# ACE: A Self-Correcting Agentic Canvas Editor for Multi-Slide Presentation Automation

arXiv: https://arxiv.org/abs/2608.24103 · HTML: https://mlsanity.com/paper/2608.24103/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 9 of its 18 references that are in the map.
- First posted on arXiv 25 Aug 2026.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 9 of 9)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides](https://mlsanity.com/paper/2501.03936/) (2025)
- [AutoPresent: Designing Structured Visuals from Scratch](https://mlsanity.com/paper/2501.00912/) (2025)
- [SlideCoder: Layout-aware RAG-enhanced Hierarchical Slide Generation from Design](https://mlsanity.com/paper/2506.07964/) (2025)
- [VASCAR: Content-Aware Layout Generation via Visual-Aware Self-Correction](https://mlsanity.com/paper/2412.04237/) (2024)
- [Talk to Your Slides: High-Efficiency Slide Editing via Language-Driven Structured Data Manipulation](https://mlsanity.com/paper/2505.11604/) (2025)
- [AeSlides: Incentivizing Aesthetic Layout in LLM-Based Slide Generation via Verifiable Rewards](https://mlsanity.com/paper/2604.22840/) (2026)
- [Revision Matters: Generative Design Guided by Revision Edits](https://mlsanity.com/paper/2406.18559/) (2024)

## Abstract (arXiv)

Commercial design platforms increasingly edit documents through large language model (LLM) agents, but two practical problems block reliable deployment: legacy document formats expose only flat, absolutely positioned elements, so agents must recompute coordinates and routinely break layouts; and design has no unique ground truth, so diff-against-reference metrics penalize valid-but-different outputs. We present ACE, an agentic canvas editor over a hierarchical scene-graph with a presentation-specialized action space (98 tools), paired with CARE, a content-aware router that feeds the agent only the relevant slice of each deck (avg. ~89% input-token reduction), and a self-correction loop driven by a ground-truth-free instruction-following (IF) judge whose natural-language critique is fed back as the next-turn instruction. With a fixed backbone, a scene-graph editor in a single turn already matches a same-backbone agentic HTML pipeline that iterates internally; adding self-correction lifts ACE significantly above it on instruction following (IF 4.23 vs. 3.81 on the full 94-task benchmark, paired p=.010, replicated by an out-of-loop judge) at 1.75× the speed and ~44% lower cost. VQ means are statistically indistinguishable, but 26 blind raters prefer ACE overall (58.7% decisive win-rate) and prefer the self-corrected output 81% of the time; the ranking is invariant across three judge families, and out-of-loop judges retain two-thirds of the self-correction gain, bounding circularity. 66% of cases halt after one pass, and a strict-peak rollback removes every observed regression.