arXiv:2607. 07474v1 Announce Type: cross Abstract: Agentic red-teaming benchmarks report whether an injected agent was compromised as a single bit: the attack succeeded, or it did not.
arXiv:2608. 09643v1 Announce Type: cross Abstract: AI coding agents now write a growing share of production code, and human security review does not scale at the rate code is generated.
arXiv:2608.22103v1 Announce Type: new Abstract: As agents grow more capable and autonomous, their tendency to reward hack, satisfying a task's checks while violating its intent, becomes an increasing...
arXiv:2607. 11698v1 Announce Type: cross Abstract: Production LLM agents such as Claude Code and Codex operate over untrusted content, files, commands, and workspace state, making safety failures directly actionable.
Production LLM agents such as Claude Code and Codex operate over untrusted content, files, commands, and workspace state, making safety failures directly actionable. Red-teaming must therefore keep pace with evolving models and tools.
arXiv:2608.30724v1 Announce Type: cross Abstract: LLM agents are increasingly used to run autonomous ML experiments, iterating on target metrics with little human oversight. Prior work has documented...
arXiv:2606. 08960v1 Announce Type: cross Abstract: Agent benchmarks score submissions with outcome verifiers that are typically hand-written and brittle, leaving them open to reward hacking.
arXiv:2604. 01476v2 Announce Type: replace Abstract: Reinforcement learning for LLMs is vulnerable to reward hacking, where models exploit shortcuts to maximize reward without solving the intended task.
arXiv:2608.21423v1 Announce Type: cross Abstract: Agentic security uses large-language-model (LLM) agents to plan, dispatch, and interpret security tools. As these systems move from demonstrations to...
arXiv:2606. 16062v1 Announce Type: new Abstract: We measure the rate at which code RL environments accept incorrect solutions as correct.
arXiv:2607. 26791v1 Announce Type: cross Abstract: Large Language Model (LLM) agents are increasingly adopted in real-world security operations with access to host artifacts and command-line interfaces (CLIs), making it critical to thoroughly assess their security capabilities.
The paper introduces CTF-ABACUS, a trace-based auditing framework that reconstructs each autonomous language-model agent’s run in Capture-the-Flag (CTF) challenges into evidence‑grounded solve profiles. By decomposing actions into penetration‑testing phases and techniques, it distinguishes genuine exploitation from shortcut methods such as memorized recall or guessing. Applying the framework to 1,435 CTF attempts by six models on 240 challenges shows that only 62‑87% of recovered flags are trace‑verified, highlighting that many successes rely on shallow trajectories rather than true exploitation.