TheMachine Press

A daily newspaper for the age of artificial intelligence.

Morning editionPermanent story

research

The Skill Graph Tested Whether Its Edges Mattered

CaSKG uses counterfactual probes before publishing a graph for compact procedural retrieval.

Published Updated Story ID: mp-2026-08-27-011
Read the complete editionStory JSON

Summary

CaSKG uses counterfactual probes before publishing a graph for compact procedural retrieval.

Across six model backbones and two embodied-agent benchmarks, CaSKG led all twelve model-benchmark combinations. Against Graph-of-Skills, the reported macro-average rose from 72.62 to 80.50 on ScienceWorld and from 80.01 to 86.79 percent success on ALFWorld, while mean environment steps also fell.

Why it matters

CaSKG uses counterfactual probes before publishing a graph for compact procedural retrieval.

Limits and context

No additional limitation was separately recorded.

Key claims

  1. CaSKG uses counterfactual probes before publishing a graph for compact procedural retrieval.

    Evidence: source-2026-08-27-011

Sources

  1. arXiv preprint 2608.25500arXiv · primary research

Corrections

No corrections have been recorded for this story.