Newest papers

RACE: Learning Multimodal Search through Referential Abstraction and Compositional Evidence

Eric Tao, Minhao Sun, Liyan Liu, Zhijing Wu, Xiaohan Yu, Lang Mei, Li Huang, Chao Feng, Jinchao Ma, Sichen Kang, Siyu Mo, Chong Chen · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.28382 · cited by 0 works (OpenAlex) · open-access PDF

German

Das Training von multimodalen Suchagenten erfordert Daten, die eine visuell zugrunde liegende Suche zur Bestimmung der Antwort erforderlich machen. Textidentitäts-Tipps und ungenutzte Zielbeweise ermöglichen Abkürzungen in synthetischen Fragen, die Aufsicht für die visuelle Suche und die Integration von Beweisen schwächen. Wir schlagen RACE vor, ein Bildbedingter Task-Synthese-Framework, das Abhängigkeiten von Bildern zu Zielen und von zielspezifischen Beweisen zu Antworten konstruiert. Referenzabstraktion (RA) ersetzt Identitäts-weiterlegenden Text mit spezifischen visuellen Referenzen oder zweideutigen relationalen Referenzen, die durch die Suche unter den dargestellten Kandidaten gelöst werden. Compositional Evidence (CE) verbindet abgeruf

Machine translation (Meta M2M100); the English original follows.

Abstract

Training multimodal search agents requires tasks that make visually grounded search necessary for determining the answer. Textual identity clues and unused target evidence allow shortcuts in synthetic questions, weakening supervision for visual search and evidence integration. We propose RACE, an image-conditioned task synthesis framework that constructs dependencies from images to targets and from target-specific evidence to answers. Referential Abstraction (RA) replaces identity-revealing text with specific visual references or ambiguous relational references resolved by searching among depicted candidates. Compositional Evidence (CE) links retrieved facts about multiple entities in one image or entities from different images into joint questions whose answers require every designated contribution. Both operations also apply to images found during search, allowing new visual observations to determine subsequent search targets or supply answer evidence. Fine-tuning Qwen3.5-27B on only 12K teacher-generated trajectories from RACE raises average accuracy across ten multimodal benchmarks from 53.5 to 56.0, a relative improvement of approximately 4.7% over the matched base agent. Our code, data, and model will be publicly available.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Abstraction, Computer science, Task (project management), Artificial intelligence, Visual search, Natural language processing

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange