Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

CaSKG: Counterfactual-Causal Skill Graphs for Scalable Agent Skill Retrieval

Zhiyuan Li, Linyuan Gao, Xuechun Ding, Hongwei Chen +2 more

Published

Aug 26, 2026

Citations

0

Trust level

Low

Usefulness score

17/100 (Low)

Extraction confidence

55% (Moderate)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Aug 26, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

Tags

Simulation Env

Should you rely on this paper?

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Use this as background context only. Do not make protocol decisions from this page alone.

Best use

Background context only

Use if you need

A benchmark-and-metrics comparison anchor.

What to verify

Validate the exact study setup in the full paper before operational use.

Main weakness

This paper looks adjacent to evaluation work, but not like a strong protocol reference.

Human feedback signal
Not explicit
Not explicit in abstract metadata
Evaluation signal
Detected
Eval setup described
Usefulness for eval research
17/100
Adjacent candidate

Treat as adjacent context, not a core eval-method reference.

If you are doing eval pipeline work, start here

Human Eval Papers LLM-as-Judge Papers Pairwise Preference Papers Tool-Use Evaluation Search

Abstract

Reusable skill libraries allow large language model (LLM) agents to reuse procedural knowledge across tasks, but they also turn memory access into a challenging retrieval problem. Full-library prompting preserves coverage at high context cost, vector retrieval returns compact neighborhoods but treats skills as independent text, and graph-based retrieval can recover workflow context only when the edges that carry relevance are reliable. We propose CaSKG, a counterfactual-causal skill graph framework that calibrates procedural relations before retrieval. CaSKG first builds a high-recall directed candidate graph from semantic, lexical, input/output, and structural evidence, with repair evidence and an optional LLM judge further refining candidate scores. It then applies direction-conditioned textual counterfactual probes that remove, substitute, and reorder skill pairs, aggregates the evidence with Bayesian smoothing, and publishes a state-filtered weighted graph for task-conditioned expansion. The graph is constructed offline and used without changing 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 combinations of model and benchmark. Relative 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 further show that calibrated edges help retrieval preserve prerequisites, state-changing actions, verification routines, and final completion steps. These results position edge-confidence calibration as an effective route to compact and executable skill retrieval at scale\footnote{Code is available at: https://github.com/ZhiyuanLi218/Caskg }.

What we could verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

missing

None explicit

No explicit feedback protocol extracted.

"Reusable skill libraries allow large language model (LLM) agents to reuse procedural knowledge across tasks, but they also turn memory access into a challenging retrieval problem."

Evaluation Modes

strong

Simulation Env

Includes extracted eval setup.

"Reusable skill libraries allow large language model (LLM) agents to reuse procedural knowledge across tasks, but they also turn memory access into a challenging retrieval problem."

Quality Controls

strong

Calibration

Calibration/adjudication style controls detected.

"These results position edge-confidence calibration as an effective route to compact and executable skill retrieval at scale\footnote{Code is available at: https://github.com/ZhiyuanLi218/Caskg }."

Benchmarks / Datasets

strong

ALFWorld

Useful for quick benchmark comparison.

"Across six LLM backbones on ALFWorld ID-140 and ScienceWorld U211, CaSKG achieves the highest task score in all twelve combinations of model and benchmark."

Reported Metrics

strong

Recall, Relevance

Useful for evaluation criteria comparison.

"Full-library prompting preserves coverage at high context cost, vector retrieval returns compact neighborhoods but treats skills as independent text, and graph-based retrieval can recover workflow context only when the edges that carry relevance are reliable."

Benchmarks and datasets

ALFWorld

Reported metrics

recallrelevance
Human feedback details
Uses human feedback
No
Feedback types
None
Rater population
Not reported
Unit of annotation
Scalar
Expertise required
Coding
Evaluation details
Evaluation modes
Simulation Env
Agentic eval
None
Quality controls
Calibration
Evidence quality
Low
Use this page as
Background context only

Research brief

Metadata summary

Reusable skill libraries allow large language model (LLM) agents to reuse procedural knowledge across tasks, but they also turn memory access into a challenging retrieval problem.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key takeaways

  • Reusable skill libraries allow large language model (LLM) agents to reuse procedural knowledge across tasks, but they also turn memory access into a challenging retrieval problem.
  • Full-library prompting preserves coverage at high context cost, vector retrieval returns compact neighborhoods but treats skills as independent text, and graph-based retrieval can recover workflow context only when the edges that carry relevance are reliable.
  • We propose CaSKG, a counterfactual-causal skill graph framework that calibrates procedural relations before retrieval.

Researcher actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Validate inferred eval signals (Simulation environment) against the full paper.
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Recommended queries

Calibration

Contribution summary

  • Reusable skill libraries allow large language model (LLM) agents to reuse procedural knowledge across tasks, but they also turn memory access into a challenging retrieval problem.
  • We propose CaSKG, a counterfactual-causal skill graph framework that calibrates procedural relations before retrieval.
  • CaSKG first builds a high-recall directed candidate graph from semantic, lexical, input/output, and structural evidence, with repair evidence and an optional LLM judge further refining candidate scores.

Why it matters for eval

  • Reusable skill libraries allow large language model (LLM) agents to reuse procedural knowledge across tasks, but they also turn memory access into a challenging retrieval problem.
  • CaSKG first builds a high-recall directed candidate graph from semantic, lexical, input/output, and structural evidence, with repair evidence and an optional LLM judge further refining candidate scores.

Researcher checklist

  • Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Evaluation mode is explicit

    Detected: Simulation Env

  • Quality control reporting appears

    Detected: Calibration

  • Benchmark or dataset anchors are present

    Detected: ALFWorld

  • Metric reporting is present

    Detected: recall, relevance