{"id":1151270,"date":"2025-10-06T03:47:46","date_gmt":"2025-10-06T10:47:46","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-research-item&#038;p=1151270"},"modified":"2025-10-06T03:48:26","modified_gmt":"2025-10-06T10:48:26","slug":"ecoact-economic-agent-determines-when-to-register-what-action","status":"publish","type":"msr-research-item","link":"https:\/\/www.microsoft.com\/en-us\/research\/publication\/ecoact-economic-agent-determines-when-to-register-what-action\/","title":{"rendered":"EcoAct: Economic Agent Determines When to Register What Action"},"content":{"rendered":"<blockquote class=\"abstract mathjax\"><p>Recent advancements have enabled Large Language Models (LLMs) to function as agents that can perform actions using external tools. This requires registering, i.e., integrating tool information into the LLM context prior to taking actions. Current methods indiscriminately incorporate all candidate tools into the agent&#8217;s context and retain them across multiple reasoning steps. This process remains opaque to LLM agents and is not integrated into their reasoning procedures, leading to inefficiencies due to increased context length from irrelevant tools. To address this, we introduce EcoAct, a tool using algorithm that allows LLMs to selectively register tools as needed, optimizing context use. By integrating the tool registration process into the reasoning procedure, EcoAct reduces computational costs by over 50% in multiple steps reasoning tasks while maintaining performance, as demonstrated through extensive experiments. Moreover, it can be plugged into any reasoning pipeline with only minor modifications to the prompt, making it applicable to LLM agents now and future.<\/p><\/blockquote>\n","protected":false},"excerpt":{"rendered":"<p>Recent advancements have enabled Large Language Models (LLMs) to function as agents that can perform actions using external tools. This requires registering, i.e., integrating tool information into the LLM context prior to taking actions. Current methods indiscriminately incorporate all candidate tools into the agent&#8217;s context and retain them across multiple reasoning steps. This process remains [&hellip;]<\/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":null,"msr_publishername":"","msr_publisher_other":"","msr_booktitle":"","msr_chapter":"","msr_edition":"","msr_editors":"","msr_how_published":"","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":"ICLR Workshop on Reasoning and Planning for Large Language Models","msr_doi":"","msr_arxiv_id":"","msr_s2_paper_id":"","msr_mag_id":"","msr_pubmed_id":"","msr_other_authors":"","msr_other_contributors":"","msr_speaker":"","msr_award":"","msr_affiliation":"","msr_institution":"","msr_host":"","msr_version":"","msr_duration":"","msr_original_fields_of_study":"","msr_release_tracker_id":"","msr_s2_match_type":"","msr_citation_count_updated":"","msr_published_date":"2025-4-1","msr_highlight_text":"","msr_notes":"","msr_longbiography":"","msr_publicationurl":"","msr_external_url":"","msr_secondary_video_url":"","msr_conference_url":"","msr_journal_url":"","msr_s2_pdf_url":"","msr_year":0,"msr_citation_count":0,"msr_influential_citations":0,"msr_reference_count":0,"msr_s2_match_confidence":0,"msr_microsoftintellectualproperty":true,"msr_s2_open_access":false,"msr_s2_author_ids":[],"msr_pub_ids":[],"msr_hide_image_in_river":null,"footnotes":""},"msr-research-highlight":[],"research-area":[13556],"msr-publication-type":[193716],"msr-publisher":[],"msr-focus-area":[],"msr-locale":[268875],"msr-post-option":[269148,269142],"msr-field-of-study":[],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-1151270","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-artificial-intelligence","msr-locale-en_us","msr-post-option-approved-for-river","msr-post-option-include-in-river"],"msr_publishername":"","msr_edition":"","msr_affiliation":"","msr_published_date":"2025-4-1","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":"","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":1,"msr_main_download":"","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"url","viewUrl":"false","id":"false","title":"https:\/\/arxiv.org\/abs\/2411.01643","label_id":"243109","label":0}],"msr_related_uploader":"","msr_citation_count":0,"msr_citation_count_updated":"","msr_s2_paper_id":"","msr_influential_citations":0,"msr_reference_count":0,"msr_arxiv_id":"","msr_s2_author_ids":[],"msr_s2_open_access":false,"msr_s2_pdf_url":null,"msr_attachments":[],"msr-author-ordering":[{"type":"text","value":"Shaokun