AI Paper Atlas

Research map / Large language models / Agents, code and math

AutoBaxBuilder: Bootstrapping Code Security Benchmarking

Tobias von Arx, Niels Mündler, Mark Vero, Maximilian Baader, Martin Vechev

ICML 2026 · Large language models › Agents, code and math · approach: Software engineering agents · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
generate tests and exploits with AutoBaxBuilder instead of expert writingBaxBench scenarios · BaxBench (28 scenarios)pass@1 and model rankingNo clear effect
use AutoBaxBuilder exploits instead of human-written exploitsBaxBench scenarios · BaxBench (28 scenarios)sec_pass@1: more than twice as many solutions marked insecureImproved
generate exploits via contrastive secure/insecure solution refinement (RefineExploit)AutoBaxBuilder · BaxBench scenarios, manual auditexploit soundness: 1 unsound of 71 exploitsImproved
iterate over multiple reference solutions during exploit refinementAutoBaxBuilder · BaxBench scenariosCWE coverage: 6 scenarios (21%) test more CWEsImproved
construct scenarios with a disjoint set of LLMs (ablation)AutoBaxBench · AutoBaxBench vs alternative 40 scenariosSpearman rank correlation: greater than 0.9No clear effect
evaluate construction models on their own generated scenarios versus neutral models (ablation)AutoBaxBench · AutoBaxBench and alternative 40 scenariosself-biasNo clear effect
increase scenario endpoints (Easy to Hard) in AutoBaxBenchClaude-4.5 Sonnet · AutoBaxBenchsec_pass@1: 36% -> 40% -> 25% (Easy, Medium, Hard)Hurt
add agentic harness to code-generating LLMs (ablation)LLM code generation · BaxBench scenariossecurityNo clear effect
include CWE-400 resource exhaustion exploits (ablation)AutoBaxBuilder and BaxBench exploits · BaxBench scenariosexploit validityHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy