We have 5 of 14 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
As the production of software passes into the hands of software itself, coding agents are increasingly commissioned to build agents fitted to their users'own workflows. This delegation carries a quiet assumption, that the delivered agent will faithfully serve the requirement it was built for, rather than merely appear...
A large-scale benchmark ICRL4AHT is introduced, built upon a high-throughput JAX implementation of Overcooked-V2 AHT, establishing this benchmark as a critical testbed for next-generation coordination algorithms.
This work introduces RecreationWorld, a five-platform framework built around recreation: given a running reference, an agent must discover its behavior and build a faithful implementation with no prescribed workflow, and introduces RecreationBench, comprising 250 diverse tasks across domains and platforms.
DyTrim is proposed, a principle-based dynamic pruning framework that reallocates gradient budget through class-aware pruning on labeled data and confidence-based soft pruning on unlabeled data and provides theoretical guarantees that DyTrim reduces class bias and improves generalization.
Qwen-CUA is introduced, a native computer-use agent with a 397B-A17B Qwen mixture-of-experts backbone that outperforms Qwen3.7 and remains competitive with leading proprietary systems, and scalable verifiable interaction and hybrid tool use as key directions.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
