Users of a deployed language model routinely encounter behaviours that testing almost never surfaces, since deployment puts the model through orders of magnitude more interactions than any evaluation...
arXiv:2608.31105v1 Announce Type: new Abstract: Users of a deployed language model routinely encounter behaviours that testing almost never surfaces, since deployment puts the model through orders of...
arXiv:2610.07186v1 Announce Type: new Abstract: Large language models make claims about themselves that are both consequential and increasingly difficult to verify from behavior alone. How can we dis...
arXiv:2608. 13840v1 Announce Type: cross Abstract: Audits of generative AI (GenAI) systems often summarize behavior as a reported rate: how often the audited system complies with policy.
arXiv:2606. 29713v1 Announce Type: cross Abstract: Hallucination is the reliability bottleneck for LLM-based agents, and fact attribution verifiers are the last line of defense -- yet today's verifiers emit only opaque binary labels, leaving agents unable to self-correct and operators unable to audit.
arXiv:2604.00477v2 Announce Type: replace Abstract: LLM-based agent judges are an emerging approach to evaluating conversational AI, yet a fundamental uncertainty remains: can we trust their assessme...
arXiv:2601. 16398v3 Announce Type: replace-cross Abstract: Algorithmic audits are essential tools for examining systems for properties required by regulators or desired by operators.
arXiv:2609.35596v2 Announce Type: replace-cross Abstract: Self-evolving LLM agents have gained prominence for their ability to improve after deployment by modifying their harness, including their con...
arXiv:2610.36660v1 Announce Type: new Abstract: Self-improving AI systems can revise the designs that govern their own behavior. Yet existing approaches center improvement on selected parent agents a...
S3Gym is an interactive benchmark designed to evaluate large language models (LLMs) on their ability to self-improve through self-testing, self-judging, and self-improvement. It separates permissive exploration from strict held-out evaluation across seven text-based games with executable environment verifiers. Experiments show that self-improvement varies by task, with different experience incorporation pathways (direct history, summary memory, or parameter training) yielding mixed results and highlighting the need for agents to transform feedback into executable, transferable policies.
PROBE is an algorithm that trains language‑model auditors to probe deployed tool‑using agents for policy violations through realistic, multi‑turn, tool‑mediated dialogue. By framing auditing as a two‑player Markov game and using a composite reward that balances violation discovery, behavioral plausibility, conversation progress, and policy diversity, PROBE outperforms zero‑shot adversaries in uncovering broader and higher‑yield policy violations. The study compares GRPO, DPO, and GFlowNet optimizations, demonstrating that multi‑turn behavioral auditing is a distinct and necessary axis of agent evaluation, complementing existing capability and safety benchmarks.
Self-improving AI systems can revise the designs that govern their own behavior. Yet existing approaches center improvement on selected parent agents and their evolutionary experience, leaving the bro...