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

Mit einem betont unterhaltsamen und zugleich programmatischen Auftritt hat der Kanton Schwyz seine Rolle als Gastkanton an der 83. Olma in St. Gallen übernommen. Bereits die offizielle Eröffnungsfeier im Theater St. Gallen zeigte, wie breit sich der Innerschweizer Kanton präsentieren will – kulturell, politisch und touristisch. Unter dem Motto «Schwyz liefert» rückt der Kanton während elf Tagen ein gutes Stück weiter nach Osten und nutzt die Publikumsmesse als Schaufenster für seine Produkte, sein Brauchtum und seine Eigenheiten.

Musikalisch setzte Schwyz zum Auftakt auf vertraute Namen mit regionalen Wurzeln: Unter der geistreichen, pointierten Moderation der Schwyzer Dirigentin Graziella Contratto spannten Jodlerin Nadja Räss, Schwyzerörgeler Markus Flückiger, Kontrabassist Pirmin Huber, Violinist Raphael Nussbaumer, das Ensemble Kulturschock mit Mezzosopranistin Lydia Opilik sowie Sängerin Linda Elys den Bogen von Volksmusik über Klassik bis Pop. Das Publikum im Stadttheater dankte den Schwyzer Klängen, die sonst eher zwischen Mythen und Rigi zuhause sind, mit tosendem Applaus.

Auch die Bundespolitik war prominent vertreten. Bundesrat Guy Parmelin eröffnete die Messe traditionsgemäss mit einem Ferkel – in diesem Jahr mit Säuli Vivienne, das sich beim Fototermin mit lautem Quieken gegen den Auftritt wehrte. Der Landwirtschaftsminister nutzte die Bühne, um die Olma als «herausragenden Begegnungsort» zwischen Konsumenten und Landwirtschaft zu würdigen und sprach von einer «Schweiz im Kleinformat», in der Fachleute, Familien, Politiker und Tiere zusammenkommen. Gleichzeitig verwies er auf die «Ernsthaftigkeit der Lage» für die Landwirtschaft, etwa mit Blick auf Trockenheit und grosse Hitze im vergangenen Sommer.

Der Schwyzer Landammann Sandro Patierno und Regierungsrätin Petra Steimen-Rickenbacher, Präsidentin des Organisationskomitees für den Gastkanton-Auftritt, stellten den Kanton ins Zentrum. Patierno zeigte sich besonders stolz auf den in Übergrösse ausgestellten Bundesbrief, das Hölloch und die legendären Wetterpropheten und spielte im Bühnengespräch mit Contratto mit dem Motto «Schwyz liefert». Humor bewies er auch, als er – gefragt nach seinen Lieblingstieren – Wildsäue, Wölfe und die Asiatische Hornisse nannte und festhielt, der Kanton Schwyz «liefere» auch in dieser Hinsicht. Verwaltungsratspräsident Markus Streckeisen erklärte die Olma schliesslich offiziell für eröffnet und erinnerte daran, dass die Messe aus dem Zusammenspiel vieler Menschen und Partnerschaften entstehe.

Während der elf Messetage, die in St. Gallen als «fünfte Jahreszeit» gelten, setzt der Gastkanton auf ein Konzept mit zahlreichen Boxen, in denen Besucher Produkte und Bräuche aus Schwyz entdecken können. Neben Klassikern wie der Degustationshalle bleibt auch das traditionelle Säulirennen um 16 Uhr ein Publikumsmagnet. Für Bundesrat Parmelin, der direkt von einem Staatsbesuch in Neu-Delhi an den «etwas kleineren Flughafen» Altenrhein reiste, ist der Gang durch die Olma mehr als Folklore: Er bezeichnete den offenen Dialog zwischen Produzenten, Verarbeitern, Händlern, Konsumenten und Regulierungsbehörden als zentral – eine Botschaft, die zum Selbstverständnis der Messe und zum Auftritt des Gastkantons gleichermassen passt.