% Key papers for GUI agent memory and trajectories (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages. @inproceedings{aaai2025_verilogcoder_11231, title = {{VerilogCoder: Autonomous Verilog Coding Agents with Graph-based Planning and Abstract Syntax Tree (AST)-based Waveform Tracing Tool}}, booktitle = {AAAI Conference on Artificial Intelligence (AAAI)}, year = {2025}, url = {https://ojs.aaai.org/index.php/AAAI/article/view/32007}, } @inproceedings{neurips2024_osworld_74211, title = {{OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2024}, url = {https://neurips.cc/virtual/2024/poster/97468}, } @inproceedings{neurips2024_on_74568, title = {{On the Effects of Data Scale on UI Control Agents}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2024}, url = {https://neurips.cc/virtual/2024/poster/97433}, } @inproceedings{cvpr2025_gui_26376, title = {{GUI-Xplore: Empowering Generalizable GUI Agents with One Exploration}}, booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2025}, url = {https://cvpr.thecvf.com/virtual/2025/poster/33390}, } @inproceedings{neurips2025_ui_75069, title = {{UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2025}, url = {https://openreview.net/forum?id=3uUmJzSSOW}, } @inproceedings{iclr2025_navigating_83262, title = {{Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents}}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2025}, url = {https://iclr.cc/virtual/2025/poster/32062}, } @inproceedings{aaai2026_agent_107835, title = {{Agent-SAMA: State-Aware Mobile Assistant}}, booktitle = {AAAI Conference on Artificial Intelligence (AAAI)}, year = {2026}, url = {https://ojs.aaai.org/index.php/AAAI/article/view/40187}, } @inproceedings{iclr2025_androidworld_83130, title = {{AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents}}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2025}, url = {https://iclr.cc/virtual/2025/poster/28677}, } @inproceedings{iclr2025_agent_83287, title = {{Agent S: An Open Agentic Framework that Uses Computers Like a Human}}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2025}, url = {https://iclr.cc/virtual/2025/poster/28525}, } @inproceedings{aaai2026_tongui_105473, title = {{TongUI: Internet-Scale Trajectories from Multimodal Web Tutorials for Generalized GUI Agents}}, booktitle = {AAAI Conference on Artificial Intelligence (AAAI)}, year = {2026}, url = {https://ojs.aaai.org/index.php/AAAI/article/view/38229}, } @inproceedings{neurips2025_mobileuse_76538, title = {{MobileUse: A Hierarchical Reflection-Driven GUI Agent for Autonomous Mobile Operation}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2025}, url = {https://openreview.net/forum?id=KR6tnkb6h4}, } @inproceedings{iclr2026_grounding_85032, title = {{Grounding Computer Use Agents on Human Demonstrations}}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2026}, url = {https://openreview.net/forum?id=9WiPZy3Kro}, } @inproceedings{cvpr2026_see_96760, title = {{See, Think, Act: Teaching Multimodal Agents to Effectively Interact with GUI by Identifying Toggles}}, booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2026}, url = {https://openaccess.thecvf.com/content/CVPR2026/html/Wu_See_Think_Act_Teaching_Multimodal_Agents_to_Effectively_Interact_with_CVPR_2026_paper.html}, } @inproceedings{icml2025_aguvis_47216, title = {{Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction}}, booktitle = {International Conference on Machine Learning (ICML)}, year = {2025}, url = {https://icml.cc/virtual/2025/poster/45371}, } @inproceedings{icml2026_windeskground_49251, title = {{WinDeskGround: A Benchmark for Robust GUI Grounding in Complex Multi-Window Desktop Environments}}, booktitle = {International Conference on Machine Learning (ICML)}, year = {2026}, url = {https://openreview.net/forum?id=0bPwAi78Iq}, } @inproceedings{icml2026_scaleenv_49631, title = {{ScaleEnv: Scaling Environment Synthesis from Scratch for Generalist Interactive Tool-Use Agent Training}}, booktitle = {International Conference on Machine Learning (ICML)}, year = {2026}, url = {https://openreview.net/forum?id=4GX4r1CYtD}, } @inproceedings{icml2026_cap_49636, title = {{CaP-X: A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation}}, booktitle = {International Conference on Machine Learning (ICML)}, year = {2026}, url = {https://openreview.net/forum?id=4JRO9plGAI}, } @inproceedings{icml2026_continual_49949, title = {{Continual GUI Agents}}, booktitle = {International Conference on Machine Learning (ICML)}, year = {2026}, url = {https://openreview.net/forum?id=7WeA5TAjHK}, } @inproceedings{icml2026_executable_50071, title = {{Executable Agentic Memory for GUI Agent}}, booktitle = {International Conference on Machine Learning (ICML)}, year = {2026}, url = {https://openreview.net/forum?id=8metOwZHjD}, } @inproceedings{icml2026_se_50149, title = {{SE-GA: Memory-Augmented Self-Evolution for GUI Agents}}, booktitle = {International Conference on Machine Learning (ICML)}, year = {2026}, url = {https://openreview.net/forum?id=9S9V5ntQJM}, }