Search papers, labs, and topics across Lattice.
2
0
6
0
ModularRSI is proposed, a benchmark-disjoint, contrastive, and modular framework for generalizable harness evolution that contrasts successful and failed trajectories for the same task and aggregates evidence across tasks to identify recurring behavioral deficiencies.
Aegis, trained with CyberFactory, outperforms existing models by 22.8 points in cybersecurity tasks, showcasing the power of agentic learning from real-world vulnerabilities.
