…AI-generated summary While GUI agents have shown impressive capabilities in common computer-use tasks such as OSWorld, current benchmarks mainly focus on isolated and single-application tasks. This overlooks a critical…
…To train this capability, we use a two-stage procedure. First, we construct structure-aware perturbations of expert trajectories along longitudinal progress and lateral heading directions and supervise the model to recover…
…These consistent patterns confirm poor help-seeking is a model-level flaw, not task-specific. RL training on shaped Ask-F1 reward shows judgment is trainable: a 32B model improves both help…
…However, achieving it requires three capabilities that current systems lack: accumulating reusable procedural knowledge across projects, retaining user-specific experience across sessions, and internalizing implicit preferences that resist explicit formalization. We propose…
…Metacognition is thus essential for LLMs to be both trustworthy and capable; we conclude by highlighting open problems for progress towards this objective. View arXiv page View PDF Add to collection Community…
…No model linking this paper Cite arxiv.org/abs/2605.10376 in a model README.md to link it from this page. No dataset linking this paper Cite arxiv.org/abs/2605…
…To assess AI agents ' capability in driving this process, we present AutoResearchBench , a dedicated benchmark for autonomous scientific literature discovery . AutoResearchBench consists of two complementary task types: (1) Deep Research , which requires…
…AI-generated summary Deep search has become a crucial capability for frontier multimodal agents, enabling models to solve complex questions through active search, evidence verification, and multi-step reasoning. Despite rapid progress…
…A Multi-View Multi-Capability Retail Video Dataset for Embodied Vision-Language Models (2026) OmniHuman: A Large-scale Dataset and Benchmark for Human-Centric Video Generation (2026) LARY: A Latent Action Representation…
…EVA-A (Accuracy), capturing task completion , faithfulness, and audio-level speech fidelity ; and EVA-X (Experience), capturing conversation progression , spoken conciseness, and turn-taking timing . Both metrics apply to different agent architectures…