Tootfinder

This https://arxiv.org/abs/2506.00618 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

RiOSWorld: Benchmarking the Risk of Multimodal Compter-Use Agents
With the rapid development of multimodal large language models (MLLMs), they are increasingly deployed as autonomous computer-use agents capable of accomplishing complex computer tasks. However, a pressing issue arises: Can the safety risk principles designed and aligned for general MLLMs in dialogue scenarios be effectively transferred to real-world computer-use scenarios? Existing research on evaluating the safety risks of MLLM-based computer-use agents suffers from several limitations: it ei…

RiOSWorld: Benchmarking the Risk of Multimodal Compter-Use Agents
Jingyi Yang, Shuai Shao, Dongrui Liu, Jing Shao
https://arxiv.org/abs/2506.00618 https://…

RiOSWorld: Benchmarking the Risk of Multimodal Compter-Use Agents
With the rapid development of multimodal large language models (MLLMs), they are increasingly deployed as autonomous computer-use agents capable of accomplishing complex computer tasks. However, a pressing issue arises: Can the safety risk principles designed and aligned for general MLLMs in dialogue scenarios be effectively transferred to real-world computer-use scenarios? Existing research on evaluating the safety risks of MLLM-based computer-use agents suffers from several limitations: it ei…

Hidden in Plain Sight: Probing Implicit Reasoning in Multimodal Language Models
Qianqi Yan, Hongquan Li, Shan Jiang, Yang Zhao, Xinze Guan, Ching-Chen Kuo, Xin Eric Wang
https://arxiv.org/abs/2506.00258

Hidden in Plain Sight: Probing Implicit Reasoning in Multimodal Language Models
Multimodal large language models (MLLMs) are increasingly deployed in open-ended, real-world environments where inputs are messy, underspecified, and not always trustworthy. Unlike curated benchmarks, these settings frequently involve instructions that refer to missing objects or contradictory facts, rely on ambiguous references, or request infeasible actions. In such cases, success hinges not on task execution alone, but on a model's ability to detect when something is silently wrong. This pap…