SE-GoS: Self-Evolving Graph-of-Skills for Skill Library at Scale

• URL: http://arxiv.org/abs/2609.08228v1
• Date: Tue, 08 Sep 2026 04:20:11 GMT
• Title: SE-GoS: Self-Evolving Graph-of-Skills for Skill Library at Scale
• Abstract summary: We present Self-Evolving Graph-of-Skills (SE-GoS), a training-free framework that evolves an existing GoS graph from execution traces.<n>We show that SE-GoS consistently improves task reward while reducing input tokens relative to full skill loading.
• Score: 10.571709993050748
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Modern LLM agents increasingly rely on reusable skills, yet as skill libraries scale to thousands of entries, effective retrieval becomes a bottleneck. Graph-of-Skills (GoS) addresses this challenge by exploiting dependency-aware graph structure for scalable skill retrieval, while SkillDAG further demonstrates that skill graphs can accumulate execution-backed structure online. However, these approaches leave open whether historical execution traces can be systematically distilled into a better retrieval graph that generalizes to unseen tasks. We present Self-Evolving Graph-of-Skills (SE-GoS), a training-free framework that evolves an existing GoS graph from execution traces while preserving the original retrieval pipeline. SE-GoS performs three complementary updates: topology evolution that discovers and prunes skill relationships from execution evidence, edge-weight evolution that reinforces retrieval-relevant relationships based on historical effectiveness, and description evolution that optimizes retrieval-facing skill descriptions using execution feedback. Across three LLMs on SkillsBench, SE-GoS consistently improves task reward while reducing input tokens relative to full skill loading, with gains varying across model families. In a representative setting, one evolution round improves reward from 52.4\% to 59.4\% while reducing input tokens by approximately one-third relative to full skill loading, and the resulting graph transfers to a disjoint held-out split with a 5.4-point improvement over the static GoS baseline. These results show that skill graphs can be improved from execution experience without model training, changes to the retrieval algorithm, or modifications to skill content, turning a static retrieval graph into an evolving retrieval infrastructure.

