520752},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5228999853134155},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.47859999537467957},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3903000056743622},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3779999911785126},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.3095000088214874},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C2778671685","wikidata":"https://www.wikidata.org/wiki/Q219239","display_name":"Recipe","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2678999900817871},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.25699999928474426}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2605.04036","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.04036","pdf_url":"https://arxiv.org/pdf/2605.04036","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2605.04036","doi":"https://doi.org/10.48550/arxiv.2605.04036","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.04036","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2605.04036","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.04036","pdf_url":"https://arxiv.org/pdf/2605.04036","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7160432063.pdf","grobid_xml":"https://content.openalex.org/works/W7160432063.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W4406840771","https://openalex.org/W4415317994","https://openalex.org/W4417006854","https://openalex.org/W4417089504","https://openalex.org/W6929371760","https://openalex.org/W7102388436","https://openalex.org/W7102411227","https://openalex.org/W7119523234","https://openalex.org/W7129373530","https://openalex.org/W7138230811","https://openalex.org/W7139010259"],"related_works":["https://openalex.org/W7138230811","https://openalex.org/W7214557306","https://openalex.org/W4415194584","https://openalex.org/W7171646184","https://openalex.org/W7160533687","https://openalex.org/W4414597364","https://openalex.org/W7155108762","https://openalex.org/W7166860182","https://openalex.org/W7214898040","https://openalex.org/W7119918735"],"abstract_inverted_index":{"Deep":[0],"search":[1,68,158,196],"capabilities":[2],"have":[3],"become":[4],"an":[5],"indispensable":[6],"competency":[7],"for":[8,65,81,89],"frontier":[9,67,195],"Large":[10],"Language":[11],"Model":[12],"(LLM)":[13],"agents,":[14],"yet":[15,190],"their":[16],"development":[17],"remains":[18],"dominated":[19],"by":[20,169],"industrial":[21],"giants.":[22],"The":[23],"typical":[24],"industry":[25],"recipe":[26],"involves":[27],"a":[28,57,98,170],"highly":[29],"resource-intensive":[30],"pipeline":[31],"spanning":[32],"pre-training,":[33],"continual":[34],"pre-training":[35],"(CPT),":[36],"supervised":[37],"fine-tuning":[38],"(SFT),":[39],"and":[40,54,92,131,149,164,186],"reinforcement":[41],"learning":[42],"(RL).":[43],"In":[44],"this":[45],"report,":[46],"we":[47,96],"show":[48],"that":[49],"when":[50],"fueled":[51],"with":[52,117,140],"informative":[53],"high-difficulty":[55],"trajectories,":[56],"simple":[58,73,189],"SFT":[59],"approach":[60],"could":[61],"be":[62,167],"surprisingly":[63],"powerful":[64],"training":[66],"agents.":[69],"By":[70],"introducing":[71],"three":[72],"data":[74,105],"synthesis":[75],"modifications:":[76],"scaling":[77],"knowledge":[78],"graph":[79],"size":[80,88],"richer":[82],"exploration,":[83],"expanding":[84],"the":[85,155,182,202],"tool":[86],"set":[87],"broader":[90],"functionality,":[91],"strict":[93],"low-step":[94],"filtering,":[95],"establish":[97],"stronger":[99],"baseline.":[100],"Trained":[101],"on":[102,121,124,127,133],"merely":[103],"10.6k":[104],"points,":[106],"our":[107,188],"OpenSeeker-v2":[108,153,183],"achieves":[109,145],"state-of-the-art":[110,157],"performance":[111],"across":[112],"4":[113],"benchmarks":[114],"(30B-sized":[115],"agents":[116],"ReAct":[118],"paradigm):":[119],"46.0%":[120],"BrowseComp,":[122],"58.1%":[123],"BrowseComp-ZH,":[125],"34.6%":[126],"Humanity's":[128],"Last":[129],"Exam,":[130],"78.0%":[132],"xbench,":[134],"surpassing":[135],"even":[136],"Tongyi":[137],"DeepResearch":[138],"trained":[139],"heavy":[141],"CPT+SFT+RL":[142],"pipeline,":[143],"which":[144],"43.4%,":[146],"46.7%,":[147],"32.9%,":[148],"75.0%,":[150],"respectively.":[151],"Notably,":[152],"represents":[154],"first":[156],"agent":[159,197],"within":[160],"its":[161],"model":[162,184],"scale":[163],"paradigm":[165],"to":[166,180,193,201],"developed":[168],"purely":[171],"academic":[172],"team":[173],"using":[174],"only":[175],"SFT.":[176],"We":[177],"are":[178],"excited":[179],"open-source":[181],"weights":[185],"share":[187],"effective":[191],"findings":[192],"make":[194],"research":[198],"more":[199],"accessible":[200],"community.":[203]},"counts_by_year":[{"year":2026,"cited_by_count":9}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-05-07T00:00:00"}