SkillDAG: Self-Evolving Typed Skill Graphs for LLM Skill Selection at Scale

• URL: http://arxiv.org/abs/2606.03056v1
• Date: Tue, 02 Jun 2026 02:45:21 GMT
• Title: SkillDAG: Self-Evolving Typed Skill Graphs for LLM Skill Selection at Scale
• Abstract summary: We present SkillDAG, which models inter-skill relationships as a typed directed graph.<n>Each search returns vector matches, typed-edge neighbors, and conflict signals, and a propose-then-commit protocol lets the agent register execution-backed edges.<n>On ALFWorld and SkillsBench with MiniMax-M2.7, SkillDAG reaches 67.1% success and 27.3% reward.
• Score: 54.70985426016736
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As LLM agents adopt large skill libraries, selecting the right subset becomes a structural problem rather than a similarity-matching one: skills depend on, conflict with, specialize, or duplicate one another, a structure invisible to both full enumeration and embedding similarity. We present SkillDAG, which models inter-skill relationships as a typed directed graph and exposes it to an LLM agent as an inference-time, agent-callable structural retrieval interface, queried and evolved during execution rather than baked into a fixed retrieval pipeline: each search returns vector matches, typed-edge neighbors, and conflict signals, and a propose-then-commit protocol lets the agent register execution-backed edges so the graph accumulates structure across episodes. On ALFWorld and SkillsBench with MiniMax-M2.7, SkillDAG reaches 67.1% success and 27.3% reward, exceeding the strongest reported Graph-of-Skills baseline by +12.8 and +8.6 points; the advantage ports to gpt-5.2-codex, and intrinsic SkillsBench Ret@K rises from 65.5 to 78.2 under matched queries. These gains trace to isolable mechanisms: candidate ranking that stays robust as the pool grows 10x where a fixed seeding-diffusion pipeline degrades, and set-monotone online edits that enlarge ground-truth recall without evicting prior hits.

