1
The rapid evolution of software libraries presents a significant challenge for code generation models, which must adapt to frequent …
We introduce DRBench, a benchmark for evaluating AI agents on complex, open-ended deep research tasks in enterprise settings. Unlike …
Building reliable computer-use agents requires grounding: accurately connecting natural language instructions to the correct on-screen …
Leading language model (LM) providers like OpenAI and Anthropic allow customers to fine-tune frontier LMs for specific use cases. To …
Workflows are a fundamental component of automation in enterprise platforms, enabling the orchestration of tasks, data processing, and …
Aligning visual features with language embeddings is a key challenge in vision-language models (VLMs). The performance of such models …
Language model activations entangle concepts that mediate their behavior, making it difficult to interpret these factors, which has …
Large language model (LLM) agents for web interfaces have advanced rapidly, yet open-source systems still lag behind proprietary …
Scalable Vector Graphics (SVG) offer a powerful format for representing visual designs as interpretable code. Recent advances in …