<!-- mobian-agent-page publisher="dailydev" canonical="https://daily.dev/posts/tivkppigh" -->

---
title: New Alibaba AI framework skips loading every tool,...
description: Alibaba researchers developed SkillWeaver, a framework for compositional skill routing in AI agents that dramatically reduces token consumption. Instead of...
canonical: https://daily.dev/posts/tivkppigh
twitter:card: summary_large_image
twitter:site: @dailydotdev
og:type: website
og:site_name: daily.dev
og:title: New Alibaba AI framework skips loading every tool, cutting agent token use 99% | daily.dev
og:description: Alibaba researchers developed SkillWeaver, a framework for compositional skill routing in AI agents that dramatically reduces token consumption. Instead of...
og:url: https://daily.dev/posts/tivkppigh
og:image: https://api.daily.dev/og/posts/tiVKPPigh.png
og:image:alt: Post cover image
og:image:width: 1200
og:image:height: 630
og:locale: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# New Alibaba AI framework skips loading every tool, cutting agent token use 99%

**[Jacob B. Bonde](https://daily.dev/sources/5cqvizkr5tdfdotvdjulg)** · [@byteoutlaw](https://daily.dev/byteoutlaw) · 2 upvotes · 1 comments

## Summary

Alibaba researchers developed SkillWeaver, a framework for compositional skill routing in AI agents that dramatically reduces token consumption. Instead of loading an entire tool library into context, SkillWeaver uses a three-stage Decompose-Retrieve-Compose pipeline. The key innovation is Skill-Aware Decomposition (SAD), a feedback loop that feeds retrieved tool hints back to the LLM so it rewrites its task breakdown using vocabulary aligned with actual available tools. Benchmarked on 300 multi-step queries against 2,209 real-world MCP skills, SkillWeaver reduced token usage from ~884,000 to ~1,160 per query (99.9% reduction) while significantly improving accuracy. Notably, larger models without SAD performed worse than smaller ones due to over-decomposition, and the traditional ReAct baseline achieved 0% decomposition accuracy. Source code is not yet released, but the SAD technique can be reproduced using LangChain, LlamaIndex, or raw Python with prompt templates from the paper.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://venturebeat.com/orchestration/new-alibaba-ai-framework-skips-loading-every-tool-cutting-agent-token-use-99>

## Community discussion

Top comments from developers on daily.dev.

**@byteoutlaw** · 0 upvotes

> Wow honestly if correct, we just jumped another step into the foreseen future of agentic AI

## Similar posts on daily.dev

- [Don’t just attend KubeCon \+ CloudNativeCon, Merge Forward your experience\!](https://daily.dev/posts/don-t-just-attend-kubecon-cloudnativecon-merge-forward-your-experience--l0rpp73x8) · CNCF · 1 upvotes · 0 comments
- [Announcing H2 2026 KCDs](https://daily.dev/posts/announcing-h2-2026-kcds-m96goajm1) · CNCF · 1 upvotes · 0 comments
- [Two months of Open Community Groups](https://daily.dev/posts/two-months-of-open-community-groups-asf52zhbs) · CNCF · 0 upvotes · 0 comments
- [CNCF Unveils Schedule for KubeCon \+ CloudNativeCon Europe 2026](https://daily.dev/posts/cncf-unveils-schedule-for-kubecon-cloudnativecon-europe-2026-ikhcoa5cb) · CNCF · 2 upvotes · 0 comments
- [CNCF Debuts KubeCon \+ CloudNativeCon Japan 2026 Schedule](https://daily.dev/posts/cncf-debuts-kubecon-cloudnativecon-japan-2026-schedule-xp5pyudub) · CNCF · 1 upvotes · 0 comments

---

Tags: [#llm](https://daily.dev/tags/llm), [#ai-agents](https://daily.dev/tags/ai-agents), [#mcp](https://daily.dev/tags/mcp), [#rag](https://daily.dev/tags/rag)

[View this post on daily.dev](https://daily.dev/posts/tivkppigh)

```json
{"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]}
{"@context":"https://schema.org","@type":"DiscussionForumPosting","mainEntityOfPage":"https://daily.dev/posts/tivkppigh","headline":"New Alibaba AI framework skips loading every tool, cutting agent token use 99%","text":"Shared: New Alibaba AI framework skips loading every tool, cutting agent token use 99%","url":"https://daily.dev/posts/tivkppigh","datePublished":"2026-07-03T08:30:56.317Z","dateModified":"2026-07-03T08:32:04.300Z","author":{"@type":"Person","name":"Jacob B. Bonde","url":"https://daily.dev/byteoutlaw","image":"https://media.daily.dev/image/upload/s--veTChHK7--/f_auto/v1733220070/avatars/avatar_5cQvIZKr5tDFDotVDjulg","description":"I am about to change this world with my fellow programmers! 😊❤️","interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"EndorseAction"},"userInteractionCount":22545}},"image":"https://media.daily.dev/image/upload/s--qPvKM23u--/f_auto/v1722860399/public/Placeholder%2009","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":2},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":1}],"sharedContent":{"@type":"WebPage","url":"https://api.daily.dev/r/CJnltsGkq"},"comment":[{"@type":"Comment","text":"Wow honestly if correct, we just jumped another step into the foreseen future of agentic AI","datePublished":"2026-07-03T08:39:03.367Z","url":"https://daily.dev/posts/tiVKPPigh#c-s6xAa48fM","author":{"@type":"Person","name":"Jacob B. Bonde","url":"https://daily.dev/byteoutlaw","image":"https://media.daily.dev/image/upload/s--veTChHK7--/f_auto/v1733220070/avatars/avatar_5cQvIZKr5tDFDotVDjulg"}}],"isPartOf":{"@type":"WebPage","url":"https://daily.dev/sources/5cqvizkr5tdfdotvdjulg","name":"Jacob B. Bonde"}}
{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Jacob B. Bonde","item":"https://daily.dev/sources/5cqvizkr5tdfdotvdjulg"},{"@type":"ListItem","position":3,"name":"New Alibaba AI framework skips loading every tool, cutting agent token use 99%"}]}
```

