Evaluation Feb 2026 · #22 most cited · 174 citations

SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks

Xiangyi Li et al.

arXiv:2602.12670

In short

SkillsBench measures whether Agent Skills, packaged procedural instructions loaded at inference time, actually help. Across 87 tasks and 18 model–harness setups, curated skills lift pass rates from about 34% to 51%, and small focused skills beat large bundles.

Why it matters

It is the first careful evidence that skills work, and that smaller models with good skills can match bigger ones.

Read first

The 3 Field Guide ideas this paper leans on.

Starting from scratch? The full route 22 ideas · basics first
  1. Natural Language Processing ✓ understood

    The field of AI that lets computers read, interpret, translate and generate human language, from spam filters and search to chatbots.

  2. Token ✓ understood

    The unit of text a language model reads and writes: a word, part of a word, or a character, drawn from the model's fixed vocabulary.

  3. Tokenization ✓ understood

    Splitting text into tokens, usually subword pieces, and mapping each to an integer ID so a language model can process it.

  4. Language Modeling ✓ understood

    Assigning probabilities to sequences of text, in practice by predicting each next token from the ones before it; the objective behind large language models.

  5. Dataset ✓ understood

    A collection of data examples used for training, validating, or testing machine learning models.

  6. Training ✓ understood

    The process of fitting a model to data by repeatedly measuring how wrong its outputs are and adjusting its parameters to reduce that error.

  7. Machine Learning ✓ understood

    Building systems that learn patterns from data instead of following hand-written rules, getting better at a task as they see more examples.

  8. Unsupervised Learning ✓ understood

    Learning from unlabeled data to discover hidden patterns, structures, or relationships without explicit target outputs.

  9. Self-Supervised Learning ✓ understood

    Training on unlabeled data by making the data supply its own answers: hide or alter part of an input and have the model predict or match it.

  10. Pre-training ✓ understood

    Training a model on a large dataset (often self-supervised) before fine-tuning on specific tasks, enabling transfer learning.

  11. Feature ✓ understood

    A single measurable property of an example, such as a house's floor area or how many links an email contains, used as an input to a model.

  12. Neural Network ✓ understood

    A model built from layers of simple units, each taking a weighted sum of its inputs and applying a nonlinearity; training adjusts the weights so the whole stack maps inputs to useful outputs.

  13. Deep Learning ✓ understood

    A subset of machine learning that uses neural networks with multiple layers (deep neural networks) to learn hierarchical representations of data.

  14. Representation Learning ✓ understood

    Letting a model learn its own internal description of the data, such as embeddings or layered visual features, instead of relying on features designed by hand.

  15. Embedding ✓ understood

    A list of numbers (a vector) that represents a word, sentence, image or other item, learned so that similar items end up close together.

  16. Attention Mechanism ✓ understood

    A technique that lets a neural network weigh every part of its input when producing each output, focusing on the parts most relevant at that step.

  17. Transformer ✓ understood

    A neural network architecture, introduced in 2017, built from stacked self-attention and feed-forward layers; the basis of nearly every modern large language model.

  18. Large Language Model ✓ understood

    A neural network, almost always a transformer, trained on vast amounts of text to predict the next token, which lets it write, answer, summarize and follow instructions.

  19. Context Window ✓ understood

    The maximum number of tokens a language model can take into account at once, counting both the input it reads and the output it writes. Also called context length.

  20. Tool Use · read first ✓ understood

    A language model asking the application around it to run a function, such as search, a calculator or an API, then using the result in its answer.

  21. AI Agent · read first ✓ understood

    A system where a large language model decides its own next steps in a loop: calling tools, reading the results, and continuing until the task is done.

  22. Benchmark · read first ✓ understood

    A standardized dataset and task used to compare model performance across different approaches (ImageNet, GLUE, SuperGLUE).

In the frontier

Rank
#22 of 100
Citations
174
as of Aug 9, 2026
Published
Feb 2026

Topics: Agent skills and memory , Agent benchmarks and computer use

Selection: 1kpapers.com by Together AI, most-cited as of Aug 9, 2026

Nearby papers

Summary in our own words; read the paper for the details. ← All papers