Customer-obsessed science
Research areas
-
November 16, 202611 min readNew open-source tool turns existing test suites into sets of formal-verification tasks, which catch buggy solutions that tests alone would miss.
-
November 11, 20265 min read
-
-
-
Featured news
-
ICDM 20262026Analytical pipelines that aggregate measurements from multiple independent data sources are vulnerable to a class of corruption we term Structurally Valid Data Corruption (SVDC): every individual record passes schema, range, and type validation, yet distributional properties of the dataset deviate from ground truth. Through grounded-theory analysis of 58 quality incidents observed across experimental monitoring
-
NeurIPS 2026 Workshop on Who Verifies the Agents? Toward Reliable Agent Development (Verify-Agents)2026Training agents with reinforcement learning requires a gym, comprising a task, an executable environment in which the task can be attempted, and a verifier that reliably distinguishes success from failure. Constructing such gyms remains manual, expensive, and static. Task sets saturate as models improve and are increasingly exposed to contamination. Synthetic generation offers scale, but single-pass synthesis
-
NeurIPS 2026 Workshop on Trust-AI-Eval: Can We Trust AI Evaluation? (TAE)2026Large language models (LLMs) are increasingly used as classifiers, yet they operate as opaque systems whose decisions are difficult to interpret, which complicates their use in regulated domains such as credit scoring or medical diagnosis. We propose an evolutionary framework that iteratively discovers natural language feature definitions (rubrics) for interpretable classification. An LLM generates candidate
-
ISSTA 20262026Cloud infrastructure is managed through a mix of interfaces—traditionally, cloud consoles, command-line interfaces (CLI), and SDKs are the tools of choice. Recently, Infrastructure-as-Code/IaC frameworks (e.g., Terraform) have quickly gained popularity. Unlike conventional tools, IaC frameworks encode the infrastructure in a “source-of-truth” configuration. They are capable of automatically carrying out
-
2026Large language model agents rely on effective model context to obtain task-relevant information for decision-making. Many existing context engineering approaches primarily rely on the context generated from the past experience and retrieval mechanisms that reuse these context. However, retrieved context from past tasks must be adapted by the execution agent to fit new situations, placing additional reasoning
Collaborations
View allWhether you're a faculty member or student, there are number of ways you can engage with Amazon.
View all