Time series reasoning tasks often start with a natural language question and require targeted analysis of a time series. Evidence may span the full series or appear in a few short intervals, so the model must decide what to inspect. Most existing approaches encode the entire time series into a fixed representation before inference, regardless of whether or not the entire sequence is relevant. We introduce ARTIST, which formulates time-series reasoning as a sequential decision problem. ARTIST interleaves reasoning with adaptive temporal segment selection. It adopts a controller-reasoner architecture and uses reinforcement learning to train the controller role to select informative segments and the reasoner role to generate segment-conditioned reasoning traces and final answers. During inference, the model actively acquires task-relevant information instead of relying on a static summary of the full sequence. We use a novel hierarchical policy optimization approach for post-training that allows the model to excel in both segment selection and question-answering behavior. We evaluate ARTIST on six time-series reasoning benchmarks and compare it with large language models, vision-language models, and prior time-series reasoning systems. ARTIST improves average accuracy by 6.46 absolute percentage points over the strongest baseline. The largest gains appear on rare event localization and multi-segment reasoning tasks. Supervised fine-tuning improves performance, and reinforcement learning provides additional gains by optimizing question-adaptive segment selection. These results show that selective data use drives effective time-series reasoning.<\/p>\n","protected":false},"excerpt":{"rendered":"
Time series reasoning tasks often start with a natural language question and require targeted analysis of a time series. Evidence may span the full series or appear in a few short intervals, so the model must decide what to inspect. Most existing approaches encode the entire time series into a fixed representation before inference, regardless […]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","msr-author-ordering":[{"type":"text","value":"Shvat Messica","user_id":0},{"type":"user_nicename","value":"Jiawen Zhang","user_id":"44233"},{"type":"text","value":"Kevin Li","user_id":0},{"type":"text","value":"Theodoros Tsiligkaridis","user_id":0},{"type":"text","value":"M. Zitnik","user_id":0}],"msr_publishername":"","msr_publisher_other":"","msr_booktitle":"","msr_chapter":"","msr_edition":"","msr_editors":"","msr_how_published":"arXiv","msr_isbn":"","msr_issue":"","msr_journal":"","msr_number":"","msr_organization":"","msr_pages_string":"","msr_page_range_start":"","msr_page_range_end":"","msr_series":"","msr_volume":"","msr_copyright":"","msr_conference_name":"","msr_doi":"10.48550\/arXiv.2602.18645","msr_arxiv_id":"2602.18645","msr_mag_id":"","msr_other_authors":"","msr_other_contributors":"","msr_speaker":"","msr_award":"","msr_affiliation":"","msr_institution":"","msr_host":"","msr_version":"","msr_duration":"","msr_release_tracker_id":"","msr_highlight_type":"","msr_date_display_format":"","msr_main_download_label":"","msr_external_link_label":"","msr_doi_label":"","msr_published_date":"2026-02-20","msr_startdate":"","msr_presentation_date":"","msr_highlight_text":"","msr_notes":"","msr_longbiography":"","msr_publicationurl":"","msr_external_url":"","msr_secondary_video_url":"","msr_conference_url":"","msr_journal_url":"","msr_year":2026,"msr_month":2,"msr_day":20,"msr_microsoftintellectualproperty":false,"msr_pub_id":"3ab8286b0d07447bfb9a87980a8f8656f535da1a","msr_publication_uploader":[{"type":"url","title":"https:\/\/arxiv.org\/abs\/2602.18645","label_id":243109,"id":false,"viewUrl":false},{"type":"url","title":"https:\/\/dblp.org\/rec\/journals\/corr\/abs-2602-18645.html","label_id":243109,"id":false,"viewUrl":false}],"msr_related_uploader":[],"msr_original_fields_of_study":[],"msr_s2_paper_id":"3ab8286b0d07447bfb9a87980a8f8656f535da1a","msr_s2_pdf_url":"","msr_citation_count_updated":"","msr_citation_count":1,"msr_influential_citations":0,"msr_reference_count":53,"msr_s2_open_access":false,"msr_s2_author_ids":[],"msr_pub_ids":[{"provider":"s2","id":"3ab8286b0d07447bfb9a87980a8f8656f535da1a"},{"provider":"doi","id":"10.48550\/arXiv.2602.18645"},{"provider":"arxiv","id":"2602.18645"},{"provider":"dblp","id":"journals\/corr\/abs-2602-18645"},{"provider":"corpusid","id":"285973423"}],"msr_hide_image_in_river":0,"footnotes":""},"msr-research-highlight":[],"research-area":[13556],"msr-publication-type":[270373],"msr-publisher":[],"msr-publication-cta":[],"msr-focus-area":[],"msr-locale":[268875],"msr-post-option":[],"msr-field-of-study":[246691,265497],"msr-conference":[],"msr-journal":[268188],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