This paper was accepted on the Fifth Workshop on Pure Language Technology, Analysis, and Metrics at ACL 2026.<\/p>\n

Software-calling brokers are evaluated on device choice, parameter accuracy, and scope recognition, but LLM trajectory assessments stay inherently post-hoc. Disconnected from the energetic execution loop, such assessments establish errors which are normally addressed by way of prompt-tuning or retraining, and essentially can not course-correct the agent in actual time. To shut this hole, we transfer analysis into the execution loop at inference time: a specialised reviewer agent evaluates provisional device calls previous to execution, shifting the paradigm from post-hoc restoration to proactive analysis and error mitigation.<\/p>\n

In apply, this structure establishes a transparent separation of issues between the first execution agent and a secondary overview agent. As with all multi-agent system, the reviewer can introduce new errors whereas correcting others, but no prior work to our information has systematically measured this tradeoff. To quantify this tradeoff, we introduce Helpfulness-Harmfulness metrics: helpfulness measures the proportion of base agent errors that suggestions corrects; harmfulness measures the proportion of right responses that suggestions degrades. These metrics straight inform reviewer design by revealing whether or not a given mannequin or immediate offers internet constructive worth.<\/p>\n

We consider our method on BFCL (single-turn) and \u03c42-Bench (multi-turn stateful situations), attaining +5.5% on irrelevance detection and +7.1% on multi-turn duties. Our metrics reveal that reviewer mannequin selection is essential: the reasoning mannequin o3-mini achieves a 3:1 benefit-to-risk ratio versus 2.1:1 for GPT-4o. Automated immediate optimization through GEPA offers a further +1.5\u20132.8%. Collectively, these outcomes reveal a core benefit of separating execution and overview: the reviewer will be systematically improved by way of mannequin choice and immediate optimization, with out retraining the bottom agent.<\/p>\n<\/div>\n\n","protected":false},"excerpt":{"rendered":"

This paper was accepted on the Fifth Workshop on Pure Language Technology, Analysis, and Metrics at ACL 2026. Software-calling brokers are evaluated on device choice, parameter accuracy, and scope recognition, but LLM trajectory assessments stay inherently post-hoc. Disconnected from the energetic execution loop, such assessments establish errors which are normally addressed by way of prompt-tuning […]<\/p>\n","protected":false},"author":2,"featured_media":14366,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[55],"tags":[75,617,3029,3492,8905,8906],"class_list":["post-14364","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-machine-learning","tag-agent","tag-agents","tag-feedback","tag-inferencetime","tag-reinforced","tag-toolcalling"],"_links":{"self":[{"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=\/wp\/v2\/posts\/14364","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=14364"}],"version-history":[{"count":1,"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=\/wp\/v2\/posts\/14364\/revisions"}],"predecessor-version":[{"id":14365,"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=\/wp\/v2\/posts\/14364\/revisions\/14365"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=\/wp\/v2\/media\/14366"}],"wp:attachment":[{"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=14364"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=14364"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=14364"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}