ACE is a self‑correcting agentic canvas editor that operates on a hierarchical scene‑graph rather than flat document formats, enabling reliable multi‑slide presentation automation. It pairs a presentation‑specialized action space of 98 tools with CARE, a content‑aware router that reduces input tokens by about 89%, and a ground‑truth‑free instruction‑following judge that feeds natural‑language critiques back into the agent for self‑correction. In benchmarks, ACE outperforms a comparable agentic HTML pipeline on instruction following (4.23 vs. 3.81), runs 1.75× faster, costs 44% less, and is preferred by 58.7% of blind raters, with 81% favoring the self‑corrected output.
By JooYoung Jang, Taegyeong Lee, Jihyeon Park, Nojun Kwak
Research dissemination, turning a paper into a poster, a talk video, and a blog post, is still a manual last mile. Prior automation treats each artifact in isolation that each re-extract the paper from scratch, usually ship one-way renders the author cannot reopen in PowerPoint or Word, and gates quality on soft VLM-preference scores that plateau while load-bearing sections still read as empty.
arXiv:2607. 04438v1 Announce Type: cross Abstract: Research dissemination, turning a paper into a poster, a talk video, and a blog post, is still a manual last mile.
By Lingao Xiao, Yalun Dai, Yangyu Huang, Qihao Zhao, Wenshan Wu, Hugo He, Ruishuo Chen, Jin Jiang, Qianli Ma, Jiahuan Zhang, Xin Zhang, Ying Xin, Yang Ou, Yan Xia, Scarlett Li, Longbo Huang, Zhipeng Zhang, Yang He, Yap Kim Hui, Yan Lu
Professional graphic design is a long-horizon agentic task in which structured, editable artifacts emerge from many interdependent actions, yet outcomes admit no reliable programmatic oracle. We intro...
Designer‑RSI presents a continual adaptation framework that lets a frozen frontier model operate professional design software while an external procedural memory learns natural‑language design skills from user traffic. Over five rounds on 1,406 real briefs and 1,869 graded trajectories, the memory grew from 76 to 139 skills, boosting execution success from 72.7% to 99.3% and improving win rates on four design benchmarks. The study shows that widening and deepening the memory, especially together, significantly outperforms a no‑skill baseline.
By Hongyang Du, Lan Yan, Christian Flores, Asim Kadav
arXiv:2512. 03042v3 Announce Type: replace-cross Abstract: We introduce PPTArena, a benchmark for PowerPoint editing that evaluates how agents modify real slides from natural-language instructions.
By Michael Ofengenden, Yunze Man, Ziqi Pang, Liang-Yan Gui, Yu-Xiong Wang
arXiv:2607. 20499v1 Announce Type: new Abstract: Large Language Models generate plausible backend code, but a single-pass paradigm provides no guarantee of correctness or runtime reliability.
By Sai Deekshith Lekkala, Jothi Prabha Appadurai, Rohith Reddy Bellibatlu, Manpreet Singh
arXiv:2607. 11493v1 Announce Type: cross Abstract: Agentic systems increasingly improve themselves by editing skills: prompts, rubrics, plans, tool contracts, examples, validators, and traces.
By Sridhar Mahadevan
Agentic systems increasingly improve themselves by editing skills: prompts, rubrics, plans, tool contracts, examples, validators, and traces. Skill edits are not independent coordinates in a vector space: they are local repairs to structured artifacts whose effects are observed only after rollout, validation, and critique.
arXiv:2610.14224v1 Announce Type: new
Abstract: LLM agents' capabilities depend not only on their underlying models but also on their execution harnesses. Recursive self-improvement (RSI) offers a pr...
By Ruiyao Xu, Yanfei Chen, Zhongying CuiZhu, Bhavana Dalvi Mishra, Yifei Ming, Han Yu, Rujun Han, Chen-Yu Lee, Tomas Pfister
arXiv:2610.14495v1 Announce Type: new
Abstract: Explainer videos -- a worked geometry problem, why the sky is blue, how a dynasty fell -- are usually one more target for pixel video generation. We ar...
By Wei Lin
AgentHorizon is a benchmark comprising 1,373 computer‑use tasks with instruction‑trajectory pairs collected from 166 hours of human‑recorded activity across three operating systems. The benchmark uses a paired design that swaps instructions to create negative tasks, testing judges’ ability to distinguish successful trajectories from those that completed a similar but incompatible request. Eleven judges were evaluated, with GPT‑5.5 achieving the highest balanced accuracy of 80.9% on the full trajectory subset, while tool‑use benefits some models but harms others, revealing large variability in judges’ performance.
By Xing Han L\`u, Dheeraj Vattikonda, Sina Hajimiri, Fatemeh Pesaran Zadeh, Parishad BehnamGhader, Ghazwa Darwiche, Amirhossein Kazemnejad, Christopher Pal, Alexandre Drouin, Siva Reddy