FORGE deploys a fixed five-agent pipeline on 603 CVEs to achieve 67.8% L1+ exploitation success at $1.50 per CVE while generating detection rules whose grounding improves with deeper exploitation traces.
arXiv preprint arXiv:2510.18508 (2025), https://arxiv.org/abs/2510.18508
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CR 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Symbolicate-Enrich-Sample recovers symbols and call graphs from Windows binaries, enriches functions with LLM labels on reachability and risk, and produces a prioritized ~22K-function shortlist from 7.2M total via importance sampling.
citing papers explorer
-
FORGE: Multi-Agent Graduated Exploitation and Detection Engineering
FORGE deploys a fixed five-agent pipeline on 603 CVEs to achieve 67.8% L1+ exploitation success at $1.50 per CVE while generating detection rules whose grounding improves with deeper exploitation traces.
-
Needles at Scale: LLM-Assisted Target Selection for Windows Vulnerability Research
Symbolicate-Enrich-Sample recovers symbols and call graphs from Windows binaries, enriches functions with LLM labels on reachability and risk, and produces a prioritized ~22K-function shortlist from 7.2M total via importance sampling.