mlsanityData to 14 Oct 2026

From Lexical Baselines to Agentic Retrieval-Augmented Generation: Structured Skill and Responsibility-Level Extraction with the SFIA Framework

arXiv 2609.35806 ↗First posted 19 Sep 2026cs.CL cs.AIcited by 0

On the map: Retrieval-augmented generation → Agentic RAG, agents and memory

also in 1 more
Abstract (arXiv)

Automated skill extraction underpins workforce planning, yet most systems represent skills as flat labels with no notion of the responsibility level at which a skill is practiced. The Skills Framework for the Information Age (SFIA) captures exactly this dimension, defining 147 professional skills across seven responsibility levels, but no automated LLM-based extraction targeting SFIA has been reported. We formalize the task as structured prediction of (skill, level) pairs from free text and ask three questions: how accurately can text be mapped onto SFIA's closed vocabulary, which strategies reliably predict the level alongside the skill, and do agentic designs improve on simpler retrieval and prompting? We evaluate five strategies (a lexical baseline, dense retrieval with LLM reranking, a zero-shot schema-constrained LLM, single-agent agentic RAG, and a three-agent retriever--matcher--verifier crew) against expert-mapped European ICT role profiles, all drawing on an SFIA~9 corpus built by a fully automated agentic pipeline that we release. Retrieval-based matching identifies the most skills while generative strategies are markedly more precise; only strategies assigning the level as an explicit decision predict it reliably, with similarity-based selection more than twice as inaccurate; and the crew doubles latency without improving accuracy, so added agent roles do not automatically benefit closed-taxonomy matching. These results provide the first reproducible baseline for structured, level-aware skill extraction against SFIA.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Agentic RAG, agents and memory, one of 15 directions in Retrieval-augmented generation. Builds on 29 of its 40 references that are in the map. First posted on arXiv 19 Sep 2026.

Builds on

29 of 40 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG15 Jan

Other references · 28

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  3. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  4. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  5. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
  6. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  7. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,808
  8. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
  9. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  10. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,252
  11. 2023ChatDev: Communicative Agents for Software Developmentcited by 919
  12. 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debatecited by 742
16 more
  1. 2023In-Context Retrieval-Augmented Language Modelscited by 702
  2. 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrievalcited by 532
  3. 2023Better Zero-Shot Reasoning with Role-Play Promptingcited by 223
  4. 2020Sparse, Dense, and Attentional Representations for Text Retrievalcited by 214
  5. 2024A Human-Inspired Reading Agent with Gist Memory of Very Long Contextscited by 146
  6. 2024Retrieval Augmented Generation or Long-Context LLMs? A Comprehensive Study and Hybrid Approachcited by 119
  7. 2023Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakescited by 111
  8. 2024Blended RAG: Improving RAG (Retriever-Augmented Generation) Accuracy with Semantic Search and Hybrid Query-Based Retrieverscited by 84
  9. 2021Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?cited by 60
  10. 2022SkillSpan: Hard and Soft Skill Extraction from English Job Postingscited by 43
  11. 2025AI Hiring with LLMs: A Context-Aware and Explainable Multi-Agent Framework for Resume Screeningcited by 20
  12. 2023Large Language Models as Batteries-Included Zero-Shot ESCO Skills Matcherscited by 15
  13. 2024Deep Learning-based Computational Job Market Analysis: A Survey on Skill Extraction and Classification from Job Postingscited by 14
  14. 2025Reconstructing Context: Evaluating Advanced Chunking Strategies for Retrieval-Augmented Generationcited by 13
  15. 2024Rethinking Skill Extraction in the Job Market Domain using Large Language Modelscited by 11
  16. 2025A Multi-Stage Framework with Taxonomy-Guided Reasoning for Occupation Classification Using Large Language Modelscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026SkillCorpus: Consolidating and Evaluating the Open Skill Ecosystem for Real-World LLM Agents
  2. 2026SkillRet: A Large-Scale Benchmark for Skill Retrieval in LLM Agents
  3. 2026Skill Following: Evaluating Actual Skill Use in Retrieval-Enabled LLM Agents
  4. 2026SkillSight: Calibrating Generic Content Bias for Skill Retrieval
  5. 2026Skills Know Their Neighbors: Cluster-Contrastive Capability Pages for Skill Retrieval
  6. 2026Graph-of-Skills: Dependency-Aware Structural Retrieval for Massive Agent Skills
  7. 2026LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents
  8. 2026Imagine Before Retrieval: Prospective Skill Retrieval for LLM Agents