Litmus is a zero-label system that automatically designs evaluation and monitoring metrics for AI pipelines by extracting evaluation intent from source code and targeted interrogation. It identifies what must be measured and why, then generates a justified, per-stage metric portfolio. In experiments on three real code-defined pipelines, Litmus outperforms AutoMetrics and DynamicRubric baselines in concern coverage, stage span, redundancy, and validity against per-row quality labels, especially on scientific QA.
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.
The paper introduces AXIOM, a perturbation-based framework for creating a balanced benchmark of code evaluation problems. AXIOM refines program quality by applying controlled semantic perturbations and then calibrates scores through selective manual annotation, resulting in the multilingual AXIOMBENCH dataset with 1,962 problems. This approach addresses limitations of prior benchmarks that rely on coarse binary labels or subjective human scoring.
The paper presents EvalAgent, an AI assistant that automates agent evaluation by encoding domain expertise into evaluation skills such as procedural instructions, reusable code, and dynamic API retrieval. EvalAgent constructs a trace-based pipeline that outputs metrics, executable code, and reports, and is evaluated using a new meta-evaluation framework and AgentEvalBench. Results show that EvalAgent improves the Eval@1 metric from 17.5% to 65% and receives 79.5% human expert preference, while ablation studies confirm the importance of evaluation skills.
arXiv:2607. 19386v1 Announce Type: new Abstract: Cross-paper comparison of sparse autoencoder (SAE) interpretability often relies on autointerpretability scores.
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.
EvalResearchBench (ERB) is a benchmark that tests whether AI agents can autonomously design evaluation tasks for recursive self‑improvement. In ERB, a researcher agent selects or synthesizes tasks, builds graders, and refines them through pilot tests before producing a final evaluator that runs within fixed time and API budgets. Experiments with nine researchers and thirteen candidate models show that the best automated evaluators achieve about 75% concordance with target benchmarks, below the 91% ceiling set by target disagreements, and that human‑designed task samples still outperform many automated approaches.
The paper introduces BenchGuard, a framework that uses advanced language models to audit execution-based agent benchmarks. BenchGuard systematically cross-verifies benchmark artifacts through structured LLM protocols, optionally incorporating agent solutions or execution traces for deeper diagnostics. In tests on ScienceAgentBench and BIXBench Verified-50, BenchGuard uncovered numerous author-confirmed and expert-identified issues, including fatal errors that made tasks unsolvable, and demonstrated cost-effective auditing for complex bioinformatics tasks.
arXiv:2607. 28037v1 Announce Type: new Abstract: As LLM-based agents are deployed in complex, multi-step workflows, a critical evaluation gap has emerged: most existing benchmarks judge only final outcomes, unable to distinguish reliable reasoning from lucky success or attribute failures to specific process deficiencies, hindering attribution in long-horizon tasks.
arXiv:2606. 24839v1 Announce Type: new Abstract: Agentic data analysis systems produce rich outputs, including code, numerical results, and verbal diagnostics.
arXiv:2609.21841v1 Announce Type: new Abstract: Frontier language models now produce professional deliverables that expert graders judge to match human work on a substantial share of economically val...
arXiv:2607. 12790v1 Announce Type: new Abstract: Self-evolving agent systems improve by creating, revising, and retiring their own skills, but every such loop rests on a hidden assumption: a reliable evaluation metric already exists.
arXiv:2607. 14673v1 Announce Type: new Abstract: Evaluations (Evals) are a deployment bottleneck for real-world AI applications: public benchmarks rarely match a team's users, context, or policies, and human review is often tedious to scale.