The paper presents a reinforcement learning approach to enhance large language model (LLM) auditors for alignment tasks. By training policies that investigate target models for hidden behaviors and using an LLM judge to compare investigations, the method improves audit realism and reduces false positives. Experiments show better performance on adversarially fine‑tuned targets and a low false‑positive rate below 1%.
arXiv:2510. 06096v3 Announce Type: replace Abstract: The objectives that Large Language Models (LLMs) implicitly optimize remain dangerously opaque, making trustworthy alignment and auditing a grand challenge.
Safety tuning pipelines judge only the final answer, which makes it difficult to distinguish robust refusal from two undesirable shortcuts: blanket refusal on benign requests and polished but unfaithf...
AUDITPLAN introduces a plan-then-answer method for safety alignment in language models, where the model first generates a compact structured safety plan before responding. The plan includes a threat label, intended action, and explicit constraints, allowing machine‑checkable auditing while remaining hidden from end users. Training combines supervised fine‑tuning with reinforcement learning using the FAITHGATE reward, which only rewards correct plans, thereby reducing unsafe shortcuts and improving robustness across Qwen model variants.
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.
The paper proposes probe-guided fine-tuning, a method that uses probes detecting undesired properties in model activations as a direct training signal. Experiments show that continuously updated probes reduce harmfulness and improve honesty while preserving utility, outperforming DPO and inference-time steering in safety-utility trade-offs and robustness to jailbreak and abliteration attacks. Importantly, the concepts remain linearly encoded after fine-tuning, maintaining monitorability.
arXiv:2610.16911v1 Announce Type: new Abstract: Does providing additional context to automated AI auditors improve their effectiveness? Using the Petri tool to audit LLM coding agents, we test the im...
The paper introduces a protocol for auditing and composing reinforcement‑learning policies using discrete behavioral rules, defining auditability through six testable predicates such as trace integrity and rule coverage. Experiments show that overlapping rule sets do not guarantee behavioral agreement, and that rule‑based fusion often fails to outperform value‑based composition, highlighting limitations in current description layers. The authors provide an evidence‑bounded audit framework and outline future directions for more robust skill composition.
The paper introduces TRACE, a digital‑advertising diagnostic environment that uses simulated interventions to generate verifiable rewards for training reasoning agents. By injecting controlled interventions into a simulator, the hidden cause of anomalies becomes an oracle label, enabling agents to learn to identify root causes and affected segments through noisy, confounded evidence. Experiments show that reinforcement learning with these synthesized rewards outperforms large prompted baselines, achieving higher accuracy while using fewer tool calls.
arXiv:2606. 18327v1 Announce Type: cross Abstract: Language models (LMs) that faithfully describe their own behavior can more easily be audited, understood, and trusted by users.
arXiv:2606. 27291v1 Announce Type: new Abstract: Job-search platforms rely on low-bandwidth query interfaces that often fail to capture the high-dimensional complexity of candidate profiles.
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:2606. 08480v1 Announce Type: cross Abstract: Reinforcement learning (RL) presents a promising avenue for enhancing generative recommendation beyond supervised imitation, leveraging reward signals to guide policy improvement.