arXiv:2608.24103v1 Announce Type: new
Abstract: Commercial design platforms increasingly edit documents through large language model (LLM) agents, but two practical problems block reliable deployment: legacy document formats expose only \emph{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 \textbf{ACE}, an agentic canvas editor over a \emph{hierarchical scene-graph} with a presentation-specialized action space (98 tools), paired with \textbf{CARE}, a content-aware router that feeds the agent only the relevant slice of each deck (avg.\ $\sim$89\% input-token reduction), and a \emph{self-correction} loop driven by a \emph{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 \emph{single turn} already matches a same-backbone \emph{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$\times$ the speed and $\sim$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.
Abstract: Commercial design platforms increasingly edit documents through large language model (LLM) agents, but two practical problems block reliable deployment: legacy document formats expose only \emph{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 \textbf{ACE}, an agentic canvas editor over a \emph{hierarchical scene-graph} with a presentation-specialized action space (98 tools), paired with \textbf{CARE}, a content-aware router that feeds the agent only the relevant slice of each deck (avg.\ $\sim$89\% input-token reduction), and a \emph{self-correction} loop driven by a \emph{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 \emph{single turn} already matches a same-backbone \emph{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$\times$ the speed and $\sim$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.
This article has been indexed from cs.AI updates on arXiv.org
Read the original article: