{"id":"https://openalex.org/W7166511662","doi":"https://doi.org/10.48550/arxiv.2606.27757","title":"Towards Reliable and Robust LLM Planning: Symbolic Feedback-Driven Iterative Self-Refinement Framework","display_name":"Towards Reliable and Robust LLM Planning: Symbolic Feedback-Driven Iterative Self-Refinement Framework","publication_year":2026,"publication_date":"2026-06-26","ids":{"openalex":"https://openalex.org/W7166511662","doi":"https://doi.org/10.48550/arxiv.2606.27757"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.27757","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.27757","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.2606.27757","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139624616","display_name":"Jiajing Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jiajing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109388992","display_name":"Jiamei Jiang","orcid":"https://orcid.org/0009-0002-9096-5844"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Jiamei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139568555","display_name":"Chenyang Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Chenyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139589853","display_name":"Feifei Mo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mo, Feifei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139557013","display_name":"Linjing Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Linjing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5121317340","display_name":"Daniel Zeng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeng, Daniel","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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.3271999955177307,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.3271999955177307,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.11069999635219574,"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/T10028","display_name":"Topic Modeling","score":0.050999999046325684,"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/correctness","display_name":"Correctness","score":0.7222999930381775},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6668999791145325},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5291000008583069},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.49779999256134033},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.4812999963760376},{"id":"https://openalex.org/keywords/trustworthiness","display_name":"Trustworthiness","score":0.4632999897003174},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.3806000053882599},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.37869998812675476}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7605000138282776},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.7222999930381775},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6668999791145325},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5291000008583069},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.49779999256134033},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4812999963760376},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.4632999897003174},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.415800005197525},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4133000075817108},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3806000053882599},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.37869998812675476},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.36010000109672546},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.3564000129699707},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3531999886035919},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.3497999906539917},{"id":"https://openalex.org/C2779639559","wikidata":"https://www.wikidata.org/wiki/Q7661178","display_name":"Symbolic execution","level":3,"score":0.3425999879837036},{"id":"https://openalex.org/C39920170","wikidata":"https://www.wikidata.org/wiki/Q693083","display_name":"Soundness","level":2,"score":0.3395000100135803},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32350000739097595},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.30959999561309814},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.30140000581741333},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.2752000093460083},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.260699987411499},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.2540999948978424},{"id":"https://openalex.org/C100521375","wikidata":"https://www.wikidata.org/wiki/Q2015382","display_name":"Competence (human resources)","level":2,"score":0.25200000405311584},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.27757","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.27757","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.2606.27757","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.27757","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":{"Large":[0],"language":[1,74,85],"models":[2],"(LLMs)":[3],"have":[4],"attracted":[5],"widespread":[6],"attention":[7],"from":[8],"academia":[9],"and":[10,21,64,94,105,147,164],"industry,":[11],"yet":[12],"their":[13],"deployment":[14],"raises":[15],"critical":[16],"security":[17],"concerns":[18],"regarding":[19],"robustness":[20,63],"reliability.":[22],"Planning,":[23],"a":[24,54,72,99,122],"core":[25],"component":[26],"of":[27,66,161],"intelligent":[28],"behavior,":[29],"remains":[30],"challenging":[31],"for":[32],"LLMs,":[33],"which":[34],"often":[35],"produce":[36],"infeasible":[37],"or":[38],"incorrect":[39],"solutions":[40],"in":[41,68,149,157],"long-horizon":[42,69,150],"decision-making":[43],"tasks":[44],"due":[45],"to":[46,60,79,89,125,166],"inherent":[47],"complexity.":[48],"In":[49,118],"this":[50],"paper,":[51],"we":[52,120],"propose":[53],"symbolic":[55,100],"feedback-driven":[56],"iterative":[57],"self-refinement":[58],"framework":[59,142],"enhance":[61],"the":[62,113,140,159],"reliability":[65,160],"LLMs":[67,88],"planning.":[70],"Specifically,":[71],"natural":[73,84],"prompting":[75],"mechanism":[76],"is":[77],"introduced":[78],"map":[80],"logical":[81],"symbols":[82],"into":[83,108],"descriptions,":[86],"enabling":[87],"better":[90],"capture":[91],"task":[92],"constraints":[93],"semantics.":[95],"We":[96],"further":[97],"design":[98],"verifier":[101],"that":[102,139],"identifies":[103],"errors":[104],"converts":[106],"them":[107],"corrective":[109],"instructions":[110],"interpretable":[111],"by":[112],"LLM,":[114],"thereby":[115],"guiding":[116],"self-refinement.":[117],"addition,":[119],"leverage":[121],"plan":[123],"recognizer":[124],"infer":[126],"goal":[127],"reachability,":[128],"facilitating":[129],"more":[130,168],"effective":[131],"guidance":[132],"toward":[133],"desired":[134],"goals.":[135],"Empirical":[136],"results":[137],"demonstrate":[138],"proposed":[141],"consistently":[143],"improves":[144],"both":[145],"feasibility":[146],"correctness":[148],"planning":[151,163],"tasks.":[152],"This":[153],"highlights":[154],"its":[155],"effectiveness":[156],"enhancing":[158],"LLM-based":[162],"potential":[165],"enable":[167],"trustworthy":[169],"AI":[170],"systems.":[171]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-30T00:00:00"}