AI Paper Atlas

Research map / Large language models / Agents, code and math

A²Flow: Automating Agentic Workflow Generation via Self-Adaptive Abstraction Operators

Mingming Zhao, Xiaokang Wei, Yuanqi Shao, Kaiwen Zhou, Lin Yang, Siwei Rao, Junhui Zhan, Zhitang Chen

AAAI 2026 · Large language models › Agents, code and math · approach: LLMs for optimization and heuristics · 13 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 Operators Memory (ablation)A2Flow · MATH (level 5)score: 53.9 -> 58.5Improved
add case-based initial operator generation (ablation)A2Flow · MATH (level 5)score: 49.6 -> 58.5Improved
add operator clustering (ablation)A2Flow · MATH (level 5)score: 54.5 -> 58.5Improved
add deep extraction of abstract execution operators (ablation)A2Flow · MATH (level 5)score: 51.6 -> 58.5Improved
use abstract operators without initial operators or without deep extraction, versus no abstraction operators and no memory (ablation)A2Flow · MATH (level 5)score: 56.2 -> 49.6 (no initial), 51.6 (no deep extraction)Hurt
replace AFLOW predefined operators with A2Flow abstract operatorsagentic workflow search · DROPF1: 80.6 -> 85.1Improved
replace AFLOW predefined operators with A2Flow abstract operatorsagentic workflow search · MATH (level 5)solve rate: 56.2 -> 58.5Improved
replace AFLOW predefined operators with A2Flow abstract operatorsagentic workflow search · HumanEvalpass@1: 90.9 -> 92.4Mixed
replace AFLOW predefined operators with A2Flow abstract operatorsagentic workflow search · GSM8Ksolve rate: 93.5 -> 93.8Improved
use A2Flow instead of AFLOW on embodied tasksagentic workflow search · ALFWorld seensuccess rate: 17.1 -> 25.0Improved
use A2Flow instead of AFLOW on TextCraftagentic workflow search · TextCraftsuccess rate: 53.0 -> 59.0Improved
use ADAS instead of manual baselinesautomated workflow search · MBPPpass@1: IO 71.8 -> ADAS 53.4Hurt

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