Frontier-Eng: Benchmarking Self-Evolving Agents on Real-World Engineering Tasks with Generative Optimization

Current LLM agent benchmarks, which predominantly focus on binary pass/fail tasks such as code generation or search-based question answering, often neglect the value of real-world engineering that is often captured through the iterative optimization of feasible designs. To this end, we introduce Frontier-Eng, a human-verified benchmark for generative optimization -- an iterative propose-execute-evaluate loop in which an agent generates candidate artifacts, receives executable verifier feedback, and revises them under a fixed interaction budget -- spanning $47$ tasks across five broad engineering categories. Unlike previous suites, Frontier-Eng tasks are grounded in industrial-grade simulators and verifiers that provide continuous reward signals and enforce hard feasibility constraints under constrained budgets. We evaluate eight frontier language models using representative search frameworks, finding that while Claude 4.6 Opus achieves the most robust performance, the benchmark remains challenging for all models. Our analysis suggests a dual power-law decay in improvement frequency ($\sim$ 1/iteration) and magnitude ($\sim$ 1/improvement count). We further show that although width improves parallelism and diversity, depth remains crucial for hard-won improvements under a fixed budget. Frontier-Eng establishes a new standard for assessing the capacity of AI agents to integrate domain knowledge with executable feedback to solve complex, open-ended engineering problems.

Test-time Scaling over Perception: Resolving the Grounding Paradox in Thinking with Images

Recent multimodal large language models (MLLMs) have begun to support Thinking with Images by invoking visual tools such as zooming and cropping during inference. Yet these systems remain brittle in fine-grained visual reasoning because they must decide where to look before they have access to the evidence needed to make that decision correctly. We identify this circular dependency as the Grounding Paradox. To address it, we propose Test-Time Scaling over Perception (TTSP), a framework that treats perception itself as a scalable inference process. TTSP generates multiple exploratory perception traces, filters unreliable traces using entropy-based confidence estimation, distills validated observations into structured knowledge, and iteratively refines subsequent exploration toward unresolved uncertainty. Extensive experiments on high-resolution and general multimodal reasoning benchmarks show that TTSP consistently outperforms strong baselines across backbone sizes, while also exhibiting favorable scalability and token efficiency. Our results suggest that scaling perception at test time is a promising direction for robust multimodal reasoning under perceptual uncertainty.