arXiv:2607. 12042v1 Announce Type: cross Abstract: Visual generation is increasingly ubiquitous in diverse domains, from text-to-image/video synthesis to multimodal interactive creation.
By Jinxiu Liu, Jianru Li, Tanqing Kuang, Xuanming Liu, Kangfu Mei, Yandong Wen, Weiyang Liu
The paper introduces Vision-as-a-Tool (VaaT), a paradigm that treats multimodal large language models as external utilities for visual reasoning, allowing text-only agents to offload visual tasks and vision-capable agents to augment perception on demand. It presents VHarness, a unified framework with five atomic actions, and evaluates it on Image-to-HTML, Image-to-SVG, and Image-to-3D generation tasks. Results show consistent improvements in visual fidelity and geometric accuracy for both text-only and multimodal coding agents.
By Haolin Yang, Wenshan Wu, Jin Jiang, Yu Cheng, Yan Xia, Ting Song, Yangyu Huang, Zhiliang Peng, Wenhui Wang, Hangbo Bao, Yuzhe Zhang, Wen-Da Wei, Tengchao Lv, Li Dong, Lei Cui, Furu Wei
Beacon is a new agentic visual reasoning model that improves multimodal large language models (MLLMs) by better deciding when to use tools and how to use them. It introduces two key concepts—Mode Adaptiveness, which ensures tools are invoked only when necessary, and Tool Effect, which measures the net benefit of tool use— and trains the model with supervised fine‑tuning and reinforcement learning that rewards necessity-aware decisions and expands capability through expert hints. Across 13 benchmarks, Beacon outperforms other open‑source models, achieving the highest average score and the largest net tool‑gain on diagnostic tests.
By Qixun Wang, Yang Shi, Letian Cheng, Zhuoran Zhang, Yan He, Yuqi Tang, Qi Zhang, Xinlei Yu, Ruizhe Chen, Tianrun Xu, Yuanxing Zhang, Pengfei Wan, Haotian Wang, Xianghua Ying
VISA (Visual Instruction Synthesis Agent) is an agentic framework that transforms multimodal instruction synthesis into a self‑evolving loop. Each cycle analyzes images to filter constraints, samples new constraint sets, generates candidate instructions, and verifies them using executable tools and large language model judges. Failed samples trigger diagnostic recovery, while accepted samples are evaluated against the target model to estimate difficulty, with all feedback written back to memory to adapt future rounds and provide reward signals for reinforcement learning.
By Min Zeng, Guanxin Tan, Libin Cen, Yawei Wen, Rui Hu, Liuyang Bian, Xiaolong Chen, Xiaoxin Chen
arXiv:2601. 20334v2 Announce Type: replace-cross Abstract: Robotic manipulation has increasingly adopted vision-language-action (VLA) models, which achieve strong performance but typically require task-specific demonstrations and fine-tuning, and often generalize poorly under domain shift.
By Brian Y. Tsui, Alan Y. Fang, Tiffany J. Hwu
The paper investigates how visual understanding and generation objectives interact within unified multimodal models (UMMs). At the representation level, each objective enriches the other, but forcing them through the same computation path can cause one to dominate; a task‑decoupled architecture mitigates this. At the task and system levels, the authors demonstrate bidirectional transfer between shared knowledge and superior performance of an end‑to‑end UMM over a planner–executor pipeline on complex tasks.
By Penghao Wu, Haiwen Diao, Weichen Fan, Lewei Lu, Dahua Lin, Ziwei Liu
ATP‑Bench proposes a new benchmark for evaluating agentic tool planning in multimodal large language models (MLLMs) that generate interleaved text-and-image responses. The benchmark contains 7,702 QA pairs, including 1,592 visual‑question‑answer pairs, across eight categories and 25 visual‑critical intents, all verified by humans. A Multi‑Agent MLLM‑as‑a‑Judge (MAM) system is introduced to assess tool‑call precision, missed opportunities, and overall response quality without relying on ground‑truth references.
By Yinuo Liu, Zi Qian, Heng Zhou, Jiahao Zhang, Yajie Zhang, Zhihang Li, Mengyu Zhou, Erchao Zhao, Xiaoxi Jiang, Guanjun Jiang
arXiv:2608.22174v1 Announce Type: new
Abstract: Unified multimodal models (UMMs) can perform both understanding and generation, raising a central question: can visual generation improve understanding...
