arXiv:2602. 16111v2 Announce Type: replace-cross Abstract: Online media platforms track the share of impressions associated with content attributes, or prevalence, to evaluate trade-offs and set guardrails in A/B experiments.
arXiv:2606. 10794v3 Announce Type: replace Abstract: Existing black-box LLM provenance methods achieve comparability by querying every candidate model with the same diagnostic prompts.
arXiv:2609.14762v1 Announce Type: cross Abstract: Cloud-hosted large language models (LLMs) are increasingly used for root cause analysis (RCA) in AIOps pipelines, but they introduce data privacy ris...
arXiv:2602. 18518v2 Announce Type: replace Abstract: Content safety teams need metrics that reflect what users actually experience, not only what is reported.
arXiv:2606. 01034v2 Announce Type: replace Abstract: Deploying an LLM judge panel spends human labels on fitting a calibrator, constructing candidate judge paths, and validating which candidate to deploy.
The paper introduces RAISE, a diagnostic framework that tests whether a costly large language model (LLM) signal provides enough pre-call information to justify selective use. It identifies the failure mode of acquisition collapse, where an LLM appears useful overall but lacks actionable evidence for individual decisions. The authors demonstrate RAISE with Structured Hypothesis Embeddings (SHE) and evaluate it across multiple study designs, showing that predictable incremental benefit, rather than average lift, indicates recoverable selective value.
The paper investigates the reliability of language‑model judges used as measurement instruments on shared endpoints. Through two preregistered audits of 52,988 requests, the authors found that repeat rankings and byte‑identical replays fell far short of required thresholds, revealing significant instability. They identify three mechanisms—label‑to‑meaning bias, candidate gaps below the noise floor, and input permutation noise—that explain the gap, and propose a snapshot‑identity ladder, design rules, and a reporting checklist to mitigate such failures.
The study examines the composition of a random sample from the Model Context Protocol (MCP) registry, revealing that only 48.8% of the 400 sampled npm/stdio servers successfully complete an initialization handshake, compared to 66.7% for a hand‑curated frame. Among the servers that run, there are no fatal JSON Schema violations across 2,766 advertised tools, but optional safety annotations vary widely, with a 58.8% omission rate in the random draw versus 41.5% in the curated set. The authors also compare MCP tool descriptions to two benchmark corpora, finding minimal near‑duplication in real MCP tools (2.8%) and significant repetition in synthetic datasets (up to 85.6%).
arXiv:2607. 27083v1 Announce Type: new Abstract: As LLM agents increasingly depend on diverse external services such as search engines, databases, and connectors, agent harnesses face a fundamental tool-selection challenge: acquiring too few tools leaves the task under-informed, while too many adds cost, context load, and privacy exposure.
arXiv:2607. 24010v1 Announce Type: new Abstract: Active RAG systems decide when to retrieve external knowledge during generation, making them a budget-sensitive case of agentic RAG and self-adaptive retrieval.
arXiv:2608. 13563v1 Announce Type: cross Abstract: Early-stage teams often lack users, time, and budget to run repeated UX studies, yet still need decision-oriented signals to iterate safely.
arXiv:2609.15015v1 Announce Type: new Abstract: Synthetic perturbations appear to offer inexpensive calibration data for LLM evaluators in biomedical ML, where expert review is scarce. Yet a planted...
arXiv:2607. 28545v2 Announce Type: replace-cross Abstract: Large language models can write, patch, and search code, but oncall root cause analysis (RCA) demands something different: reasoning over noisy metrics, logs, traces, and source code, starting from ambiguous user-facing reports, often hours after the incident began.