English
Related papers

Related papers: PPTArena: A Benchmark for Agentic PowerPoint Editi…

200 papers

Leaderboard scores on public benchmarks have been steadily rising and converging, with many frontier language models now separated by only marginal differences. However, these scores often fail to match users' day to day experience, because…

Artificial Intelligence · Computer Science 2026-02-05 Yiliang Song , Hongjun An , Jiangong Xiao , Haofei Zhao , Jiawei Shao , Xuelong Li

Large language model (LLM)-based agents frequently generate seemingly coherent plans that fail upon execution due to infeasible actions, constraint violations, and compounding errors over extended horizons. PIVOT (Plan-Inspect-eVOlve…

Artificial Intelligence · Computer Science 2026-05-13 Tuo Zhang , Alin-Ionut Popa , Yan Xu , Rui Song , Dimitrios Dimitriadis

Evaluating the safety of LLM-based agents is increasingly important because risks in realistic deployments often emerge over multi-step interactions rather than isolated prompts or final responses. Existing trajectory-level benchmarks…

Artificial Intelligence · Computer Science 2026-05-14 Yu Li , Haoyu Luo , Yuejin Xie , Yuqian Fu , Zhonghao Yang , Shuai Shao , Qihan Ren , Wanying Qu , Yanwei Fu , Yujiu Yang , Jing Shao , Xia Hu , Dongrui Liu

We present SMART-Editor, a framework for compositional layout and content editing across structured (posters, websites) and unstructured (natural images) domains. Unlike prior models that perform local edits, SMART-Editor preserves global…

Computation and Language · Computer Science 2025-08-06 Ishani Mondal , Meera Bharadwaj , Ayush Roy , Aparna Garimella , Jordan Lee Boyd-Graber

While world models have emerged as a cornerstone of embodied intelligence by enabling agents to reason about environmental dynamics through action-conditioned prediction, their evaluation remains fragmented. Current evaluation of embodied…

Proactive agents that anticipate user intentions without explicit prompts represent a significant evolution in human-AI interaction, promising to reduce cognitive load and streamline workflows. However, existing datasets suffer from two…

Human-Computer Interaction · Computer Science 2026-02-11 Yuanbo Tang , Huaze Tang , Tingyu Cao , Lam Nguyen , Anping Zhang , Xinwen Cao , Chunkang Liu , Wenbo Ding , Yang Li

Fine-tuning large language models for vertical domains remains labor-intensive, requiring practitioners to curate data, configure training, and iteratively diagnose model behavior. Despite growing interest in autonomous machine learning and…

Artificial Intelligence · Computer Science 2026-05-21 Qizheng Li , Yifei Zhang , Xiao Yang , Xu Yang , Zhuo Wang , Weiqing Liu , Jiang Bian

Large language model agents now act on codebases, browsers, operating systems, calendars, files, and tool ecosystems, but their evaluations often collapse behavior into final task success. AgentAtlas reframes agent evaluation as a…

Artificial Intelligence · Computer Science 2026-05-27 Parsa Mazaheri , Kasra Mazaheri

This paper presents BPMN Assistant, a tool that leverages Large Language Models for natural language-based creation and editing of BPMN diagrams. While direct XML generation is common, it is verbose, slow, and prone to syntax errors during…

Artificial Intelligence · Computer Science 2026-01-23 Josip Tomo Licardo , Nikola Tankovic , Darko Etinger

Safe deployment of Large Language Model (LLM) agents in autonomous settings requires reliable oversight mechanisms. A central challenge is detecting scheming, where agents covertly pursue misaligned goals. One approach to mitigating such…

Computation and Language · Computer Science 2026-03-03 Simon Storf , Rich Barton-Cooper , James Peters-Gill , Marius Hobbhahn

The ability to autonomously navigate safely, especially within dynamic environments, is paramount for mobile robotics. In recent years, DRL approaches have shown superior performance in dynamic obstacle avoidance. However, these…

Modern coding scaffolds turn LLMs into capable software agents, but their ability to follow scaffold-specified instructions remains under-examined, especially when constraints are heterogeneous and persist across interactions. To fill this…

Visual content creation tasks demand a nuanced understanding of design conventions and creative workflows-capabilities challenging for general models, while workflow-based agents lack specialized knowledge for autonomous creative planning.…

Computer Vision and Pattern Recognition · Computer Science 2026-03-04 Jinxiang Lai , Zexin Lu , Jiajun He , Rongwei Quan , Wenzhe Zhao , Qinyu Yang , Qi Chen , Qin Lin , Chuyue Li , Tao Gao , Yuhao Shan , Shuai Shao , Song Guo , Qinglin Lu

Current Graphical User Interface (GUI) agents operate primarily under a reactive paradigm: a user must provide an explicit instruction for the agent to execute a task. However, an intelligent AI assistant should be proactive, which is…

Artificial Intelligence · Computer Science 2026-03-10 Yuxiang Chai , Shunye Tang , Han Xiao , Rui Liu , Hongsheng Li

Navigating the landscape of particle accelerators has become increasingly challenging with recent surges in contributions. These intricate devices challenge comprehension, even within individual facilities. To address this, we introduce…

Computation and Language · Computer Science 2023-11-28 Antonin Sulc , Raimund Kammering , Annika Eichler , Tim Wilksen

Training Vision Language Models (VLMs) for video event reasoning requires high-quality structured annotations capturing not only what happened, but when, where, why, and with what consequence, at a scale manual labelling cannot support. We…

Computer Vision and Pattern Recognition · Computer Science 2026-05-22 Han Zhang , Wanting Jiang , Tomasz Kornuta , Tian Zheng , Vidya Murali

Designing academic posters is a labor-intensive process requiring the precise balance of high-density content and sophisticated layout. While existing paper-to-poster generation methods automate initial drafting, they are typically…

Artificial Intelligence · Computer Science 2026-01-09 Chengxin Shi , Qinnan Cai , Zeyuan Chen , Long Zeng , Yibo Zhao , Jing Yu , Jianxiang Yu , Xiang Li

We present TextAtari, a benchmark for evaluating language agents on very long-horizon decision-making tasks spanning up to 100,000 steps. By translating the visual state representations of classic Atari games into rich textual descriptions,…

Computation and Language · Computer Science 2025-06-11 Wenhao Li , Wenwu Li , Chuyun Shen , Junjie Sheng , Zixiao Huang , Di Wu , Yun Hua , Wei Yin , Xiangfeng Wang , Hongyuan Zha , Bo Jin

How-to procedures, such as how to plant a garden, are now used by millions of users, but sometimes need customizing to meet a user's specific needs, e.g., planting a garden without pesticides. Our goal is to measure and improve an LLM's…

Computation and Language · Computer Science 2024-06-03 Yash Kumar Lal , Li Zhang , Faeze Brahman , Bodhisattwa Prasad Majumder , Peter Clark , Niket Tandon

Search-augmented language models combine web search with Large Language Models (LLMs) to improve response groundedness and freshness. However, analyzing these systems remains challenging: existing datasets are limited in scale and narrow in…