Related papers

• Procedural Graphs: Self-Evolving Execution Structures for LLM Agents [11.810729293911622]
  Procedural Graph organizes procedural knowledge into (procedure, relation, procedure) triplets for what-to-do questions.<n>At each decision step, the framework localizes the agent's active node, and a guidance model translates the surrounding subgraph into step-level situational guidance.<n>The graph is self-evolving: an LLM refiner contrasts failed trajectories with successful ones and edits the graph's topology and attributes.
  arXiv  Detail & Related papers  (2026-09-08T17:59:41Z)
• CaSKG: Counterfactual-Causal Skill Graphs for Scalable Agent Skill Retrieval [20.44841712209369]
  CaSKG is a skill graph framework that calibrates procedural relations before retrieval.<n>It achieves the highest task score in all twelve combinations of model and benchmark.
  arXiv  Detail & Related papers  (2026-08-26T08:12:41Z)
• HiSkill: Empowering LLM Agents with Hierarchical Skill Graphs [27.33052401264838]
  HiSkill is a hierarchical skill graph framework that organizes interaction trajectories into a directed graph with skill nodes, AtomicOp nodes, and typed edges.<n>It connects reusable high-level skills with executable action templates, while also capturing decomposition, temporal transition, compatibility, support, and recovery relations.<n>Experiments show that HiSkill outperforms state-of-the-art baselines while reducing inference token consumption.
  arXiv  Detail & Related papers  (2026-07-28T15:25:47Z)
• PromptDyG: Test-Time Prompt Adaptation on Dynamic Graphs [97.88691137307723]
  We propose PromptDyG, a novel framework that leverages unsupervised test-time Prompt adaptation for Dynamic Graph learning under a live-update online setting.<n>We show theoretically that this unsupervised prompt adaptation can guarantee a larger similarity margin between positive and negative pairs, facilitating more accurate dynamic predictions.
  arXiv  Detail & Related papers  (2026-06-22T06:54:02Z)
• ExpGraph: Model-Agnostic Experience Learning with Graph-Structured Memory for LLM Agents [32.42010710901808]
  Large language model (LLM) agents have shown strong capabilities in reasoning, tool use, and multi-step interaction.<n>Fine-tuning on collected experience can improve reuse, but it is inflexible when stronger or more suitable executors emerge.<n>We propose ExpGraph, a model-agnostic experience learning framework that enables frozen and replaceable LLM executors to improve through external experience reuse.
  arXiv  Detail & Related papers  (2026-05-29T01:04:41Z)
• GraphMind: From Operational Traces to Self-Evolving Workflow Automation [8.929269898719822]
  We present GraphMind, a system that constructs, executes, and evolves action-centric workflow graphs with minimal human effort.<n>The system has been deployed across four production cloud database services for incident investigation.<n>A 12-week field study confirms practical value: 97% of scored conversations yield actionable results within interactive latency.
  arXiv  Detail & Related papers  (2026-05-17T19:22:22Z)
• SkillGraph: Skill-Augmented Reinforcement Learning for Agents via Evolving Skill Graphs [70.1970574147839]
  We propose SKILLGRAPH, a framework that represents reusable skills as nodes in a directed graph.<n>SKILLGRAPH retrieves not just individual skills, but an ordered skill subgraph that can guide multi-step decision making.<n> Experiments show that SKILLGRAPH achieves state-of-the-art performance against memory-augmented RL methods.
  arXiv  Detail & Related papers  (2026-05-12T12:21:49Z)
• Graph-Anchored Knowledge Indexing for Retrieval-Augmented Generation [53.42323544075114]
  We propose GraphAnchor, a novel Graph-Anchored Knowledge Indexing approach.<n> Experiments on four multi-hop question answering benchmarks demonstrate the effectiveness of GraphAnchor.
  arXiv  Detail & Related papers  (2026-01-23T05:41:05Z)
• Semi-supervised Instruction Tuning for Large Language Models on Text-Attributed Graphs [62.544129365882014]
  We propose a novel Semi-supervised Instruction Tuning pipeline for Graph Learning, named SIT-Graph.<n> SIT-Graph is model-agnostic and can be seamlessly integrated into any graph instruction tuning method that utilizes LLMs as the predictor.<n>Extensive experiments demonstrate that when incorporated into state-of-the-art graph instruction tuning methods, SIT-Graph significantly enhances their performance on text-attributed graph benchmarks.
  arXiv  Detail & Related papers  (2026-01-19T08:10:53Z)
• TeaRAG: A Token-Efficient Agentic Retrieval-Augmented Generation Framework [62.66056331998838]
  TeaRAG is a token-efficient agentic RAG framework capable of compressing both retrieval content and reasoning steps.<n>Our reward function evaluates the knowledge sufficiency by a knowledge matching mechanism, while penalizing excessive reasoning steps.
  arXiv  Detail & Related papers  (2025-11-07T16:08:34Z)
• GRAIL:Learning to Interact with Large Knowledge Graphs for Retrieval Augmented Reasoning [13.481673780508215]
  GRAIL is a framework designed to interact with large-scale graphs for retrieval-augmented reasoning.<n>GRAIL achieves an average accuracy improvement of 21.01% and F1 improvement of 22.43% on knowledge graph question-answering datasets.
  arXiv  Detail & Related papers  (2025-08-07T15:34:41Z)
• SimTeG: A Frustratingly Simple Approach Improves Textual Graph Learning [131.04781590452308]
  We present SimTeG, a frustratingly Simple approach for Textual Graph learning. We first perform supervised parameter-efficient fine-tuning (PEFT) on a pre-trained LM on the downstream task. We then generate node embeddings using the last hidden states of finetuned LM.
  arXiv  Detail & Related papers  (2023-08-03T07:00:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.