AI Paper Atlas

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

Knowledge-Centric Agents for Workflow Generation in ComfyUI

Zhendong Li, Lei Sun, Ruibo Ming, He Zhang, Danda Paudel, Luc Van Gool, Jinjin Gu

ECCV 2026 · Large language models › Agents, code and math · approach: Code generation benchmarks · 1 citations (OpenAlex)

This paper tried a common change: Chain-of-thought prompting

add CoT or self-consistency prompting to GPT-5 · Own test set (30 workflows) · TaskCons (%): 34.7 (Few-Shot) vs 32.9 (CoT) vs 34.8 (CoT-SC) No clear effect

What 1,107 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

Read the paper

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
use hierarchical strategy/skeleton supervision with Qwen3-14B instead of end-to-end Qwen3-32B Q2P (ablation)knowledge-centric agent · Own test set (30 workflows)Pass (%): 56.7 -> 86.9Improved
use hierarchical strategy supervision instead of end-to-end Q2P (ablation)knowledge-centric agent · Own test set (30 workflows)VND: 148 -> 152Improved
use hierarchical strategy supervision instead of end-to-end Q2P (ablation)knowledge-centric agent · Own test set (30 workflows)NodeComp (%): 92.3 -> 96.3Improved
use knowledge-centric agent instead of ComfyAgentknowledge-centric agent · Own test set (30 workflows)Resolve (%): 29.4 -> 61.1Improved
use knowledge-centric agent instead of RAGknowledge-centric agent · Own test set (30 workflows)VND: 42 -> 152Improved
evaluate on ComfyBench subsetknowledge-centric agent · ComfyBench subsetResolve (%): 25.0 (ours) vs 25.0 (RAG)No clear effect
evaluate on FlowBenchknowledge-centric agent · FlowBenchPass (%): 46.7 -> 66.7Improved
swap LLM judge from GPT-5 to Gemini-2.5 (ablation)TaskCons evaluation · Own test set (30 workflows)TaskCons (%): 86.9 vs 85.6No clear effect
add CoT or self-consistency prompting to GPT-5 (ablation)GPT-5 baselines · Own test set (30 workflows)TaskCons (%): 34.7 (Few-Shot) vs 32.9 (CoT) vs 34.8 (CoT-SC)No clear effect
add retrieval of exemplars (RAG) to GPT-5 (ablation)GPT-5 baselines · Own test set (30 workflows)NodeComp (%): 36.7 -> 56.7Improved

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