-1179131","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-artificial-intelligence","msr-locale-en_us","msr-field-of-study-computer-science","msr-field-of-study-machine-learning-296"],"msr_publishername":"","msr_edition":"","msr_affiliation":"","msr_published_date":"2026-02-20","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"","msr_chapter":"","msr_isbn":"","msr_journal":"","msr_volume":"","msr_number":"","msr_editors":"","msr_series":"","msr_issue":"","msr_organization":"","msr_how_published":"arXiv","msr_notes":"","msr_highlight_text":"","msr_release_tracker_id":"","msr_original_fields_of_study":"","msr_download_urls":"","msr_external_url":"","msr_secondary_video_url":"","msr_longbiography":"","msr_microsoftintellectualproperty":0,"msr_main_download":"","msr_publicationurl":"","msr_doi":"10.48550\/arXiv.2602.18645","msr_publication_uploader":[{"type":"url","title":"https:\/\/arxiv.org\/abs\/2602.18645","label_id":243109,"id":false,"viewUrl":false},{"type":"url","title":"https:\/\/dblp.org\/rec\/journals\/corr\/abs-2602-18645.html","label_id":243109,"id":false,"viewUrl":false}],"msr_related_uploader":[],"msr_citation_count":1,"msr_citation_count_updated":"","msr_s2_paper_id":"3ab8286b0d07447bfb9a87980a8f8656f535da1a","msr_influential_citations":0,"msr_reference_count":53,"msr_arxiv_id":"2602.18645","msr_s2_author_ids":[],"msr_s2_open_access":false,"msr_s2_pdf_url":null,"msr_attachments":[],"msr-author-ordering":[{"type":"text","value":"Shvat Messica","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Jiawen Zhang","user_id":44233,"rest_url":"https:\/\/research.codeghost.online\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Jiawen Zhang"},{"type":"text","value":"Kevin Li","user_id":0,"rest_url":false},{"type":"text","value":"Theodoros Tsiligkaridis","user_id":0,"rest_url":false},{"type":"text","value":"M. Zitnik","user_id":0,"rest_url":false}],"msr_impact_theme":[],"msr_research_lab":[],"msr_event":[],"msr_group":[1144240],"msr_project":[],"publication":[],"video":[],"msr-tool":[],"msr_publication_type":"misc","related_content":[],"_links":{"self":[{"href":"https:\/\/research.codeghost.online\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1179131","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/research.codeghost.online\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/research.codeghost.online\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":2,"href":"https:\/\/research.codeghost.online\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1179131\/revisions"}],"predecessor-version":[{"id":1179419,"href":"https:\/\/research.codeghost.online\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1179131\/revisions\/1179419"}],"wp:attachment":[{"href":"https:\/\/research.codeghost.online\/en-us\/research\/wp-json\/wp\/v2\/media?parent=1179131"}],"wp:term":[{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/research.codeghost.online\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=1179131"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/research.codeghost.online\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=1179131"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/research.codeghost.online\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=1179131"},{"taxonomy":"msr-publisher","embeddable":true,"href":"https:\/\/research.codeghost.online\/en-us\/research\/wp-json\/wp\/v2\/msr-publisher?post=1179131"},{"taxonomy":"msr-publication-cta","embeddable":true,"href":"https:\/\/research.codeghost.online\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-cta?post=1179131"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/research.codeghost.online\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=1179131"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/research.codeghost.online\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=1179131"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/research.codeghost.online\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=1179131"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/research.codeghost.online\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=1179131"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/research.codeghost.online\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=1179131"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/research.codeghost.online\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=1179131"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/research.codeghost.online\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=1179131"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/research.codeghost.online\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=1179131"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}