Generating HTML from natural-language specifications is an important application of code large language models (LLMs). Despite producing renderable pages, current models often fail to ensure functionality and visual quality during actual interaction. Existing methods typically target task-specific webpage supervision,...
Xu-Jia Wang, Yi-Xuan Liu, Shao-Han Huang et al.· 0 citations
CART turns red teaming from a one-time checklist into a continuous, adaptive, and auditable search for model and agent weaknesses, suggesting that contextual adaptation can reveal weaknesses that direct prompt replay does not exercise.
The number of agents is revealed as a new scaling dimension for multi-agent organizations to expand the frontier of general intelligence, offering a practical solution for complex tasks under hard latency constraints or time budgets.
Zhi-Hao Zhan, Ting Song, Li Dong et al.· 2 citations
This work proposes Learning to Coach (L2C), a framework that trains a dedicated LLM-as-a-Coach to extract actionable experiential knowledge from an actor model's previous trajectory, and studies two such rewards: a same-instance reward, which improves subsequent responses on the original problem, and a cross-instance r...
Guan-Heng Chen, Tian-Zhu Ye, Li Dong et al.· 0 citations
This work introduces credit-addressable reasoning, in which the semantic units exposed during inference also define where learning compares alternatives and assigns credit, and instantiates Code-CoT, which retains the diagram, represents visual relations as line-addressable executable code, and organizes reasoning into...
Jia-Ni Guo, Junjie Wang, Jie Wu et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.