---
title: "Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2608.05139v1"
permalink: "https://feed.astralor.com/items/itm_aefad45b7a940d1b5f2de382"
published: "2026-08-05T17:57:16.000Z"
score: 78
channel: "ai"
tags: ["OpenR1-Math","Qwen3","Skill²-Bench","Skill-Entropy RL","Skill Entropy","Long-Horizon Reasoning"]
---

# Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning

## AI commentary

> What impresses me most is that the paper doesn’t stop at observing model failures; it turns the cognitive burden of skill switching into a computable entropy and directly uses it as an RL reward. For researchers in training algorithms, this is a clean signal design. Benchmark designers will also find its difficulty-grading methodology worth considering.

## At a glance

Long-horizon reasoning requires LLMs to switch between distinct skills within a chain, yet existing benchmarks rarely assess this. This paper introduces Skill Entropy, a measure of switching difficulty, and Skill^2-Bench, a benchmark spanning 558 skills across 9 verifiable domains. Evaluations of 8 frontier and 4 open-source models reveal a clear skill-switching gap: accuracy drops on higher-entropy tasks. To address this, the authors propose Skill-Entropy RL, where the model predicts both answers and the skill used per step, with rewards combining step-level correctness and skill-entropy alignment. On Qwen3-4B-Instruct and Qwen3-1.7B, scores jump from 34.4% to 68.4% and 14.6% to 40.1% respectively, outperforming baselines. The approach also transfers to off-the-shelf datasets like OpenR1-Math, suggesting skill entropy is a reusable training signal. Code is open-sourced.

## Key points

- Introduces Skill Entropy to quantify cross-skill switching difficulty and builds Skill²-Bench covering 558 skills across 9 domains.
- Evaluates 8 frontier and 4 open-source models, revealing a skill-switching gap: accuracy drops on higher-entropy tasks.
- Proposes Skill-Entropy RL, where the model predicts both answer and skill at each step, with rewards combining correctness and skill-entropy alignment.
- Improves Skill²-Bench scores from 34.4% to 68.4% on Qwen3-4B and from 14.6% to 40.1% on Qwen3-1.7B, transferring to OpenR1-Math as well.

## Full text

Long-horizon reasoning in recent LLMs demands that the model switch between distinct skills inside a reasoning chain, such as first doing a math derivation, then using the result to plan a schedule. We call such problems cross-skill long-horizon tasks: multi-step tasks whose steps require different reasoning skills and depend on earlier outputs. Existing benchmarks often evaluate individual skills, lacking a principled way to measure how well a model switches between skills. We address this gap from both the evaluation and training sides. We introduce Skill Entropy, a measure of the difficulty of switching from one skill to another. We then propose Skill^2-Bench, a benchmark of cross-skill long-horizon tasks built over 558 skills across 9 verifiable and open-ended domains. Each task is assigned a task-level skill-entropy score and grouped into three difficulty levels. Evaluating 8 frontier and 4 open-source models on Skill^2-Bench reveals a skill-switching gap: accuracy decreases on higher-entropy tasks. We then turn skill entropy from a benchmark scale into a training signal. We propose Skill-Entropy RL, an RL framework where the model predicts not only the answer at each step but also the skill used to produce it. The reward combines step-level correctness with a skill-entropy reward that measures the alignment between the model-predicted skill sequence and the gold skill sequence. On Qwen3-4B-Instruct and Qwen3-1.7B, Skill-Entropy RL improves the Skill^2-Bench score from 34.4% to 68.4% and from 14.6% to 40.1%, respectively, outperforming competitive baselines. The same pipeline can be applied to off-the-shelf training data such as OpenR1-Math, indicating that skill entropy is a reusable training signal. Code available at: https://github.com/Gen-Verse/Skill-Entropy-RL

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_aefad45b7a940d1b5f2de382