Agentic memory systems give LLMs persistent memory by extracting experience into text and retrieving it at query time, but the model itself does not evolve: however many interactions it has had, it starts each query the same. Extraction errors compound, implicit cross-session patterns that no single fragment states can...
The DRAGON dataset contains 11,664 annotated question instances from six diagram QA datasets, with a 2,445-instance test set carrying human-verified evidence annotations and a standardized evaluation framework, which supports future research on models that ground their predictions in visual evidence.
Anirudh Iyengar, Tampu Ravi Kumar, Gaurav Najpande et al.· arXiv.org· 0 citations
CyberForge is a framework that synthesizes executable, repository-level security training data by injecting vulnerabilities into real C/C++ projects and holds 1034 validated vulnerabilities across 80 projects and 63 weakness categories, with edit locality similar to real CVE patches under a real-versus-real noise floor...
Amine Lbath, Manan Suri, A. Delaitre et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.