Large language models (LLMs) are increasingly used in agentic coding settings, where they can inspect files, execute commands, run tests, observe failures, and iteratively revise code. This shift raises a central evaluation question: can an agentic LLM generate an end-to-end software artifact that is both deployable and behaviorally correct under execution? Backend services provide a controlled but realistic substrate for this evaluation. Their APIs expose application-level executable semantics, and deployed behavior can be checked deterministically against an OpenAPI contract through black-box HTTP interactions. We introduce , a benchmark of 56 contract-defined backend generation tasks rewritten from real open-source applications. Given a visible specification and an OpenAPI contract, an LLM must generate a Dockerized service that is built, deployed, and evaluated only through HTTP tests. To strengthen evaluation without introducing hidden requirements, uses a test agent and a code agent to co-evolve the test oracle and reference service, where the test agent proposes specification-grounded backend tests and the code agent repairs the reference implementation. Although the best-performing model, GPT-5.5, succeeds on 55.4% of tasks under the base oracle, it succeeds on only 28.6% under the final oracle. This gap suggests that current LLMs can implement many local API behaviors, but still struggle to produce complete backend services.

Scaling generalist GUI agents is hindered by the data scalability bottleneck of expensive human demonstrations and reliance on ungrounded synthetic teacher supervision. To transcend these limitations, we propose , a framework that shifts the learning focus from mimicking high-level trajectories to learning interaction dynamics from executed transitions. Through a systematic investigation of self-supervised objectives, we identify that forward dynamics, defined as the generative prediction of future interface states, acts as the primary driver for scalability and outperforms inverse and backward objectives. leverages this insight by converting low-cost autonomous exploration into high-density generative supervision to learn a semantic transition world model from executed transitions. Experimental evaluations across a series of models demonstrate consistent gains from our approach: models utilizing Continual Pre-Training (CPT) on synthetic dynamics outperform non-CPT baselines with an average success rate improvement of 7% on offline benchmarks, which amplifies to a 16.8% gain in real-world online navigation. Furthermore, we observe that navigation performance scales with synthetic data volume. These results suggest that grounding agents in forward predictive modeling offers a promising pathway to scalable GUI automation with cross-domain adaptability and compositional generalization.

In the era of evaluating large language models (LLMs), data contamination has become an increasingly prominent concern. To address this risk, LLM benchmarking has evolved from a static to a dynamic paradigm. In this work, we conduct an in-depth analysis of existing static and dynamic benchmarks for evaluating LLMs. We first examine methods that enhance static benchmarks and identify their inherent limitations. We then highlight a critical gap—the lack of standardized criteria for evaluating dynamic benchmarks. Based on this observation, we propose a series of optimal design principles for dynamic benchmarking and analyze the limitations of existing dynamic benchmarks.This survey provides a concise yet comprehensive overview of recent advancements in data contamination research, offering valuable insights and a clear guide for future research efforts. We maintain a GitHub repository to continuously collect both static and dynamic benchmarking methods for LLMs. The repository can be found at this link.