{"id":"https://openalex.org/W7213284899","doi":"https://doi.org/10.48550/arxiv.2609.14992","title":"MTAC-IFBench: Benchmarking Instruction-Following in Multi-Turn Agentic Coding","display_name":"MTAC-IFBench: Benchmarking Instruction-Following in Multi-Turn Agentic Coding","publication_year":2026,"publication_date":"2026-09-14","ids":{"openalex":"https://openalex.org/W7213284899","doi":"https://doi.org/10.48550/arxiv.2609.14992"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.14992","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.14992","pdf_url":"https://arxiv.org/pdf/2609.14992","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/2609.14992","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091647182","display_name":"Bosi Wen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen, Bosi","raw_affiliation_strings":["The Conversational Artificial Intelligence (CoAI) Group , Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Conversational Artificial Intelligence (CoAI) Group , Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127966976","display_name":"Cunxiang Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4401726915","display_name":"Zhipu AI (China)","ror":"https://ror.org/005dzvw93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Cunxiang","raw_affiliation_strings":["Zhipu AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhipu AI","institution_ids":["https://openalex.org/I4401726915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049173771","display_name":"Jiayi Gui","orcid":"https://orcid.org/0000-0003-2371-4690","observed_orcids":["https://orcid.org/0000-0003-2371-4690"]},"institutions":[{"id":"https://openalex.org/I4401726915","display_name":"Zhipu AI (China)","ror":"https://ror.org/005dzvw93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gui, Jiayi","raw_affiliation_strings":["Zhipu AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhipu AI","institution_ids":["https://openalex.org/I4401726915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127945838","display_name":"Haoke Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4401726915","display_name":"Zhipu AI (China)","ror":"https://ror.org/005dzvw93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Haoke","raw_affiliation_strings":["Zhipu AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhipu AI","institution_ids":["https://openalex.org/I4401726915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109718198","display_name":"Yilin Niu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4401726915","display_name":"Zhipu AI (China)","ror":"https://ror.org/005dzvw93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Niu, Yilin","raw_affiliation_strings":["Zhipu AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhipu AI","institution_ids":["https://openalex.org/I4401726915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091491018","display_name":"Pei Ke","orcid":"https://orcid.org/0000-0001-7554-5636","observed_orcids":["https://orcid.org/0000-0001-7554-5636"]},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke, Pei","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128032932","display_name":"Dayong Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4401726915","display_name":"Zhipu AI (China)","ror":"https://ror.org/005dzvw93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang, Dayong","raw_affiliation_strings":["Zhipu AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhipu AI","institution_ids":["https://openalex.org/I4401726915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085094109","display_name":"Hongning Wang","orcid":"https://orcid.org/0000-0002-6524-9195","observed_orcids":["https://orcid.org/0000-0002-6524-9195"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Hongning","raw_affiliation_strings":["The Conversational Artificial Intelligence (CoAI) Group , Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Conversational Artificial Intelligence (CoAI) Group , Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5128003039","display_name":"Minlie Huang","orcid":"https://orcid.org/0000-0001-7111-1849","observed_orcids":["https://orcid.org/0000-0001-7111-1849"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huang, Minlie","raw_affiliation_strings":["The Conversational Artificial Intelligence (CoAI) Group , Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Conversational Artificial Intelligence (CoAI) Group , Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T10260","display_name":"Software Engineering Research","score":0.9854000210762024,"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/T10260","display_name":"Software Engineering Research","score":0.9854000210762024,"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/T10430","display_name":"Software Engineering Techniques and Practices","score":0.004800000227987766,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.0019000000320374966,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/instruction-following","display_name":"instruction following","score":0.628000020980835},{"id":"https://openalex.org/keywords/ai-coding-agents","display_name":"coding agents","score":0.6800000071525574},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8519999980926514},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.6290000081062317},{"id":"https://openalex.org/keywords/llm-evaluation","display_name":"LLM evaluation","score":0.35499998927116394}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7915999889373779},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.6924999952316284},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.5199000239372253},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.4950000047683716},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4837000072002411},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4693000018596649},{"id":"https://openalex.org/C2779182362","wikidata":"https://www.wikidata.org/wiki/Q17126187","display_name":"Session (web