New SMITH framework lets small models rival larger ones with far fewer tokens, paving the way for scalable multi-agent collaboration

SINGAPORE, Sept. 30, 2026 /PRNewswire/ -- Appier (TSE: 4180), an AI-native company delivering Agentic AI as a Service (AaaS), today announced its latest research paper, "Joint Optimization of Tool Creation and Use for Large Language Model Agents," accepted at NeurIPS, the world's premier AI and machine learning conference, often called "the Olympics of AI." The paper introduces SMITH (Schema-grounded Multi-task Iterative Tool Honing), a reinforcement learning framework that lets AI build tools and use them effectively in a single training loop, with each tool continuously refined based on real-world problem-solving results. The breakthrough tackles a key challenge in Agentic AI: models can create tools, but often struggle to use them well.

The research shows that small models trained with SMITH can build reusable tools that rival those created by much larger models, even on tasks they have never seen. These tools can also be shared across models and tasks, significantly reducing the token cost of repeated reasoning. The paper's acceptance at NeurIPS highlights Appier's research strength in improving AI agent efficiency and advancing multi-agent collaboration, and reinforces its position at the forefront of global Agentic AI research.

"Humans turn their problem-solving experience into tools, so they never have to start from scratch. AI agents are now evolving in the same way," said Dr. Chih-Han Yu, CEO and Co-founder of Appier. "This research shows that agents can learn to build tools, continuously refine them, and share proven tools across models of all sizes, making multi-agent collaboration more efficient and scalable. NeurIPS's acceptance of this paper further recognizes Appier's forward-looking research and innovation. We will continue to bring Agentic AI into real-world applications and deliver measurable results for businesses."

AI agents must build tools and know whether they work

As Agentic AI handles more enterprise workflows on its own, selecting and calling the right external tools has become critical for real-world deployment. Yet many AI systems still rely on engineers to build APIs or configure fixed tools in advance, which must be rebuilt whenever data sources, tasks, or business needs change. Even when AI can create its own tools, existing methods typically assign creation and use to separate models. As a result, the tool-building model gets little feedback on real-world performance, and cannot easily tell whether a tool is clearly described, works reliably, or can be called correctly by other models.

SMITH puts both skills into one training loop, so the AI learns to build good tools and use them well at the same time. When a tool has a vague description, poorly designed parameters, or fails to run, that result feeds back into the model. A closed loop of building, using, verifying, and refining keeps improving tool quality. The study found that training tool creation and tool use together clearly beats training them separately.

"When SMITH trains a model to use tools, it sees only the tool's description and parameter specifications, not the underlying code," said Chieh-Yen Lin, Research Scientist at Appier. "This makes the clarity of each description, and whether the tool can be called correctly, direct feedback during training. Our experiments also confirmed that other models can use these tools to solve problems more effectively. Looking ahead, we hope to build models that can continuously interact with their environment and take on a wider range of tasks."

Learning from 4 examples, proven on 16 new problems

SMITH trains from easy to hard. The AI first learns a method from 4 simple examples and builds tools from it. It then tests the model on 16 harder, previously unseen problems to see whether it can generalize. It keeps only tools that solve new problems and adds them to a shared tool library that multiple AI agents can use. As more high-quality tools come in, better ones replace weaker ones. Instead of building new tools for every task, agents can build and reuse proven problem-solving skills.

The research delivers three key findings:

1. Small models can outperform larger ones at tool creation: A model of about 4 billion parameters trained with SMITH built tools that outperformed those from every other method in the study on unseen tasks. It even beat a baseline in which a roughly 30-billion-parameter model built tools on the fly. Effective tool creation doesn't have to depend on bigger models.
   
   
   
   
2. Proven tools work across model sizes: Tools built by the small model handled new tasks well even when used by a lightweight model of only about 350 million parameters. The same tools also boosted the performance of larger models, allowing agents to divide work more flexibly and efficiently.
   
   
   
   
3. Repeated reasoning becomes a reusable tool: SMITH turns repeated reasoning into tools that can be called directly. In experiments, average output fell from 3,206 tokens with conventional step-by-step reasoning to about 100 tokens, roughly a 32-fold gain in efficiency. When facing similar problems, the AI doesn't need to run the full reasoning process every time, maintaining task performance while speeding up reasoning and lowering compute costs.

This research opens a new direction for enterprise Agentic AI. Many daily operations are repetitive, from converting financial metrics and processing data to querying reports, checking rules, and routing customer service cases. AI could turn these scattered methods into proven, shared tools that any agent can call, cutting the cost of repeated development and reasoning.

