CaSKG: Counterfactual-Causal Skill Graphs for Scalable Agent Skill Retrieval
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 scaleCode is available at: https://github.com/ZhiyuanLi218/Caskg .
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
CLEAR: Generative Counterfactual Explanations on Graphs
Counterfactual explanations promote explainability in machine learning models by answering the question "how should an input instance be perturbed to obtain a desired predicted label?". The comparison of this instance be…
counterfactualCounterfactual ExplanationExplanation GenerationUnderstanding and evaluating computer vision models through the lens of counterfactuals
Counterfactual reasoning -- the practice of asking ``what if'' by varying inputs and observing changes in model behavior -- has become central to interpretable and fair AI. This thesis develops frameworks that use counte…
Image GenerationExecutable Counterfactuals: Improving LLMs' Causal Reasoning Through Code
Counterfactual reasoning, a hallmark of intelligence, consists of three steps: inferring latent variables from observations (abduction), constructing alternatives (interventions), and predicting their outcomes (predictio…
Reinforcement LearningLLM Explainability with Counterfactual Chains and Causal Graphs
Causal graphs provide a high-level language for making mechanisms transparent. Recent work uses Large Language Models (LLMs) to recover causal graphs of external-world processes. Instead, in this paper, we use causal gra…
Sentiment AnalysisCounterfactual Causal Inference in Natural Language with Large Language Models
Causal structure discovery methods are commonly applied to structured data where the causal variables are known and where statistical testing can be used to assess the causal relationships. By contrast, recovering a caus…
ArticlesCausal InferencecounterfactualCounterfactual Inference