{"id":"https://openalex.org/W7166849861","doi":"https://doi.org/10.18653/v1/2026.acl-long.609","title":"Beyond Single-shot Writing: Deep Research Agents are Unreliable at Multi-turn Report Revision","display_name":"Beyond Single-shot Writing: Deep Research Agents are Unreliable at Multi-turn Report Revision","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166849861","doi":"https://doi.org/10.18653/v1/2026.acl-long.609"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.609","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.609","pdf_url":"https://aclanthology.org/2026.acl-long.609.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.609.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139733028","display_name":"Bingsen Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bingsen Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139786107","display_name":"Boyan Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boyan Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139826183","display_name":"Ping Nie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ping Nie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139792488","display_name":"Yuyu Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuyu Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139796498","display_name":"Xi Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xi Ye","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139755431","display_name":"\u8d75\u6668 Chen Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen Zhao","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.83939781,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13325","last_page":"13356"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.13459999859333038,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.13459999859333038,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.06620000302791595,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.05050000175833702,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.25619998574256897},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2529999911785126},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.23899999260902405},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.2337999939918518},{"id":"https://openalex.org/keywords/government","display_name":"Government (linguistics)","score":0.2304999977350235}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.41100001335144043},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30630001425743103},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2529999911785126},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.23899999260902405},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2337999939918518},{"id":"https://openalex.org/C2778137410","wikidata":"https://www.wikidata.org/wiki/Q2732820","display_name":"Government (linguistics)","level":2,"score":0.2304999977350235},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2298000007867813},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.22750000655651093},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.225600004196167}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.609","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.609","pdf_url":"https://aclanthology.org/2026.acl-long.609.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.609","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.609","pdf_url":"https://aclanthology.org/2026.acl-long.609.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5894559621810913}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166849861.pdf","grobid_xml":"https://content.openalex.org/works/W7166849861.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Existing":[0],"benchmarks":[1],"for":[2,58,82,158],"Deep":[3,177],"Research":[4,178],"Agents":[5,179],"(DRAs)":[6,180],"treat":[7],"report":[8,51,67],"generation":[9],"as":[10,53,122,151],"a":[11,54,64,77,91,155],"single-shot":[12],"writing":[13],"task,":[14],"which":[15],"fundamentally":[16],"diverges":[17],"from":[18],"how":[19],"human":[20],"researchers":[21],"iteratively":[22],"draft":[23],"and":[24,73,75,109,132,154,197,213],"revise":[25,35],"reports":[26,36,209],"via":[27],"self-reflection":[28],"or":[29],"peer":[30],"feedback.Whether":[31],"DRAs":[32,89],"can":[33,96],"reliably":[34],"with":[37,210],"user":[38,99],"feedback":[39,79],"remains":[40,224],"unexplored.We":[41],"introduce":[42],"MR":[43],"DRE,":[44],"an":[45,225],"evaluation":[46,56,68],"suite":[47],"that":[48,140],"establishes":[49],"multi-turn":[50,83],"revision":[52,113,159],"new":[55],"axis":[57],"DRAs.MR":[59],"DRE":[60],"consists":[61],"of":[62,86,105,168,176,205],"(1)":[63],"unified":[65],"long-form":[66,208],"protocol":[69],"spanning":[70],"comprehensiveness,":[71],"factuality,":[72],"presentation,":[74],"(2)":[76],"human-verified":[78],"simulation":[80],"pipeline":[81],"revision.Our":[84],"analysis":[85],"five":[87],"diverse":[88],"reveals":[90],"critical":[92],"limitation:":[93],"while":[94],"agents":[95],"address":[97],"most":[98],"feedback,":[100],"they":[101,123],"regress":[102],"on":[103],"16-27%":[104],"previously":[106],"covered":[107],"content":[108,127],"citation":[110],"quality.Over":[111],"multiple":[112],"turns,":[114],"even":[115],"the":[116,129,165,174,199],"best-performing":[117],"agent":[118],"leaves":[119],"significant":[120],"headroom,":[121],"continue":[124],"to":[125,134,173,218],"disrupt":[126],"outside":[128],"feedback's":[130],"scope":[131],"fail":[133],"preserve":[135],"earlier":[136],"edits.We":[137],"also":[138],"show":[139],"these":[141,220],"issues":[142],"are":[143],"not":[144],"easily":[145],"resolvable":[146],"through":[147],"inference-time":[148],"fixes":[149],"such":[150],"prompt":[152],"engineering":[153],"dedicated":[156],"sub-agent":[157],"1":[160],".":[161],"IntroductionRecent":[162],"advances":[163],"in":[164],"agentic":[166],"capabilities":[167],"language":[169],"models":[170],"have":[171],"led":[172],"rise":[175],"(OpenAI,":[181],"2025;":[182,185],"Perplexity,":[183],"2025;Tongyi,":[184],"Shao":[186],"et":[187],"al.,":[188],"2025).DRAs":[189],"tackle":[190],"complex":[191,221],"research":[192],"queries":[193],"by":[194],"extensively":[195],"searching":[196],"browsing":[198],"web,":[200],"then":[201],"synthesizing":[202],"large":[203],"volumes":[204],"information":[206],"into":[207],"rich":[211],"citations":[212],"well-organized":[214],"structure.However,":[215],"what":[216],"dimensions":[217],"evaluate":[219],"systems":[222],"against":[223],"open":[226],"prob-*":[227],"Equal":[228],"contribution.":[229]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}