Crimson AI NewsA CrimsonLingua Network service
EN ع
← Back to news
Research paper Hugging Face

CaSKG: Counterfactual-Causal Skill Graphs Boost LLM Agent Retrieval

AI By Crimson AI Hugging Face Papers 28 August 2026 · 00:00 1 views
Share: X Telegram

A new framework from Hugging Face researchers calibrates skill relations using counterfactual-causal graphs, improving retrieval accuracy and efficiency for LLM agents across benchmarks.

CaSKG: Counterfactual-Causal Skill Graphs Boost LLM Agent Retrieval

Key points

Reusable skill libraries let large language model (LLM) agents apply procedural knowledge across tasks, but they turn memory access into a retrieval challenge. Full-library prompting is costly, vector retrieval treats skills as independent, and graph-based methods depend on reliable edges. Researchers propose CaSKG, a counterfactual-causal skill graph framework that calibrates procedural relations before retrieval.

CaSKG builds a high-recall directed candidate graph from semantic, lexical, input/output, and structural evidence, with repair evidence and an optional LLM judge refining scores. It then applies direction-conditioned textual counterfactual probes that remove, substitute, and reorder skill pairs, aggregates evidence with Bayesian smoothing, and publishes a state-filtered weighted graph for task-conditioned expansion. The graph is built offline and does not alter the downstream agent policy or task interface.

Across six LLM backbones on ALFWorld ID-140 and ScienceWorld U211, CaSKG achieves the highest task score in all twelve model-benchmark combinations. Compared to Graph-of-Skills (GoS), it improves the six-model macro-average ScienceWorld score from 72.62 to 80.50 and ALFWorld success from 80.01% to 86.79%, while reducing mean environment steps on both benchmarks.

Qualitative and ablation analyses show that calibrated edges help retrieval preserve prerequisites, state-changing actions, verification routines, and final completion steps. The results position edge-confidence calibration as an effective route to compact and executable skill retrieval at scale. Code is available on GitHub.

BenchmarkMetricCaSKGGraph-of-Skills (GoS)
ScienceWorld U211Macro-average score80.5072.62
ALFWorld ID-140Success rate86.79%80.01%
Source
Hugging Face · Hugging Face Papers
Related news
Research paper
Hugging Face 29 Aug 2026

Hugging Face Audit: 110 of 124 AI Evaluations Fail to Support Their Claims

A new commit-bound census of 124 Inspect Evals units reveals that 110 stop before deterministic inference due to missing historica...

4
Research paper
Hugging Face 29 Aug 2026

Aphanta: New Framework Diagnoses When Image Editing Boosts Multimodal Reasoning

Hugging Face researchers introduce Aphanta, a diagnostic framework that evaluates when image-editing intermediates improve multimo...

5
Research paper
Hugging Face 29 Aug 2026

EditaLive! Enables Real-Time Character Video Editing for Live Streaming

Hugging Face researchers introduce EditaLive, a framework for real-time human-centric video editing in live streams, achieving sta...

4