Hugging Face Trending Papers

SAGE: Stochastic Prompt Optimization via Agent-Guided Exploration

Read the original on Hugging Face Trending Papers →

Context engineering has emerged as a primary lever for improving AI systems without parameter updates. Recent work showing that textual gradients do not function as real gradients motivates treating automatic prompt optimization (APO) as black-box search.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv AI
Jul 13

SCATE: Learning to Supervise Coding Agents for Cost-Effective Test Generation

arXiv:2607. 08983v1 Announce Type: cross Abstract: While autonomous coding agents have significantly advanced automated test generation, they remain fundamentally limited by lazy generation, a phenomenon where agents prematurely terminate tasks and systematically avoid complex programmatic logic, resulting in inadequate code coverage.

By Sijia Gu, Noor Nashid, Ali Mesbah