execution-verification

Tag

Cards List
#execution-verification

Feyospace-v1: How the Cyber Mercury Seven Trained Frontier Cyber Models

Hugging Face Daily Papers · 2026-09-08 Cached

A data-centric framework with five specialized systems allows small teams to train open-weight cyber agents that achieve top-tier performance on benchmark suites like CyberGym.

0 favorites 0 likes
#execution-verification

Schema-Aware Localisation (SAL): Live Schema Grounding and Hallucination Validation for Oracle NL2SQL

arXiv cs.AI · 2026-07-28 Cached

This paper introduces Schema-Aware Localisation (SAL), a lightweight middleware that grounds LLM-generated SQL queries in live Oracle schema catalog to eliminate hallucination errors, achieving 62.6% execution-grounded truth on TPC-H questions without manual schema curation.

0 favorites 0 likes
← Back to home

Submit Feedback