The paper audits a commercial non‑generative System‑1 model on biosecurity‑relevant benchmarks, evaluating accuracy, calibration, error detection, selective prediction, and sensitivity to answer‑option order. It finds that the model’s accuracy varies strongly by task, is reasonably well calibrated when the vendor’s uncertainty field is interpreted correctly, and that option order can cause significant prediction changes—averaging across rotations improves accuracy. The study also shows that applying averaging only to low‑confidence items recovers most of the gain at a lower cost.
arXiv:2606. 29654v1 Announce Type: new Abstract: Multi-agent deliberation among LLMs can improve reasoning, but deployment requires deciding when the current answer is reliable enough to act on and when it should be escalated to human review.
The paper evaluates System One decision models—typed models that output probabilities for branching decisions—against supervised classifiers and generative language models on automated decision gate tasks. Eight checkpoints from six families, including the hosted model Jev, were benchmarked on workflow, intent, and social‑science items, showing that small trained classifiers match or slightly outperform decision models on intent and workflow when labels are available, while decision models outperform zero‑shot classifiers when labels are absent. The study also explores calibration, risk thresholds, and cost‑efficiency trade‑offs, providing condition‑dependent design guidelines for automated decision gates.
arXiv:2608. 14617v1 Announce Type: cross Abstract: A recurring proposal in legal AI is to improve case-outcome prediction by fusing uncertainty tools (evidence graphs with belief propagation, sequential Bayesian odds updating, Dempster-Shafer combination, and conformal prediction) into one pipeline.
The paper reports that a model can pass fidelity checks—verifying that extracted values match the source—without actually opening a datasheet, due to a hidden constraint that disables tool use. To address this, the authors log every tool call in an agentic benchmark and develop two instruments: a rule‑based failure‑attribution classifier and a silent‑failure detector that flags runs based solely on which tools were invoked. While the detector shows low false positives on clean extractions and recovers all planted faults, its recall against correct tool usage but incorrect answers remains unmeasured, and a partial causal chamber confirms only a subset of claims, highlighting limitations in physical verification.
arXiv:2608. 10216v1 Announce Type: cross Abstract: Agent frameworks ship quality gates that compare text blocks by embedding-cosine similarity and decide at a fixed cutoff.
The paper investigates the reliability of tool‑using agents, focusing on two failure modes: selecting the wrong tool and constructing incorrect arguments. It introduces a correct‑invocation rate metric to distinguish these errors and evaluates five open‑weight models on multi‑step tasks up to depth 8, finding that by depth 6 about 70% of a model’s clean‑context capability is lost due to earlier mistakes. The study reveals that exact‑match scoring against a fixed gold trajectory forces severity and recovery parameters to extreme values, and proposes a conditional‑on‑state scoring remedy that yields more realistic severity estimates.
The paper audits a developer‑accessible on‑device language model, revealing that it can confidently produce incorrect answers while refusing benign prompts, a phenomenon termed task‑asymmetric miscalibration. The model’s confident outputs are surface‑indistinguishable, with classifiers based on user‑visible features failing to separate correct from wrong responses. The authors propose a model‑agnostic audit protocol, a surface‑indistinguishability test, and a black‑box consistency wrapper that improves reliability without requiring model access.
arXiv:2604. 08941v2 Announce Type: replace Abstract: Medical Vision-Language Models (VLMs) answering binary presence questions on chest radiographs can fail in two linked ways: they are confidently wrong, and they change answers when a clinically equivalent question is rephrased.
arXiv:2608. 02665v1 Announce Type: cross Abstract: A benchmark score is a measurement instrument, yet most benchmarks read each item at a single canonical surface form.
The paper investigates how personalized agents decide to use, ignore, update, or query retrieved user memory before acting on a task. An empirical audit protocol is developed to test structured intermediate outputs, revealing that while exposing state definitions improves accuracy, an explicit state-output field does not significantly enhance policy accuracy for large language models. The study also shows that example-level accuracy overstates consistency, with full four‑way family success being rare, and that providing benchmark‑associated state labels merely conditions predictions rather than proving internal fidelity.
arXiv:2607. 17384v1 Announce Type: new Abstract: This paper provides an experimentally verified formal law for calculating the uplift that diversity of thought provides in Large Language Model (LLM) ensembles.
The paper introduces Counterfactual Fragility Certificates (CFC), a model‑agnostic audit protocol that maps each prediction to an evidence‑failure trajectory, summarizing it with metrics such as greedy flip budget, margin‑collapse area, degradation thresholds, and fragility dominance score. CFC is shown to identify brittle high‑confidence predictions on seven tabular benchmarks with an AUROC of 0.915, outperforming existing scalar scores by up to +0.405. The method remains effective across various perturbation and review‑budget scenarios, and can also inform fragility‑aware regularization and temperature correction.