---

1. OSWorld2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks
   arXiv.org2026-06-28alphaXiv arXiv S2
2. Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence
   arXiv.org2026-04-27alphaXiv arXiv S2
3. Multimodal Depression Detection Through Conversational Interactions with an Emotion-Aware Social Robot: Pilot Study
   JMIR Formative Research2026-04-27S2
4. Holistic Agent Leaderboard: The Missing Infrastructure for AI Agent Evaluation
   arXiv.org2025-10-13alphaXiv arXiv S2
5. Agent Learning via Early Experience
   arXiv.org2025-10-09alphaXiv arXiv S2
6. Watch and Learn: Learning to Use Computers from Online Videos
   arXiv.org2025-10-06alphaXiv arXiv S2
7. WebGuard: Building a Generalizable Guardrail for Web Agents
   arXiv.org2025-07-18alphaXiv arXiv S2
8. Mind2Web 2: Evaluating Agentic Search with Agent-as-a-Judge
   Neural Information Processing Systems2025-06-26alphaXiv arXiv S2
9. OPeRA: A Dataset of Observation, Persona, Rationale, and Action for Evaluating LLMs on Human Online Shopping Behavior Simulation
   Annual Meeting of the Association for Computational Linguistics2025-06-05alphaXiv arXiv S2
10. BioCLIP 2: Emergent Properties from Scaling Hierarchical Contrastive Learning
    Neural Information Processing Systems2025-05-29alphaXiv arXiv S2
11. RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments
    arXiv.org2025-05-28alphaXiv arXiv S2
12. ARM: Adaptive Reasoning Model
    Neural Information Processing Systems2025-05-26alphaXiv arXiv S2
13. MICE for CATs: Model-Internal Confidence Estimation for Calibrating Agents with Tools
    North American Chapter of the Association for Computational Linguistics2025-04-28alphaXiv arXiv S2
14. Completing A Systematic Review in Hours instead of Months with Interactive AI Agents
    Annual Meeting of the Association for Computational Linguistics2025-04-21alphaXiv arXiv S2
15. SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills
    arXiv.org2025-04-09alphaXiv arXiv S2
16. An Illusion of Progress? Assessing the Current State of Web Agents
    arXiv.org2025-04-02alphaXiv arXiv S2
17. Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems
    arXiv.org2025-03-31alphaXiv arXiv S2
18. Towards Understanding Graphical Perception in Large Multimodal Models
    arXiv.org2025-03-13alphaXiv arXiv S2
19. On the Trustworthiness of Generative Foundation Models: Guideline, Assessment, and Perspective
    arXiv.org2025-02-20alphaXiv arXiv S2
20. From RAG to Memory: Non-Parametric Continual Learning for Large Language Models
    International Conference on Machine Learning2025-02-20alphaXiv arXiv S2
21. Explorer: Scaling Exploration-driven Web Trajectory Synthesis for Multimodal Web Agents
    Annual Meeting of the Association for Computational Linguistics2025-02-17alphaXiv arXiv S2
22. Interpretable and Testable Vision Features via Sparse Autoencoders
    2025-02-10alphaXiv arXiv S2
23. Finer-CAM: Spotting the Difference Reveals Finer Details for Visual Explanation
    Computer Vision and Pattern Recognition2025-01-20alphaXiv arXiv S2
24. Prompt-CAM: Making Vision Transformers Interpretable for Fine-Grained Analysis
    Computer Vision and Pattern Recognition2025-01-16alphaXiv arXiv S2
25. Static Segmentation by Tracking: A Frustratingly Label-Efficient Approach to Fine-Grained Segmentation
    arXiv.org2025S2
26. Discovering Severe Adverse Reactions from Pharmacokinetic Drug-Drug Interactions through Literature Analysis and Electronic Health Record Verification
    Clinical pharmacology and therapy2024-11-25S2
27. RoboSpatial: Teaching Spatial Understanding to 2D and 3D Vision-Language Models for Robotics
    Computer Vision and Pattern Recognition2024-11-25alphaXiv arXiv S2
28. Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agents
    Trans. Mach. Learn. Res.2024-11-10alphaXiv arXiv S2
29. ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery
    arXiv.org2024-10-07alphaXiv arXiv S2
30. Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents
    International Conference on Learning Representations2024-10-07alphaXiv arXiv S2
31. Attention in Large Language Models Yields Efficient Zero-Shot Re-Rankers
    International Conference on Learning Representations2024-10-03alphaXiv arXiv S2
32. Fine-Tuning is Fine, if Calibrated
    Neural Information Processing Systems2024-09-24alphaXiv arXiv S2
33. MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark
    Annual Meeting of the Association for Computational Linguistics2024-09-04alphaXiv arXiv S2
34. VLM4Bio: A Benchmark Dataset to Evaluate Pretrained Vision-Language Models for Trait Discovery from Biological Images
    Neural Information Processing Systems2024-08-28alphaXiv arXiv S2
35. VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents
    arXiv.org2024-08-12alphaXiv arXiv S2
36. WebOlympus: An Open Platform for Web Agents on Live Websites
    Conference on Empirical Methods in Natural Language Processing2024S2
37. Language Agents: Foundations, Prospects, and Risks
    Conference on Empirical Methods in Natural Language Processing2024S2
38. Adaptive Chameleon or Stubborn Sloth: Unraveling the Behavior of Large Language Models in Knowledge Clashes
    arXiv.org2023S2
39. Towards a Robust and Generalizable Embodied Agent
    2023S2