Agent skills turn procedural knowledge into reusable artifacts, allowing LLM agents to accumulate and refine expertise through experience. Building on this, skill evolution iteratively improves skills using execution feedback. However, improvement may require several interdependent edits, so low-reward versions can sti...
En-Ze Ma, Chun-Yu Miao, Yan-Kai Chen et al.· 1 citation
A separate survey comparison finds that selecting the more responsive checkpoint can worsen human fit; responsiveness is confounded with training status, and temperature calibration largely removes this cost but not errors in group ordering.
Yu-Fan Zhou, Yuxuan Liu, En-Ze Ma et al.· 0 citations
MEMPROBE is the first benchmark to study memory recovery directly, reconstructing the user state a system retains and scoring it against ground truth, and is seen as a step toward an environment where agents are trained to remember their users, growing more faithful the longer they know them.
En-Ze Ma, Yufan Zhou, Wei-Chieh Huang et al.· 4 citations
The results suggest that anti-sycophancy should be treated not as a simple suppression problem, but as a selectivity problem, where effective interventions should preserve Rational-Updating while reducing Unsupported-Yielding.
Huanhuan Ma, Henry Peng Zou, Cheng-Ze Li et al.· 2 citations· ⚡1
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.