8 papers
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…
Continual Learning Bench: Evaluating Frontier AI Systems in Real-World Stateful Environments
Parth Asawa, Christopher M. Glaze, Gabriel Orlanski +7
Continual learning, the ability of AI systems to improve through sequential experience, has attracted substantial interest, but no high-quality benchmark exists to evaluate it. We…
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…
How to Train Your Advisor: Steering Black-Box LLMs with Advisor Models
Parth Asawa, Alan Zhu, Abigail O'Neill +3
Frontier language models are deployed as black-box services, where model weights cannot be modified and customization is limited to prompting. We introduce Advisor Models, a method…
Concurrency without Model Changes: Future-based Asynchronous Function Calling for LLMs
Guangyu Feng, Huanzhi Mao, Prabal Dutta +1
Function calling, also known as tool use, is a core capability of modern LLM agents but is typically constrained by synchronous execution semantics. Under these semantics, LLM deco…
FrontierSmith: Synthesizing Open-Ended Coding Problems at Scale
Runyuan He, Qiuyang Mang, Shang Zhou +14
Many real-world coding challenges are open-ended and admit no known optimal solution. Yet, recent progress in LLM coding has focused on well-defined tasks such as feature implement…