Related papers

• Codebook Agent: Amortized Topology Design for LLM Multi-Agent Systems [67.04448659688579]
  We develop a query-independent 16-entry codebook that ranks the top decoded candidates in a single batched forward pass.<n>With no iterative search and no message passing at test time, Codebook Agent is the most accurate method on all six benchmarks.
  arXiv  Detail & Related papers  (2026-09-02T08:10:22Z)
• 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)
• SkillConsist: Detecting Inconsistencies in Agent Skills via Bidirectional Graph Alignment [8.140228855572433]
  Agent Skill inconsistencies expose undisclosed dangerous behavior or cause wrong Skill selection.<n>Recent Agent Skill research has increasingly examined Agent SkillConsist consistency detection.<n>We present SkillConsist to address both challenges.
  arXiv  Detail & Related papers  (2026-08-07T16:04:21Z)
• Comparative Approaches to Agent Retrieval over Large Skill Libraries [0.0]
  We study two systems for this problem over a corpus of 690 skills.<n>A hybrid ranker combining lexical and dense-embedding retrieval for sparse, on-demand loading, and a typed knowledge graph encoding workflow relations.<n>On a set of 117 realistic, non-echoing queries, the hybrid ranker retrieves the correct skill within the top five in 73.5% +/- 8.0 of cases, leaving roughly a quarter of queries unserved.
  arXiv  Detail & Related papers  (2026-08-06T15:54:23Z)
• Efficient Visual Pointing for Embodied AI:Agent-Driven Data Synthesis, Cross-Block Attention, and Iterative Correction [55.11480729304395]
  We describe our PointArena 2026 solution, which achieves 77.2% overall accuracy and ranks second on the benchmark.<n>The ap proach targets three failure modes. First, agent-driven syn thesis builds large semantic and anchor-relative candidate pools.<n>Second, a determinis tic steerable-data pipeline creates a verified 10,000-sample main set, plus reserve samples, using masks, templates, and path verification.
  arXiv  Detail & Related papers  (2026-06-29T06:39:03Z)
• PersonalAI 2.0: Enhancing knowledge graph traversal/retrieval with planning mechanism for Personalized LLM Agents [53.369140518949656]
  We introduce PersonalAI 2.0 (PAI-2), a novel framework to enhance large language model (LLM) based systems through integration of external knowledge graphs (KG)<n>The proposed approach addresses key limitations of existing Retrieval-Augmented Generation (GraphRAG) methods by incorporating a dynamic, multistage query processing pipeline.<n>We show that use of graph algorithms (e.g. BeamSearch, WaterCircles) gain superior results compared to standard flatten retriever on average 6%, while enabled search plan enhancement mechanism gain 18% boost compared to disabled one by LLM-as-a-Judge across six datasets.
  arXiv  Detail & Related papers  (2026-05-13T13:06:30Z)
• 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)
• MCPShield: Content-Aware Attack Detection for LLM Agent Tool-Call Traffic [1.827510863075184]
  The Model Context Protocol (MCP) has become a widely adopted interface for agents to invoke external tools.<n> MCP is presented as an attack framework for MCP tool-call traffic that encodes each agent session as a graph.
  arXiv  Detail & Related papers  (2026-05-11T14:55:48Z)
• GraSP: Graph-Structured Skill Compositions for LLM Agents [29.818044584102456]
  Skill ecosystems for LLM agents have matured rapidly, yet recent benchmarks show that providing agents with more skills does not monotonically improve performance.<n>We propose GraSP, the first executable skill graph architecture that introduces a compilation layer between skill retrieval and execution.<n>GraSP transforms flat skill sets into typed directed acyclic graphs (DAGs) with precondition-effect edges, executes them with node-level verification, and performs locality-bounded repair through five typed operators.
  arXiv  Detail & Related papers  (2026-04-20T06:31:11Z)
• SAGE: Structure Aware Graph Expansion for Retrieval of Heterogeneous Data [47.930782177987446]
  Retrieval-augmented question answering over heterogeneous corpora requires connected evidence across text, tables, and graph nodes.<n>Standard retriever-reader pipelines use flat similarity search over independently chunked text, missing multi-hop evidence chains across modalities.<n>We propose SAGE (Structure Aware Graph Expansion) framework that constructs a chunk-level graph offline using metadata-driven similarities with percentile-based pruning.<n>We instantiate the initial retriever using hybrid dense+sparse retrieval for implicit cross-modal corpora and SPARK (Structure Aware Planning Agent for Retrieval over Knowledge Graphs) an agentic retriever for explicit schema graphs.
  arXiv  Detail & Related papers  (2026-02-18T23:57:19Z)
• 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)
• Eigen-1: Adaptive Multi-Agent Refinement with Monitor-Based RAG for Scientific Reasoning [53.45095336430027]
  We develop a unified framework that combines implicit retrieval and structured collaboration.<n>On Humanity's Last Exam (HLE) Bio/Chem Gold, our framework achieves 48.3% accuracy.<n>Results on SuperGPQA and TRQA confirm robustness across domains.
  arXiv  Detail & Related papers  (2025-09-25T14:05:55Z)
• GRIL: Knowledge Graph Retrieval-Integrated Learning with Large Language Models [59.72897499248909]
  We propose a novel graph retriever trained end-to-end with Large Language Models (LLMs)<n>Within the extracted subgraph, structural knowledge and semantic features are encoded via soft tokens and the verbalized graph, respectively, which are infused into the LLM together.<n>Our approach consistently achieves state-of-the-art performance, validating the strength of joint graph-LLM optimization for complex reasoning tasks.
  arXiv  Detail & Related papers  (2025-09-20T02:38:00Z)
• BifrostRAG: Bridging Dual Knowledge Graphs for Multi-Hop Question Answering in Construction Safety [11.079426930790458]
  Many compliance-related queries are multi-hop, requiring synthesis of information across interlinked clauses.<n>This poses a challenge for traditional retrieval-augmented generation (RAG) systems.<n>We introduce BifrostRAG: a dual-graph RAG-integrated system that explicitly models both linguistic relationships and document structure.
  arXiv  Detail & Related papers  (2025-07-18T03:39:14Z)

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.