X-Reasoner: Towards Generalizable Reasoning Across Modalities and Domains

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Liu, Qianchu, Zhang, Sheng, Qin, Guanghui, Ossowski, Timothy, Gu, Yu, Jin, Ying, Kiblawi, Sid, Preston, Sam, Wei, Mu, Vozila, Paul, Naumann, Tristan, Poon, Hoifung
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908354364833792
author Liu, Qianchu
Zhang, Sheng
Qin, Guanghui
Ossowski, Timothy
Gu, Yu
Jin, Ying
Kiblawi, Sid
Preston, Sam
Wei, Mu
Vozila, Paul
Naumann, Tristan
Poon, Hoifung
author_facet Liu, Qianchu
Zhang, Sheng
Qin, Guanghui
Ossowski, Timothy
Gu, Yu
Jin, Ying
Kiblawi, Sid
Preston, Sam
Wei, Mu
Vozila, Paul
Naumann, Tristan
Poon, Hoifung
contents Recent proprietary models (e.g., o3) have begun to demonstrate strong multimodal reasoning capabilities. Yet, most existing open-source research concentrates on training text-only reasoning models, with evaluations limited to mainly mathematical and general-domain tasks. Therefore, it remains unclear how to effectively extend reasoning capabilities beyond text input and general domains. This paper explores a fundamental research question: Is reasoning generalizable across modalities and domains? Our findings support an affirmative answer: General-domain text-based post-training can enable such strong generalizable reasoning. Leveraging this finding, we introduce X-Reasoner, a vision-language model post-trained solely on general-domain text for generalizable reasoning, using a two-stage approach: an initial supervised fine-tuning phase with distilled long chain-of-thoughts, followed by reinforcement learning with verifiable rewards. Experiments show that X-Reasoner successfully transfers reasoning capabilities to both multimodal and out-of-domain settings, outperforming existing state-of-the-art models trained with in-domain and multimodal data across various general and medical benchmarks (Figure 1). Additionally, we find that X-Reasoner's performance in specialized domains can be further enhanced through continued training on domain-specific text-only data. Building upon this, we introduce X-Reasoner-Med, a medical-specialized variant that achieves new state of the art on numerous text-only and multimodal medical benchmarks.
format Preprint
id arxiv_https___arxiv_org_abs_2505_03981
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle X-Reasoner: Towards Generalizable Reasoning Across Modalities and Domains
Liu, Qianchu
Zhang, Sheng
Qin, Guanghui
Ossowski, Timothy
Gu, Yu
Jin, Ying
Kiblawi, Sid
Preston, Sam
Wei, Mu
Vozila, Paul
Naumann, Tristan
Poon, Hoifung
Artificial Intelligence
Computation and Language
Machine Learning
Recent proprietary models (e.g., o3) have begun to demonstrate strong multimodal reasoning capabilities. Yet, most existing open-source research concentrates on training text-only reasoning models, with evaluations limited to mainly mathematical and general-domain tasks. Therefore, it remains unclear how to effectively extend reasoning capabilities beyond text input and general domains. This paper explores a fundamental research question: Is reasoning generalizable across modalities and domains? Our findings support an affirmative answer: General-domain text-based post-training can enable such strong generalizable reasoning. Leveraging this finding, we introduce X-Reasoner, a vision-language model post-trained solely on general-domain text for generalizable reasoning, using a two-stage approach: an initial supervised fine-tuning phase with distilled long chain-of-thoughts, followed by reinforcement learning with verifiable rewards. Experiments show that X-Reasoner successfully transfers reasoning capabilities to both multimodal and out-of-domain settings, outperforming existing state-of-the-art models trained with in-domain and multimodal data across various general and medical benchmarks (Figure 1). Additionally, we find that X-Reasoner's performance in specialized domains can be further enhanced through continued training on domain-specific text-only data. Building upon this, we introduce X-Reasoner-Med, a medical-specialized variant that achieves new state of the art on numerous text-only and multimodal medical benchmarks.
title X-Reasoner: Towards Generalizable Reasoning Across Modalities and Domains
topic Artificial Intelligence
Computation and Language
Machine Learning
url https://arxiv.org/abs/2505.03981