By Yubo Zhu, Zhehan Kan, Jingyi Yang, Miaolin Chen, Jinbo Xing, Kai Zhu, Zijian Wang, Sheng Zhong, Wei Tong
arXiv:2608. 06699v1 Announce Type: new Abstract: Agentic multimodal large language models (MLLMs) extend multimodal perception and reasoning with planning, tool use, and interaction in dynamic environments.
By Zibo Shao, Baochen Xiong, Chengdong Xu, Linhui Xiao, Kaichen Li, Haoran Gong, Yan Li, Yaguang Song, Xiaoshan Yang
OmniBrain-0 is a lightweight, unified embodied agent that coordinates manipulation and navigation through a shared high‑level decision model. It integrates task understanding, planning, progress tracking, and feedback‑driven recovery, and is trained via embodied pretraining, domain‑specialized agent distillation, and multi‑teacher on‑policy distillation. The framework also introduces Rubric‑Guided Recursive Self‑Improvement, a data flywheel that refines rubrics and trajectories for continual domain‑expert updates, enabling efficient transfer and consolidation of embodied capabilities across multiple benchmarks and real‑world tasks.
By Xiaomi Embodied Intelligence Team, Yuechen Luo (University of Macau, Tsinghua University), Chong He (University of Macau, Tsinghua University), Fang Li (University of Macau, Tsinghua University), Shaoqing Xu (University of Macau, Tsinghua University), Jingkai Wang (University of Macau, Tsinghua University), Menglun Su (University of Macau, Tsinghua University), Jiaxin Liu (University of Macau, Tsinghua University), Shengyin Jiang (University of Macau, Tsinghua University), Zhiyi Lai (University of Macau, Tsinghua University), Long Chen (University of Macau, Tsinghua University), Longlong Wang (University of Macau, Tsinghua University), Liang Hu (University of Macau, Tsinghua University), Haochen Liu (University of Macau, Tsinghua University), Yuncheng Jiang (University of Macau, Tsinghua University), Hongwei Xie (University of Macau, Tsinghua University), Jieming Cui (University of Macau, Tsinghua University), Hanbing Li (University of Macau, Tsinghua University), Junjie Huang (University of Macau, Tsinghua University), Zhixiang Duan (University of Macau, Tsinghua University), Hexin Zhang (University of Macau, Tsinghua University), Weixiang Liang (University of Macau, Tsinghua University), Ying Gong (University of Macau, Tsinghua University), Yuhan Wang (University of Macau, Tsinghua University), Yong Pan (University of Macau, Tsinghua University), Pengna Li (University of Macau, Tsinghua University), Kangyi Wu (University of Macau, Tsinghua University), Ken Deng (University of Macau, Tsinghua University), Kun Ma (University of Macau, Tsinghua University), Fuxi Wen (University of Macau, Tsinghua University), Zhi-xin Yang (University of Macau, Tsinghua University), Hangjun Ye (University of Macau, Tsinghua University)
CoWorld Reasoner is an agentic framework that leverages a Video World Model (VWM) as a unified visual reasoning engine for Vision‑Language Models (VLMs). It exposes multiple visual operations through tools and skills, allowing the VLM to decide when to imagine, select an operation, generate visual content, and interpret the resulting evidence. The framework includes a VLM‑VWM Harness Co‑Evolution mechanism that jointly refines tools, skills, and execution code based on feedback, while keeping model weights fixed. Across seven benchmarks covering spatial, temporal, causal, and perceptual reasoning, CoWorld Reasoner outperforms direct VLM reasoning and improves accuracy on all benchmarks, achieving notable gains on MMSI and ERQA.
By Dongjie Cheng, Ruifeng Yuan, Ran Wei, Ning Song, Yongqi Li, Wenjie Li
Dynamic Cross-Modal Prompt Generation (DRAPE) is a prompt-learning framework designed for Multimodal Continual Instruction Tuning (MCIT). It generates continuous, instance-specific soft prompts by cross-attending textual instructions with visual patch features, rather than selecting from a fixed prompt pool. DRAPE also incorporates null‑space gradient projection to reduce forgetting and uses CLIP‑based prototype routing for task‑label‑free inference, achieving state‑of‑the‑art results on MCIT benchmarks.
By Tao Hu, Da-Wei Zhou