AI Paper Atlas

Research map / Vision-language and multimodal / Robot action and navigation

Decompose and Recompose: Reasoning New Skills from Existing Abilities for Cross-Task Robotic Manipulation

Xitie Zhang, Aming WU, Yahong Han

ICML 2026 · Vision-language and multimodal › Robot action and navigation · approach: Memory and subgoal-based manipulation · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add dynamic demonstrations library (visual-semantic and skill-sequence retrieval) (ablation)random-demo baseline · AGNOSTOS (ablation)overall success rate (%): 21.6 -> 23.3Improved
add coverage-aware demonstrations library (ablation)BS + DDL · AGNOSTOS (ablation)overall success rate (%): 23.3 -> 24.9Improved
add skill-augmented in-context learning (ablation)BS + DDL + CDL · AGNOSTOS (ablation)overall success rate (%): 24.9 -> 26.4Improved
use DINOv3 instead of CLIP visual encoder (ablation)Decompose and Recompose · AGNOSTOS (ablation)overall success rate (%): 24.8 -> 26.4Improved
use DINOv3 instead of DINOv2 visual encoder (ablation)Decompose and Recompose · AGNOSTOS (ablation)overall success rate (%): 25.7 -> 26.4Improved
use Qwen2.5-7B instead of Llama3.0-8B as LLM (ablation)Decompose and Recompose · AGNOSTOS (ablation)overall success rate (%): 22.4 -> 26.4Improved
use Qwen2.5-7B instead of Ministral-8B as LLM (ablation)Decompose and Recompose · AGNOSTOS (ablation)overall success rate (%): 20.2 -> 26.4Improved
use Qwen2.5-7B instead of InternLM3-8B as LLM (ablation)Decompose and Recompose · AGNOSTOS (ablation)overall success rate (%): 24.1 -> 26.4Improved
increase in-context demonstrations from 5 to 20 (ablation)Decompose and Recompose · AGNOSTOS (ablation)overall success rate (%): 19.8 -> 26.4Improved
provide in-context demonstrations (0 vs 5) (ablation)Decompose and Recompose · AGNOSTOS (ablation)overall success rate (%): 0.0 -> 19.8Improved
increase coverage-aware demonstrations from 0 to 3 (ablation)Decompose and Recompose · AGNOSTOS (ablation)overall success rate (%): 24.9 -> 26.4Improved
increase coverage-aware demonstrations from 3 to 4 (ablation)Decompose and Recompose · AGNOSTOS (ablation)overall success rate (%): 26.4 -> 26.1Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy