IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment
Current image editing software often hinges on fixed filters or expert tuning, leaving a gap between amateur users' intent and outcomes. Creations by generative models may contain artifacts, implausible details, or stylistic drift away from photorealism and offer little insight into why an edit was made. We propose IEA, a conversational Image Editing Agent that learns to operate parameterized tools in an explicit, interpretable action space. IEA is trained via a three-stage multitask pipeline: (
Record details
Published: 6 June 2026
Source: arXiv
Category: Research
Topics: Safety & alignment · Agents & autonomy
Retrieved: 14 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Aligned but Not Partner-Specific: Distinguishing How Multimodal LLM Agents Succeed in Reference Games Without Human-Like Conventions
arXiv · 6 June 2026
PACT: Self-Evolving Physical Safety Alignment for Diffusion Policies in Embodied Manipulation
arXiv · 7 June 2026
Accounting for Context: Shaping Moral Credences for Value Alignment
arXiv · 5 June 2026
GEAR-VLA: Learning Geometry-Aware Action Representations for Generalizable Robotic Manipulation
arXiv · 7 June 2026
Instrumental convergence and power-seeking
arXiv · 7 June 2026
Beyond Alignment: Value Diversity as a Collective Property in Multicultural Agent Systems
arXiv · 4 June 2026
How to cite this record
ethics.ai (6 June 2026), “IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment,” evidence record 1336, https://ethics.ai/record/1336 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.