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

Der hessische Ministerpräsident Boris Rhein (CDU) hat eine Neujustierung des Umgangs mit der AfD im Bundestag gefordert und damit eine innerparteiliche wie parlamentarische Grundsatzdebatte angestoßen. In einem Interview mit dem Magazin „Stern“ plädierte der CDU-Politiker dafür, der AfD die ihr nach dem üblichen Verteilungsschlüssel zustehenden Vorsitzendenposten in den Fachausschüssen des Bundestags nicht länger zu verwehren. „Die Partei ist gewählt, und so sollte man mit ihr auch umgehen“, sagte Rhein und verwies darauf, dass die AfD im hessischen Landtag und in anderen Länderparlamenten bereits Ausschussvorsitze innehat.

Im Bundestag verfügt die AfD wie die anderen Fraktionen über ein Vorschlagsrecht für bestimmte Ausschussvorsitze. Bisher scheiterte sie jedoch regelmäßig daran, dass ihre Kandidatinnen und Kandidaten bei den Wahlen in den Ausschüssen nicht die Unterstützung der Abgeordneten der übrigen Parteien erhielten und damit die nötigen Mehrheiten verfehlten. Eine Klage der AfD-Bundestagsfraktion vor dem Bundesverfassungsgericht blieb im September 2024 ohne Erfolg; Karlsruhe sah keinen Anlass, in das Verfahren der Ausschussbesetzungen einzugreifen. Politisch aber gewinnt die Frage durch Rheins Vorstoß neue Brisanz.

Rhein grenzt sich zugleich von einer inhaltlichen Annäherung an die AfD ab und lehnt ein Verbotsverfahren gegen die Partei ab. Er halte das vielzitierte Bild einer „Brandmauer“ für falsch, betonte der CDU-Landeschef. Für die Union gelte: „Wir grenzen uns klar von der AfD ab, aber wir grenzen die Partei nicht aus.“ Das müsse sich auch in der Parlamentsarbeit widerspiegeln. Anstelle juristischer Schritte warb Rhein dafür, die AfD politisch zu stellen: Die CDU müsse den Wählerinnen und Wählern „ein besseres Angebot machen“ und die „Deutungshoheit über die Alltagsfragen“ zurückgewinnen. Eine Zusammenarbeit mit der AfD setze aus seiner Sicht eine „Politik der klaren roten Linien“ voraus.

Die AfD bewertet die Äußerungen des hessischen Regierungschefs als Signal eines sich abzeichnenden Kurswechsels in der Union. Der Parlamentarische Geschäftsführer der AfD-Bundestagsfraktion, Bernd Baumann, sprach gegenüber der Nachrichtenagentur AFP von einem „überfälligen“ Schritt und einem Zeichen für ein „generelles Umdenken in der CDU“. Die Forderung nach Ausschussvorsitzen sei „nur der erste Schritt – weitere werden folgen“, prognostizierte Baumann. Angesichts jüngster Wahlergebnisse sehe er die Union unter Druck, ihre bisherige Ausgrenzungsstrategie zu überdenken. Koalitionsfraktionen im Bundestag wiesen einen von Rhein geforderten Kurswechsel allerdings zurück und halten bislang an der Linie fest, AfD-Kandidaten für Ausschussvorsitze nicht zu unterstützen.

In den Fachausschüssen des Bundestags wird ein Großteil der inhaltlichen Gesetzgebungsarbeit vorbereitet. Die Vorsitzenden spielen eine zentrale Rolle bei der Organisation der Beratungen und der Tagesordnungsgestaltung. Die Verteilung dieser Schlüsselpositionen erfolgt nach einem festgelegten Schlüssel zwischen den Fraktionen, doch bleibt die tatsächliche Besetzung an die Wahl durch die Ausschussmitglieder gebunden. Vor diesem Hintergrund berührt die von Rhein angestoßene Debatte nicht nur die Machtbalance zwischen den Fraktionen, sondern auch die Frage, wie das Parlament mit Parteien umgeht, die zwar demokratisch gewählt sind, von großen Teilen des Hauses aber weiterhin klar abgelehnt werden.