In advertising and marketing, agents handling customer data, personalization, customer service, and ad buying can share proven tools and consistent business rules to collaborate more efficiently. Whether entering a new market, onboarding a new advertiser, or starting with limited data, businesses can turn past successes into verifiable, scalable AI capabilities that help agents adapt to new tasks faster. Appier will continue to advance Agentic AI through forward-looking research, making AI a core engine of long-term business growth.

About Appier

Appier (TSE: 4180) is an AI-native Agentic AI as a Service (AaaS) company that empowers business decision-making with cutting-edge AdTech and MarTech solutions. Founded in 2012 with the vision of "Making AI Easy by making software intelligent," Appier endeavors to help businesses turn AI into ROI with its Ad Cloud, Personalization Cloud, and Data Cloud solutions. Now Appier has 17 offices across APAC, the US and EMEA, and is listed on the Tokyo Stock Exchange. Visit www.appier.com for more company information, and visit ir.appier.com/en/ for more IR information.

View original content to download multimedia:https://www.prnewswire.co.uk/news-releases/appier-research-accepted-at-neurips-ai-agents-learn-not-only-to-use-tools-but-to-build-their-own-302894483.html

Die steirische FPÖ hat ihren traditionellen Frühschoppen beim Hartberger Oktoberfest erneut für eine machtbewusste politische Inszenierung genutzt. Vor rund 3.500 Besucherinnen und Besuchern im vollen Festzelt trat zuerst die Landesführung um Landeshauptmann Mario Kunasek auf, ehe Bundesparteichef Herbert Kickl als Hauptredner die Bühne übernahm. Begleitet von österreichischen Fahnen, „Herbert“-Sprechchören und Schlagern wie Tina Turners „The Best“ präsentierten sich die Freiheitlichen als geschlossene Kraft mit bundespolitischem Anspruch.

Kunasek, der sich nach zuletzt guten Umfragewerten demonstrativ gelöst gab, lobte die Zusammenarbeit mit dem Koalitionspartner ÖVP in der Steiermark. Man streite nicht, sondern es gebe „Arbeit, Arbeit, Arbeit und es funktioniert“, sagte der Landeshauptmann und verwies darauf, dass die „heilige Ordnung“ nach der Landtagswahl 2024 nicht mehr gegolten habe. Zugleich zeichnete er ein scharfes Bild in der Migrations- und Integrationspolitik, warnte vor einer Gefahr durch den „politischen Islam“ und erklärte, für Menschen, die mit „unseren Werten“ ein Problem hätten, müsse es heißen: „Ab, gute Reise.“ Sein Ziel formulierte er klar: Man könne nicht nur den Landeshauptmann stellen, sondern „Österreich auf Vordermann bringen“.

Kickl knüpfte an diese Steilvorlage an und nutzte den Auftritt, um sowohl die eigene Anhängerschaft zu mobilisieren als auch die Konkurrenz frontal anzugreifen. Die „wirkliche Volkspartei“ sei im Zelt versammelt, erklärte er und spielte sich gleichzeitig als von Gegnern unterschätzter, aber entschlossener Politiker in Szene. Er verwies darauf, dass er vielfach als „gefährlichster Politiker“ bezeichnet werde, stellte jedoch klar, gefährlich sei er aus seiner Sicht nicht für „meine Landsleute“, sondern für jene, „die unseren Wohlstand verludern und unsere Heimat stehlen“. Inhaltlich bekräftigte er dabei einmal mehr den Begriff „Remigration“ als eine seiner Visionen für ein künftiges Österreich.

Breiten Raum nahm in Kickls Rede die aktuelle Krise der SPÖ ein, die er als Chance für seine Partei deutete. Die Sozialdemokratie bezeichnete er polemisch als „Selbsthilfegruppe namens Soziademokratie“ und kommentierte die Diskussion um die Nachfolge von Bundesparteichef Andreas Babler mit der Ansage „game over, das Spiel ist vorbei“. Innerhalb der SPÖ würden „Kommunisten mit Kapitalisten streiten, wer die besseren Sozialisten sind“, sagte Kickl mit Blick auf innerparteiliche Flügelkonflikte und Ambitionen potenzieller Kandidaten. Für die kommende Nationalratswahl, die er als „Schicksalswahl“ charakterisierte, gab er sich siegessicher: Wenn sich die Freiheitlichen nicht „auseinanderdividieren lassen“, werde am Ende ein „Volkskanzler“ stehen. Neuwahlen könnten seiner Einschätzung nach „jederzeit daherkommen“, die steirische FPÖ um Kunasek präsentierte er als Vorbild für die Partei in anderen Bundesländern.