الباحثون

Seong Joon Oh

المنشورات 2

نسخة أولية وصول مفتوح

Agent in a Bottle: Can LLM Agents Turn Their Capabilities Into Cheap, Scalable Artifacts?

Ankit Sonthalia, Haritz Puerto, Alexander Rubinstein وآخرون · 2026

Large language models (LLMs) can solve many narrow tasks, but querying them separately for millions of related instances can be prohibitively expensive. Can LLM agents autonomously create cheaper solutions for such workloads? We call this ability "bottling": the ability to turn general capabilities into task-specific s …

نسخة أولية وصول مفتوح

Form Over Content In Gradient-Based Data Attribution Methods

Sunwoo Kim, Seokwon Jung, Sohyung Kim وآخرون · 2026

Data attribution methods using gradient similarity are widely used to analyze and select training data for large language models, but what gradient similarity actually measures is debated. Some interpret it as identifying task-relevant skills, while other work reports that surface form is the main factor. We resolve th …

المؤلفون المشاركون