# Adaptive Multi-Resolution Procedural Knowledge Compression for Large Language Models

arXiv: https://arxiv.org/abs/2606.12203 · HTML: https://mlsanity.com/paper/2606.12203/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 31 references that are in the map.
- First posted on arXiv 10 Jun 2026.

## Builds on (most cited first, 20 of 20)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [C-Pack: Packed Resources For General Chinese Embeddings](https://mlsanity.com/paper/2309.07597/) (2023)
- [LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression](https://mlsanity.com/paper/2310.06839/) (2023)
- [LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression](https://mlsanity.com/paper/2403.12968/) (2024)
- [ToolQA: A Dataset for LLM Question Answering with External Tools](https://mlsanity.com/paper/2306.13304/) (2023)
- [WikiHow: A Large Scale Text Summarization Dataset](https://mlsanity.com/paper/1810.09305/) (2018)
- [TheoremQA: A Theorem-driven Question Answering dataset](https://mlsanity.com/paper/2305.12524/) (2023)
- [MedCalc-Bench: Evaluating Large Language Models for Medical Calculations](https://mlsanity.com/paper/2406.12036/) (2024)
- [CHAMP: A Competition-level Dataset for Fine-Grained Analyses of LLMs' Mathematical Reasoning Capabilities](https://mlsanity.com/paper/2401.06961/) (2024)
- [Skill Retrieval Augmentation for Agentic AI](https://mlsanity.com/paper/2604.24594/) (2026)
- [SkillRet: A Large-Scale Benchmark for Skill Retrieval in LLM Agents](https://mlsanity.com/paper/2605.05726/) (2026)
- [Context Cascade Compression: Exploring the Upper Limits of Text Compression](https://mlsanity.com/paper/2511.15244/) (2025)
- [SkVM: Revisiting Language VM for Skills across Heterogenous LLMs and Harnesses](https://mlsanity.com/paper/2604.03088/) (2026)
- [HarmfulSkillBench: How Do Harmful Skills Weaponize Your Agents?](https://mlsanity.com/paper/2604.15415/) (2026)
- [ATACompressor: Adaptive Task-Aware Compression for Efficient Long-Context Processing in LLMs](https://mlsanity.com/paper/2602.03226/) (2026)
- [Red Skills or Blue Skills? A Dive Into Skills Published on ClawHub](https://mlsanity.com/paper/2604.13064/) (2026)
- [Decoupled Reasoning with Implicit Fact Tokens (DRIFT): A Dual-Model Framework for Efficient Long-Context Inference](https://mlsanity.com/paper/2602.10021/) (2026)

## Built on by (most cited first, 1 of 1)

- [SkillZip: Evaluation-Free Skill Compression for Self-Evolving Agents by Discovering Reusable Structure](https://mlsanity.com/paper/2608.11079/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are widely used to tackle complex tasks with autonomous workflows. Recently, reusable natural language skills have emerged as a popular paradigm to inject procedural knowledge into LLM applications. Since popular skills are often invoked repeatedly, placing their full text in every context significantly increases prefill cost and latency. While text compression techniques have the potential to solve this problem, most existing methods are designed to compress factual knowledge in documents instead of procedural knowledge, making them insufficient for skill compression. In this paper, we argue that an effective skill compression method should: 1) preserve logical dependencies among workflows and tool protocols, 2) enable lightweight, offline compression for frequently updated community skills, and 3) be adaptable to varying complexities across skills. To address this, we present SKIM (SKIll coMpression), an adaptive multi-resolution soft token compression framework for procedural skills. Depending on the complexity of each skill, SKIM creates different numbers of soft tokens that not only improve the efficiency of LLM inference, but also preserve the effectiveness of skill usage. Experiments indicate that SKIM compresses skills to 30 to 60 percent of their original token length while preserving task performance better than existing compression methods.We have released our code at https://github.com/bebr2/SKIM .