Built on an evolutionary engine first released in 2018, STAR Fuzzer by Bright Security finds crashes, memory exhaustion and memory-safety bugs in security-critical code without a running application.
Google Research released Harness2, an Apache-2.0 framework that rewrites an agent's harness at test time. One refinement step lifted GLM-5 by 11.5 points on WorkBuddy-Bench with no weight updates.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results