Zhang","user_id":0,"rest_url":false},{"type":"text","value":"Jieyu Zhang","user_id":0,"rest_url":false},{"type":"text","value":"Dujian Ding","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Mirian Hipolito Garcia","user_id":40483,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Mirian Hipolito Garcia"},{"type":"user_nicename","value":"Ankur Mallick","user_id":42441,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Ankur Mallick"},{"type":"user_nicename","value":"Daniel Eduardo Madrigal Diaz","user_id":40480,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Daniel Eduardo Madrigal Diaz"},{"type":"user_nicename","value":"Molly Xia","user_id":41943,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Molly Xia"},{"type":"user_nicename","value":"Victor Ruehle","user_id":41027,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Victor Ruehle"},{"type":"text","value":"Qingyun Wu","user_id":0,"rest_url":false},{"type":"text","value":"Chi Wang","user_id":0,"rest_url":false}],"msr_impact_theme":[],"msr_research_lab":[],"msr_event":[],"msr_group":[1145968],"msr_project":[1150288,1150291],"publication":[],"video":[],"msr-tool":[],"msr_publication_type":"inproceedings","related_content":{"projects":[{"ID":1150288,"post_title":"System\u2011level innovation for inference at scale\u00a0","post_name":"system%e2%80%91level-innovation-for-inference-at-scale","post_type":"msr-project","post_date":"2025-10-22 10:22:38","post_modified":"2025-11-07 05:24:36","post_status":"publish","permalink":"https:\/\/www.microsoft.com\/en-us\/research\/project\/system%e2%80%91level-innovation-for-inference-at-scale\/","post_excerpt":"We reimagine the AI inference stack to be workload-aware, cost-aware, and resilient at a global scale. Our research explores innovative resource allocation, request scheduling, batching, routing, and KV caching techniques, which directly benefit Microsoft's inference infrastructure. Our goal is to bridge the gap between deployed AI models and underlying hardware through a holistic, full-stack approach. We leverage not only the diversity across workloads (e.g., agentic vs. non-agentic, stringent vs. relaxed latency requirements), model architectures and&hellip;","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/1150288"}]}},{"ID":1150291,"post_title":"Efficient AI applications: context engineering and agents","post_name":"efficient-ai-applications-context-engineering-and-agents","post_type":"msr-project","post_date":"2025-10-22 10:21:05","post_modified":"2025-11-07 05:25:17","post_status":"publish","permalink":"https:\/\/www.microsoft.com\/en-us\/research\/project\/efficient-ai-applications-context-engineering-and-agents\/","post_excerpt":"Modern AI systems face a dual challenge: delivering high\u2011quality outputs while staying cost- and latency\u2011efficient. Every token processed and every millisecond of compute impacts scalability, user experience, and sustainability. Efficiency isn\u2019t just an optimisation, it\u2019s a design principle that makes AI applications feasible and scalable. Efficient AI applications start with the right context. Identifying relevant information, reducing redundancy, and maintaining long-term memory are key to effective performance. Our research combines structured and unstructured context pruning,&hellip;","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/1150291"}]}}]},"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1151270","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":1,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1151270\/revisions"}],"predecessor-version":[{"id":1151271,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1151270\/revisions\/1151271"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=1151270"}],"wp:term":[{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=1151270"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=1151270"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=1151270"},{"taxonomy":"msr-publisher","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publisher?post=1151270"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=1151270"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=1151270"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=1151270"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=1151270"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=1151270"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=1151270"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=1151270"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=1151270"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}