SignGAD uses self-designing agentic workflows and a guarded refit step to select task-specific graph encodings and detectors for few-shot anomaly detection.
arXiv preprint arXiv:2503.11301 , year=
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
Everywhere learning trains AI to meet pointwise loss constraints almost surely, backed by approximate duality theory for generalization and L1 regularization on relaxations.
GRADE models any LLM agent run as a graph with execution and graded dependency edge layers to enable failure prediction and fault localization across tool, coding, and web agent corpora.
The paper delivers the first systematic review of self-evolving agents, structured around what components evolve, when adaptation occurs, and how it is implemented.
citing papers explorer
-
Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection
SignGAD uses self-designing agentic workflows and a guarded refit step to select task-specific graph encodings and detectors for few-shot anomaly detection.
-
Everywhere Learning: Artificial Intelligence with Pointwise Constraints
Everywhere learning trains AI to meet pointwise loss constraints almost surely, backed by approximate duality theory for generalization and L1 regularization on relaxations.
-
GRADE: Graph Representation of LLM Agent Dependency and Execution
GRADE models any LLM agent run as a graph with execution and graded dependency edge layers to enable failure prediction and fault localization across tool, coding, and web agent corpora.
-
A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence
The paper delivers the first systematic review of self-evolving agents, structured around what components evolve, when adaptation occurs, and how it is implemented.