20 results for “visual agents”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
Yuhan Wang, Shuochen Chang, Yalin Feng, Dongsheng Ma +7 more
The paper proposes EAGLE, a novel evidence-aligned multi-agent framework, demonstrating that requiring shared visual evidence among agents is crucial for achieving reliable and trustworthy consensus i…
Rui Yang, Qianhui Wu, Yuxi Chen, Hao Bai +6 more
The paper introduces OpenWebRL, an open framework that enables training visual web agents using online multi-turn Reinforcement Learning directly on live websites, achieving state-of-the-art performan…
Qiushi Han, Keya Hu, Linlu Qiu, Cathy Wu +1 more
The authors introduce VISTA, a visual harness that enables multimodal models to solve tasks in diverse interactive environments.
Xinkai Ma, Zhiqi Bai, Dingling Zhang, Pei Liu +20 more
The paper introduces TVIR, a new benchmark and multi-agent framework for deep research, to evaluate and improve the generation of factually reliable, text-visual interleaved reports.
Weijie Liang, Yuanfeng Song, Xing Chen, Caleb Chen Cao +2 more
This paper evaluates the use of rendered code as operational context for agentic coding, showing consistent reduction in prompt-token cost but limited increase in linear savings and end-to-end repair…
The paper introduces SceneBloom, a framework that generates realistic and physically valid 3D indoor scenes for training embodied agents.
VESTA introduces a novel agent framework that enhances Visual Language Models (VLMs) by equipping them with a dynamic, reusable toolkit of diagnostic and statistical tools, significantly improving aut…
Yifei Zhao, Xiangxin Zhou, Wenhao Yang, Jiaqi Tang +10 more
The paper introduces SceneActBench, a benchmark for evaluating vision-language model agents' ability to perform actions on multi-object 3D scenes.
Garvin Guo, Donglei Yu, Yu Chen, Xiang Wang +5 more
The paper argues that observed gains in multimodal agents using tools may be due to learning tool-calling patterns rather than genuine capability expansion, finding that tool access provides little co…
The paper proposes Multi-Agent Computer Use (MACU) systems, which significantly improve performance on complex, long-horizon tasks by enabling parallel execution and dynamic task decomposition compare…
Sheng-Wei Zhang, Hsi-An Chen, Yan-Ting Liou, Chih-Hsuan Chen +2 more
Manga2Animate is a multi-agent framework that generates animations from manga by decomposing the task into two intermediate representations and refining them through dual-level feedback.
Lukas Johanns, Marilin Moor, Davide Panzeri, Yu Zhou +8 more
Agentic-J is a containerized, multi-agent AI assistant designed to enable biologists to perform complex, reproducible biological microscopy image analysis by specifying tasks in natural language.
Haoqing Wang, Xiaoyi Zhang, Sicheng Fan, Zhexin Zhang +4 more
The paper introduces Hybrid Computer Use (HCU), a unified interface for general agents that combines programmatic, semantic, and visual interaction channels.
Chenming Zhu, Jingli Lin, Yilin Long, Peizhou Cao +3 more
The paper proposes Astra, an agentic framework that equips Vision-Language Models (VLMs) with the ability to perform spatial reasoning by actively generating and utilizing imagined visual evidence fro…
The paper introduces AgenticVBench, a comprehensive benchmark of 100 real-world video post-production tasks, and finds that even the best AI agents perform significantly worse than human experts on th…
Seokju Cho, Ryo Hachiuma, Abhishek Badki, Hang Su +7 more
This paper proposes SpatialClaw, a training-free framework for spatial reasoning that enables open-ended, complex 3D/4D spatial reasoning.
Wenjia Jiang, Zongyuan Cai, Yuanhang Shao, Chenru Wang +6 more
This paper introduces ManimAgent, a self-evolving multimodal agent that retains reflection experience across tasks using an Episodic Memory Bank, leading to improved performance on a code-generation t…
Hongxin Zhang, Chunru Lin, Junyan Li, Zhou Xian +2 more
This paper introduces GS-Agent, an end-to-end multi-agent framework that generates realistic, dynamic, and controllable 4D physical worlds from natural language descriptions by emulating human creatio…
EARS is a framework that improves the reliability of sub-agents in centralized multi-agent systems by enabling them to abstain from answering ambiguous or unsupported requests and provide actionable f…
Zelin Gao, Qiuyu Wang, Jiapeng Zhu, Jingye Chen +16 more
The paper introduces LingBot-World 2.0, an advanced version of a language model with unbounded interaction horizon, rapid response time, diverse interactive elements, and agentic harness integration.