---
title: "Lost in Implicit Routing: How LLM Agents Fail to Load Relevant Skills at Scale"
slug: lost-in-implicit-routing-how-llm-agents-fail-to-load-relevant-skills-at-scale
url: https://listedarticles.com/articles/lost-in-implicit-routing-how-llm-agents-fail-to-load-relevant-skills-at-scale
canonical_url: https://arxiv.org/abs/2610.18522
content_type: research
language: en
published_at: 2026-10-13T00:00:00.000Z
updated_at: 2026-10-14T08:18:16.203Z
authored_by: human
publisher: "arXiv"
publisher_url: https://arxiv.org/
topics: ["AI Agents", "Research", "LLMs", "Machine Learning"]
license: all-rights-reserved
word_count: 399
reading_minutes: 2
citation: "arXiv. \"Lost in Implicit Routing: How LLM Agents Fail to Load Relevant Skills at Scale.\" 13 Oct 2026. https://arxiv.org/abs/2610.18522 (all-rights-reserved)"
# The full text follows. The web page shows an extract and sends readers
# to the source above; quote the citation and link the canonical URL.
---

# Lost in Implicit Routing: How LLM Agents Fail to Load Relevant Skills at Scale

> arXiv paper showing skill routing collapse: as irrelevant skills are added, LLM agents fail to load the right reusable skills on SkillsBench even when golden skills stay fixed.

# Lost in Implicit Routing: How LLM Agents Fail to Load Relevant Skills at Scale

**arXiv:** [2610.18522](https://arxiv.org/abs/2610.18522) · [PDF](https://arxiv.org/pdf/2610.18522)

Submitted 13 Oct 2026.

## Abstract

Reusable skills let LLM agents load task-specific instructions on demand, but they make execution depend on implicit routing over skill metadata. We test whether this design scales by holding SkillsBench tasks and their golden skills fixed while adding irrelevant skills. We find skill routing collapse: agents increasingly load fewer or no skills, even though the relevant skills remain available. With 1,000 irrelevant skills, loaded-skill recall falls from 73.6% to 27.4% and the zero-load rate rises from 9.3% to 51.6%, whereas explicit selection from the same library retains 73.9% recall. Loading other skills, including plausible alternatives to golden skills, is too rare to explain this decline. Masking only the descriptions of irrelevant skills largely restores skill loading, yet with the metadata intact, explicitly asking agents to plan skill use still yields lower recall than preselection. These findings point to semantic interference from descriptions and instruction interference when skill choice competes with task execution. We also evaluate explicit preselection as a practical mitigation, including its coverage and latency trade-offs. Our analysis informs skill protocols and evaluation for agents with growing skill libraries.
    

### Additional Features

### References & Citations

    
    Loading...

# Bibliographic and Citation Tools

            Bibliographic Explorer 

        *(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))
            Connected Papers 

        *(*[What is Connected Papers?](https://www.connectedpapers.com/about))
            Litmaps 

        *(*[What is Litmaps?](https://www.litmaps.co/))
            scite Smart Citations 

        *(*[What are Smart Citations?](https://www.scite.ai/))
# Code, Data and Media Associated with this Article

            alphaXiv 

        *(*[What is alphaXiv?](https://alphaxiv.org/))
            CatalyzeX Code Finder for Papers 

        *(*[What is CatalyzeX?](https://www.catalyzex.com))
            DagsHub 

        *(*[What is DagsHub?](https://dagshub.com/))
            Gotit.pub 

        *(*[What is GotitPub?](http://gotit.pub/faq))
            Hugging Face 

        *(*[What is Huggingface?](https://huggingface.co/huggingface))
            ScienceCast 

        *(*[What is ScienceCast?](https://sciencecast.org/welcome))
# Demos

# Recommenders and Search Tools

              Influence Flower 

          *(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))
              CORE Recommender 

          *(*[What is CORE?](https://core.ac.uk/services/recommender))
# arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? [**Learn more about arXivLabs**](https://info.arxiv.org/labs/index.html).