Multimodal large language models (MLLMs) advance rapidly, while conventional benchmark development lags behind, delaying investigation of newly observed capability gaps. Such investigation requires an expressive task format and an on-demand construction process: information-rich charts make chart question answering (Ch...
Langxi Huang, Pingping Zhang, Lanyun Zhu et al.· 0 citations
Conversational MLLM agents are increasingly expected to assist in professional workflows, from AI research and engineering design to product management and business operations. Yet this capability remains underexplored: existing benchmarks largely focus on informal, everyday interactions and personal-life scenarios fea...
Ji-Ke Zhong, Ritwick Chaudhry, Xuan-Bai Chen et al.· 0 citations
Shared memory coordinates agents' actions, but correct records do not establish that those actions satisfy task requirements. Memory governance and failure diagnosis regulate or inspect recorded information; they do not by themselves establish whether it is sufficient to judge task duties. We define execution consisten...
Zhe Yu, Zixuan Wang, Peidong Wang et al.· 0 citations
Frontier LLM agents have been shown to be capable of solving increasingly complex tasks for which humans have measurable solutions. This begs the pertinent question of whether LLM agents can go beyond what humans have already solved. The ability to develop sophisticated strategies to tackle consequential problems becom...
Yoshinari Fujinuma, Keisuke Kamahori, Ryuto Koike et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
AI agents are increasingly being programmed to automate knowledge work over large collections of unstructured data. Such automation requires repeatability: when the underlying evidence is unchanged, the agent's categories, priorities, and counts should not shift materially between runs, even if each individual answer a...
World models are usually judged from the inside: by prediction loss, by the return a policy earns in imagination, or by how convincing their frames look. We judge one from the outside. We learn a structured, multi-agent world model of a complete ten-hero MOBA (206 units, every hero acting every tick, games of up to 6,0...
As agents continuously improve by generating and revising Skills, the process that discovers and refines those Skills becomes a learnable object in its own right. Task-Skills directly act on task execution, whereas Meta-Skills govern how agents discover and improve future Skills; their value therefore emerges through t...
Qianhan Feng, Zhongzhen Huang, Yakun Zhu et al.· 0 citations
Mobile GUI agents increasingly operate on interfaces influenced by users' histories and preferences, but their reliability across different users remains underexplored. We introduce PAIR (Personalized Application-state Instantiation and Rendering), a pipeline for constructing user-conditioned application states that en...
Recurrent neural networks typically compress information into a single vector-valued recurrent state, forcing short-term computation and long-term retention to share the same representation. Past extensions alleviate this bottleneck by increasing the memory capacity or separating timescales, but lack the combination of...
Ciaran Regan, K. Arulkumaran, L. Darlow et al.· 0 citations
Sea surface temperature (SST) forecasting depends on local temporal persistence, regional spatial dependence, and environmental conditions that evolve with the forecast date. We study how these heterogeneous conditions can be presented to a large language model (LLM) for regional multi-step forecasting without serializ...
Xiong Li, Xiaowei Zhou, Yanwei Yu et al.· 0 citations
Dietary nutrition planning plays an important role in chronic disease management and maintaining a healthy body. In applications, it must simultaneously satisfy personalized constraints and reasonable multidimensional nutritional goals. These two aspects often conflict, and user constraints evolve with feedback, result...
Miao Xie, Xiao Zhang, Yuan Wang et al.· 0 citations
Social preferences can promote cooperation in multi-agent reinforcement learning, but existing approaches often require agents to observe the rewards of their peers. In many real-world interactions, however, an agent can, as humans do, observe others'behavior and outcomes without access to their private reward signals....
M. A. Mohamed, Harshil Kotamreddy, M. M. José· 0 citations
With $2.1 million funding from Google.org, the open-source Public Transit Intelligence Hub will unify public transit monitoring, operations, and passenger communication.
Professor Sherry Turkle’s new book, “Artificial Intimacy,” offers a withering critique of chatbots and the antisocial dynamics she believes they encourage.
