{"id":"https://openalex.org/W7162804409","doi":"https://doi.org/10.48550/arxiv.2605.29893","title":"Redundant or Necessary? A Benchmark for Detecting Redundant Steps in Agent Trajectories","display_name":"Redundant or Necessary? A Benchmark for Detecting Redundant Steps in Agent Trajectories","publication_year":2026,"publication_date":"2026-05-28","ids":{"openalex":"https://openalex.org/W7162804409","doi":"https://doi.org/10.48550/arxiv.2605.29893"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.29893","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.29893","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.29893","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018490499","display_name":"Minyang Hu","orcid":"https://orcid.org/0009-0009-2560-6360"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Minyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137386963","display_name":"Bo Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Bo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007413026","display_name":"Zhinuo Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Zhinuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137358918","display_name":"Jiachen Liang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang, Jiachen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137313804","display_name":"Guo Jiahao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiahao, Guo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137368501","display_name":"Yiyang Yin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yin, Yiyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137339824","display_name":"Xiongwei Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han, Xiongwei","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":0.3028999865055084,"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":0.3028999865055084,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.06549999862909317,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10906","display_name":"AI-based Problem Solving and Planning","score":0.05939999967813492,"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/benchmark","display_name":"Benchmark (surveying)","score":0.7944999933242798},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6966999769210815},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5504999756813049},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.44690001010894775},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4408999979496002}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7944999933242798},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7703999876976013},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6966999769210815},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5504999756813049},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5027999877929688},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5016000270843506},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.44690001010894775},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4408999979496002},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.4368000030517578},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3598000109195709},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.34869998693466187},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3172000050544739}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.29893","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.29893","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.29893","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.29893","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":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"LLM-based":[0],"agents":[1],"have":[2],"demonstrated":[3],"strong":[4],"capabilities":[5],"in":[6,131,155,161,167],"solving":[7],"complex":[8],"tasks":[9,82],"through":[10],"multi-step":[11],"reasoning":[12],"and":[13,57,103,149,159],"tool":[14],"use.":[15],"However,":[16],"existing":[17],"evaluation":[18],"protocols":[19],"primarily":[20],"focus":[21],"on":[22],"task":[23,50,97],"success,":[24],"overlooking":[25],"a":[26,59,76,111],"critical":[27],"aspect":[28],"of":[29],"agent":[30,36,67],"behavior:":[31],"execution":[32],"efficiency.":[33],"In":[34,52],"practice,":[35],"trajectories":[37],"often":[38],"contain":[39],"redundant":[40,116,133],"steps":[41],"that":[42,79,122],"consume":[43],"substantial":[44],"resources":[45],"while":[46,135],"contributing":[47],"little":[48],"to":[49,93,96,108],"completion.":[51,98],"this":[53,71,156,162],"work,":[54],"we":[55,73,101],"propose":[56],"formulate":[58],"new":[60,77],"research":[61,154],"area:":[62],"\\textbf{redundant":[63],"step":[64,89,112],"detection}":[65],"for":[66,152],"trajectories.":[68],"To":[69],"support":[70],"initiative,":[72],"introduce":[74],"\\textbf{RedundancyBench},":[75],"benchmark":[78],"contains":[80],"diverse":[81],"with":[83],"carefully":[84],"annotated":[85],"trajectories,":[86],"where":[87],"each":[88],"is":[90,115],"labeled":[91],"according":[92],"its":[94],"contribution":[95],"Using":[99],"RedundancyBench,":[100],"develop":[102],"evaluate":[104],"3":[105],"representative":[106],"methods":[107,137],"answer":[109],"whether":[110],"within":[113],"trajectory":[114],"or":[117],"necessary.":[118],"Our":[119],"results":[120,144],"show":[121],"even":[123],"the":[124,146,150],"best-performing":[125],"method":[126],"achieves":[127],"only":[128],"24.88\\%":[129],"score":[130],"detecting":[132],"steps,":[134],"some":[136],"perform":[138],"worse":[139],"than":[140],"random":[141],"guessing.":[142],"These":[143],"highlight":[145],"task's":[147],"complexity":[148],"need":[151],"further":[153],"area.":[157],"\\footnote{Code":[158],"dataset":[160],"paper":[163],"are":[164],"both":[165],"available":[166],"\\href{https://anonymous.4open.science/r/RedundancyBench}{https://anonymous.4open.science/r/RedundancyBench}.}":[168]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-30T00:00:00"}