collaborators

11 papers

cs.SE2026

Fantastic Adaptive Taxonomies and How to Use Them

Mert Cemri, Andrei Cojocaru, Melissa Pan +9

An agent system's execution traces record how it fails, and procedures that improve such a system without changing model weights (trajectory selection, prompt and workflow optimiza…

cs.CY2026

Measuring Agents in Production

Melissa Z. Pan, Negar Arabzadeh, Riccardo Cogo +22

LLM-based agents already operate in production across many industries, yet we lack an understanding of what technical methods make deployments successful. We present the first syst…

cs.SE2026

BenchEvolver: Frontier Task Synthesis via Solution-Centric Evolution

Yangzhen Wu, Aaron J. Li, Wenjie Ma +10

The rapid progress of frontier large language models has led to widespread benchmark saturation, limiting the ability of existing datasets to differentiate model capabilities or pr…

cs.DB2026

The Time is Here for Just-in-Time Systems: Challenges and Opportunities

Shu Liu, Alexander Krentsel, Shubham Agarwal +8

Core systems like key-value stores have historically taken years to build, and are designed to be general so as to amortize cost across deployments, paying a significant performanc…

cs.AI2026

Inductive Deductive Synthesis: Enabling AI to Generate Formally Verified Systems

Shubham Agarwal, Alexander Krentsel, Shu Liu +10

AI agents increasingly excel at generating, testing, and refining code. However, they fall short on tasks requiring formal guarantees of full coverage that testing alone cannot pro…

cs.NE2026

AdaEvolve: Adaptive LLM Driven Zeroth-Order Optimization

Mert Cemri, Shubham Agrawal, Akshat Gupta +9

The paradigm of automated program generation is shifting from one-shot generation to inference-time search, where Large Language Models (LLMs) function as semantic mutation operato…