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
-
EMNLP 2026 Workshop for Research on Agent Language Models (REALM)2026Research on coding agents mainly focuses on generation quality. Yet, safety-critical automotive software makes two additional demands. It prioritizes verification, since every change is reviewed, traced to a requirement, and checked against industry standards such as MISRA and AUTOSAR before it can be committed. It is also a narrow domain, written against layered architectures, embedded resource constraints
-
NeurIPS 2026 Workshop on the Linguistic Principles for Foundation Models (LP4FM)2026Aggregating several LLM responses to the same question can improve accuracy, but every method that does so must decide where the responses should differ. Established test-time scaling methods such as self-consistency vary only the reasoning path, resampling from a fixed input. The input modification offers several further options: the wording of the question can be rephrased, the spelling can be perturbed
-
NeurIPS 2026 Workshop on Who Verifies the Agents? Toward Reliable Agent Development (Verify-Agents)2026We changed the agent: did it actually get better? Every self-improving agent loop answers this hundreds of times, and every answer comes from a verifier. On open-ended tasks none exists, so the loop is handed a hand-written rubric or a bare LLM judge grading output from a model like itself, inviting reward hacking and shared blind spots. We make the verifier the evolving object: an inspectable expression
-
COLM 20262026Building LLMs that behave well socially, not merely correctly, requires more than producing locally helpful responses. A socially competent agent must infer users' unstated goals, respect their preferences, and adapt as the conversation unfolds. These behaviors are inherently multi-turn and social, making them hard to optimize: real interaction data is scarce, and user preferences are typically latent rather
-
Functionally equivalent or not? Graph-grounded differential surrogate execution for code equivalenceNeurIPS 2026 Workshop on AI for Verifiable Coding2026Determining whether two programs are functionally equivalent or not is central not only to code modernization, patch validation, and refactoring, but also to code-generation evaluation in general. Yet the usual signals are incomplete: tests cover only finite inputs, textual similarity confuses implementation with behavior, and unconstrained language model judgments are difficult to audit. Direct execution
Collaborations
View allWhether you're a faculty member or student, there are number of ways you can engage with Amazon.
View all