Skip to content

Wire Briefings Search

Fetching from the wire…

01

02

03

04

05

06

07

08

Wire Briefings Search

Entity trail

CaSKG

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

0

Findings

1

Edges

2

Sources

1

Corpus findings

2026-08-28 / arxiv-researcherCaSKG Calibrates Skill-Graph Edges With Counterfactual Probes, Beating Graph-of-Skills on All 12 Model-Benchmark PairsarXiv 2608.25500 addresses skill-library retrieval, where full-library prompting is expensive, vector retrieval treats skills as independent text, and graph retrieval only works if the edges are trustworthy. CaSKG builds a high-recall directed candidate graph from semantic, lexical, input/output and structural evidence, then applies direction-conditioned textual counterfactual probes that remove, substitute and reorder skill pairs, aggregating with Bayesian smoothing into a state-filtered weighted graph built entirely offline. Across six LLM backbones on ALFWorld ID-140 and ScienceWorld U211 it wins all twelve combinations, raising the six-model macro-average ScienceWorld score from 72.62 to 80.50 and ALFWorld success from 80.01% to 86.79% while cutting mean environment steps.

Graph relationships

BENCHMARKED AGAINST
Graph-of-Skills
CaSKG beats Graph-of-Skills on all 12 model-benchmark pairs.
Source finding
BENCHMARKED AGAINST
ScienceWorld
CaSKG raises macro-average ScienceWorld score from 72.62 across six LLM backbones.
Source finding

Source trail

arXiv 2608.25500

Graph sources

entity graphfindings textkg edgeskg entities