Ant Group CaSKG: Counterfactual-Causal Graphs for Scalable Agent Skill Retrieval
antgroup · hf · 2026-08-28
Ant Group released CaSKG, which calibrates procedural skill relations via counterfactual-causal graph construction to improve compact, executable retrieval for LLM agents.
More from coding & agent
- Agent writes custom NPU kernels in Chinese to maximize low-end compute — yacineMTB · 2026-08-28
- AI Agents Fail in Companies Because Workflows Are Messy, Not Models — serpratik · 2026-08-28
- Developer Argues Agent Memory Should Rely on Schema Over Semantic Retrieval — arpit_bhayani · 2026-08-28
- Driving Gamma via Claude (MCP): Practical Configs to Avoid AI Clichés — cloudybrain07 · 2026-08-28
- Kimi Code 0.39.0 ships experimental Remote Control for accessing local web sessions remotely — KimiDevs · 2026-08-28
- Analysis confirms ExploitGym scorer rejects poisoned agents — moyix · 2026-08-28