Frontier language models are increasingly deployed as agents, and how well an agent performs depends not only on its model but also on its harness: the prompts, tools, memory, and control loop through which the model acts. When an agent is applied to a new problem, a natural question is whether it can use the feedback...
Reusable skills improve multimodal agents without updating model weights, but their effectiveness depends on both the evidence presented and the procedure used to read it. We introduce ViewCraft, which jointly evolves an executable evidence interface and its reading procedure. The interface selects, transforms, and org...
Bin-Xiao Xu, Rui-Chuan An, Bocheng Zou et al.· 0 citations
EpiCon, a shared multimodal memory framework for agent collective learning without updating host model parameters, links question-level memory evolution to a persistent experience bank through two independently trained 2B models: a memory controller and a tree self-organizer.
Ziyun Zeng, Hang Hua, S. Alshammari et al.· 1 citation
Video world models require persistent scene memory to maintain consistency during long-horizon video generation. Existing spatial memories accumulate RGB observations or latent features, increasing storage requirements as generation proceeds. We introduce Honeycomb, a video world model built on HexMemory, our proposed...
J. Shi, Kai-Chen Zhou, Haoyu Chen et al.· 0 citations
This work presents a diagnostic and optimization framework grounded in a key empirical finding: the value of tokens within a CoT reasoning sequence is highly non-uniform, and this non-uniformity can be effectively characterized by token-level log probability signals.
Run-Jia Zeng, Hang Hua, Yiyang Liu et al.· arXiv.org· 1 citation
VideoArgus is introduced, a unified rubric-grounded framework covering five video generation and editing settings that achieves higher within-input Spearman and Kendall correlations with human judgments than the corresponding benchmark-specific evaluators across all five tasks.
Ziyun Zeng, Zi-Xuan Wang, Yongsheng Yu et al.· 5 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.