analytics)","level":2,"score":0.45159998536109924},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.4481000006198883},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.4027999937534332},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3847000002861023},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.37560001015663147},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.36719998717308044},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.35740000009536743},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.35530000925064087},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3407999873161316},{"id":"https://openalex.org/C75606506","wikidata":"https://www.wikidata.org/wiki/Q1049183","display_name":"Formal methods","level":2,"score":0.32330000400543213},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.320499986410141},{"id":"https://openalex.org/C180152950","wikidata":"https://www.wikidata.org/wiki/Q2904257","display_name":"Software development process","level":4,"score":0.3165999948978424},{"id":"https://openalex.org/C111498074","wikidata":"https://www.wikidata.org/wiki/Q173326","display_name":"Formal verification","level":2,"score":0.29989999532699585},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.2897999882698059},{"id":"https://openalex.org/C146499914","wikidata":"https://www.wikidata.org/wiki/Q5469969","display_name":"Formal semantics (linguistics)","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.2842999994754791},{"id":"https://openalex.org/C1009929","wikidata":"https://www.wikidata.org/wiki/Q179550","display_name":"Software bug","level":3,"score":0.2824999988079071},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.25519999861717224},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.2533999979496002},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2522999942302704}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.14992","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.14992","pdf_url":"https://arxiv.org/pdf/2609.14992","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.2609.14992","doi":"https://doi.org/10.48550/arxiv.2609.14992","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.14992","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:2609.14992","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.14992","pdf_url":"https://arxiv.org/pdf/2609.14992","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/W7213284899.pdf","grobid_xml":"https://content.openalex.org/works/W7213284899.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W3177813494","https://openalex.org/W3195140297","https://openalex.org/W3213368902","https://openalex.org/W4385774833","https://openalex.org/W4385902209","https://openalex.org/W4388718089","https://openalex.org/W4390041933","https://openalex.org/W4406033167","https://openalex.org/W4414586252","https://openalex.org/W4415252687","https://openalex.org/W4416434653","https://openalex.org/W4416453502","https://openalex.org/W4416716405","https://openalex.org/W6947963647","https://openalex.org/W7081912778","https://openalex.org/W7119636773","https://openalex.org/W7125193990","https://openalex.org/W7126078156","https://openalex.org/W7128715130","https://openalex.org/W7130402983","https://openalex.org/W7137905904","https://openalex.org/W7166639075","https://openalex.org/W7166724480","https://openalex.org/W7166853245"],"related_works":["https://openalex.org/W7124450990","https://openalex.org/W4416716405","https://openalex.org/W4416887898","https://openalex.org/W4416453502","https://openalex.org/W7165399465","https://openalex.org/W4417209600","https://openalex.org/W4417257651","https://openalex.org/W7223241732","https://openalex.org/W7162397884","https://openalex.org/W4415926832"],"abstract_inverted_index":{"Recently,":[0],"the":[1,44,128,170],"rapid":[2],"development":[3,45,95],"of":[4,110],"large":[5],"language":[6],"models":[7],"(LLMs)":[8],"has":[9],"reshaped":[10],"software":[11,94],"engineering":[12],"by":[13],"enabling":[14],"autonomous":[15],"code":[16,66,159],"agents":[17,35,147,160],"that":[18],"plan,":[19],"execute,":[20],"and":[21,41,103,113,138,141,145],"utilize":[22],"external":[23],"tools":[24],"iteratively":[25],"to":[26,60,123,148],"tackle":[27],"complex":[28],"tasks.":[29],"Beyond":[30],"achieving":[31],"functional":[32,54,139],"correctness,":[33],"these":[34],"must":[36],"faithfully":[37],"follow":[38],"process":[39],"instructions":[40,96],"constraints":[42,99,115],"throughout":[43],"lifecycle.":[46],"However,":[47],"existing":[48,158],"benchmarks":[49],"typically":[50],"focus":[51],"on":[52],"final":[53],"correctness":[55],"or":[56,64],"confine":[57],"instruction-following":[58,70],"evaluation":[59,129],"single-turn,":[61],"general":[62],"chat":[63],"simple":[65],"generation":[67],"scenarios,":[68],"leaving":[69],"in":[71,157,161],"multi-turn":[72,92,162],"agentic":[73],"coding":[74],"underexplored.":[75],"To":[76,126],"bridge":[77],"this":[78,87],"gap,":[79],"we":[80,131],"propose":[81],"MTAC-IFBench,":[82],"a":[83,120,133],"comprehensive":[84],"benchmark":[85],"for":[86,135],"critical":[88],"capability.":[89],"It":[90],"features":[91],"progressive":[93],"with":[97,164],"diverse":[98],"spanning":[100],"6":[101],"primary":[102],"18":[104],"secondary":[105],"categories.":[106],"With":[107],"an":[108],"average":[109],"7.04":[111],"turns":[112],"91.33":[114],"per":[116],"instance,":[117],"it":[118],"poses":[119],"rigorous":[121],"challenge":[122],"current":[124],"LLMs.":[125],"make":[127],"reliable,":[130],"construct":[132],"checklist":[134,151],"each":[136,150],"constraint":[137],"requirement,":[140],"integrate":[142],"verification":[143],"scripts":[144],"judge":[146],"verify":[149],"item.":[152],"MTAC-IFBench":[153],"identifies":[154],"significant":[155],"deficiencies":[156],"instruction-following,":[163],"their":[165],"performance":[166],"degrading":[167],"rapidly":[168],"as":[169],"interaction":[171],"session":[172],"grows":[173],"longer.":[174]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-09-16T00:00:00"}