The paper investigates how AI systems that perform best‑of‑n search require different validation strategies as the search width changes. It shows that auditing only small search widths leaves a gap in reliability estimates for larger widths, and proposes retaining candidate ranks and truth labels to estimate reliability across all widths up to N. The authors derive theoretical bounds on the minimax mean‑squared error, design procedures that achieve these bounds, and demonstrate that a shared audit can significantly reduce maximum error across many widths in practical CodeRM pools.
arXiv:2608.21496v1 Announce Type: cross Abstract: AI systems increasingly generate alternatives, inspect evidence, and deploy a selected output. Validation is therefore target-relative: evidence cert...
The paper introduces a risk‑controlled framework for using large language models (LLMs) as judges in tasks without reference answers. By calibrating uncertainty thresholds on a held‑out set, the method ensures that the false discovery rate of accepted verdicts stays below a user‑specified level α with high probability, using finite‑sample Clopper–Pearson intervals. When the parametric judge lacks confidence, the instance is routed to a retrieval‑augmented mode with a second calibrated threshold, preserving the error guarantee while achieving higher coverage than single‑mode baselines.
arXiv:2608. 08709v1 Announce Type: new Abstract: The reliability of AI generative models is typically measured by output correctness, yet in practice it depends on the effort required to verify those outputs.
arXiv:2608. 01378v1 Announce Type: new Abstract: Design campaigns in chemistry, materials science, and machine learning share a bottleneck: determining how good a candidate truly is requires an expensive evaluation - an experiment, a first-principles simulation, or a full training run.
arXiv:2608. 05212v1 Announce Type: new Abstract: Deep search agents tackle challenging questions through long-horizon web interactions, a process that is both complex and fragile: small reasoning errors may propagate through long, noisy trajectories into fluent but incorrect answers.
arXiv:2606. 20820v2 Announce Type: replace Abstract: Can we trust evaluation scores to capture an LLM's true real-world performance?
The paper "Beyond Execution: Auditing Experimental Fidelity in LLM-Driven Scientific Research" argues that large language model agents must faithfully implement reference methods, design experiments that truly test claims, and provide supporting evidence. It reports that agents often hallucinate methodology—reducing datasets, substituting components, or drawing conclusions from limited resources—leading to false claims. To counter this, the authors introduce ABE‑Ralph, a reference‑anchored auditing framework that structures experimental constraints, guides implementation, and verifies results, achieving a 93% robust execution rate across 30 reproduction runs and matching or exceeding state‑of‑the‑art performance on 5 NatureBench tasks. "whyItMatters":"The study demonstrates that evaluating AI scientists requires more than code execution; it must ensure experimental design and evidence truly support the claimed scientific outcomes."
The paper investigates how to improve confidence calibration for large language models (LLMs) used in automated code revision (ACR). It proposes applying local Platt-scaling to three fine-grained confidence scores, rather than the conventional global method, and demonstrates that this approach consistently reduces calibration error across multiple tasks, metrics, and model sizes. The study shows that fine-grained calibration, especially when combined with global scaling, yields more reliable confidence estimates for ACR tasks.
arXiv:2606. 22678v2 Announce Type: replace-cross Abstract: Agentic coding harnesses - such as Agent-Skills, Superpowers, and Agent-Rigor - are increasingly deployed to augment underlying LLMs for real-world software engineering tasks.
arXiv:2608. 10406v1 Announce Type: cross Abstract: Web search, product search, and question-answering retrieval systems often assign a relevance label and confidence score to each query-candidate pair.
The paper introduces CORA (Counterfactual, Observable Redundancy Audit), a protocol for auditing website redundancy by measuring repetition load, normal-use tax, and failure-domain recovery reserve. Each audit run records screenshots, stable element identities, and task traces, while a versioned vision‑language model generates annotations that are validated and released only if they meet calibrated criteria. Experiments on a transparent mechanistic testbed show that CORA’s factorized representation separates reserve from normal-use tax and predicts perturbed success more accurately than scalar-load baselines, but it withholds automated scores when instruments fail to meet release requirements, indicating that CORA is an auditable candidate procedure for the studied benchmark rather than a universal standard.
Evolutionary Ensemble Search (EES) is a framework that builds machine‑learning procedures through expert‑guided program evolution. A specialized council interprets task evidence and experimental results to generate structured search directions, which an orchestrator assigns to execution specialists and an evolutionary engine. The engine selects parents, diagnoses errors, and creates descendants via code mutation, pipeline edits, and crossover, with each child evaluated on its own validation evidence. Population archives preserve useful alternatives, and compatible predictions compete in a validation‑gated ensemble stage. Search adapts through parent‑relative operator credit, session memory, and lessons retrieved across runs. The system achieved medal‑threshold artifacts on 19 of 22 tasks (86.36 %) with 11 gold, five silver, and three bronze outcomes across diverse modalities.