GAUGE is a new offline protocol that evaluates whether the common practice of using an LLM-as-a-judge to rank task‑oriented agents actually aligns with a verifiable reward. Across 25 agents from six providers on two benchmarks, GAUGE finds that user satisfaction scores are largely uncorrelated with task success, and that the judge’s ranking loses precision when agents are closely matched in performance. The study highlights a gap between ranking validity and construct validity in current evaluation practices.
arXiv:2606. 13685v1 Announce Type: cross Abstract: LLM-as-a-Judge is now widely used to rank model outputs, train reward models, and populate public leaderboards, but its run-to-run reliability remains under-characterized.
The paper investigates how large language models (LLMs) used as judges in absolute scoring tasks exhibit systematic biases that compromise reliability. It shows that a judge’s task accuracy strongly predicts both its judging accuracy and its directional bias, yet more capable examinee models consistently receive more lenient judgments. To mitigate these biases, the authors propose a calibrated weighted majority voting (WMV) ensemble that estimates judges’ error rates from inter-judge agreement patterns, achieving near-oracle performance without labeled data and improving both accuracy and fairness.
AgentJudgeBench is a new benchmark that evaluates the reliability of large language model (LLM) judges on agentic tool‑calling tasks involving workflow directed acyclic graphs (DAGs). It contains 3,808 instances across six DAG topologies and three difficulty tiers, tested with five generators (3B–70B open‑weight models and GPT‑5.4) and six judges (20B to frontier scale) under both paired‑with‑and‑without‑ground‑truth conditions. The study finds that judge alignment degrades with task difficulty, ground‑truth exposure can sometimes hurt alignment, and structured evaluation rubrics provide modest improvements, revealing a structural ceiling that model capacity alone cannot surpass.
arXiv:2605. 27914v2 Announce Type: replace-cross Abstract: Benchmarking is mature where answers are verifiable -- math, code, reasoning -- but the fastest-growing uses of LLMs are subjective and human-facing: companionship, emotional support, counseling.
arXiv:2604. 22891v4 Announce Type: replace-cross Abstract: LLM-as-a-Judge has become a dominant approach in automated evaluation systems, playing critical roles in model alignment, leaderboard construction, quality control, and so on.
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:2608. 11434v1 Announce Type: new Abstract: Mobile agent benchmarks increasingly rely on LLM-based judges to evaluate task completion, yet the reliability of these judges on mobile agent trajectories remains largely unexamined.
The paper presents a layered framework for evaluating conversational AI by aligning offline proxy signals with online A/B experiment outcomes. It introduces a three‑step alignment chain—behavioral label to product outcome, classifier to candidate behavior, and offline signal to experiment effect—alongside an audit protocol that compares confidence intervals and rankings. In a real‑world deployment, the composite proxy achieved 81.1% F1 versus 34.3% for the raw classifier, correctly predicting direction on all 113 contrasts and enabling efficient prioritization of candidate models before costly online testing.
arXiv:2606. 03650v1 Announce Type: cross Abstract: Choosing or ranking language models for a specific application is hardest when no task-specific labeled data exists, and standard public benchmarks cannot be trusted, their items having likely leaked into pretraining, so scores reflect memorization rather than fitness.
The paper introduces a disclosure‑gated user simulator for companion‑agent evaluation, where information release is conditioned on the agent’s behavior through a five‑level gate system. The authors train the simulator on synthetic and real data, audit its performance, and demonstrate that it preserves ranking order and score stability across 12 tested systems. Their released simulator achieves a 0.993 correlation with the original benchmark’s simulator and outperforms prompting a frontier model, which only shifts scores upward without affecting rankings.
arXiv:2603. 00077v3 Announce Type: replace-cross Abstract: Rubric-based LLM judges have become indispensable for evaluating and optimizing systems on non-verifiable tasks, where success cannot be reduced to exact programmatic checks.
The paper argues that verbalized confidence—once viewed as overconfident and coarse—has become the preferred soft‑scoring method for LLM‑as‑a‑Judge on top‑tier proprietary models released after 2025. Experiments on SummEval, AggreFact, and HelpSteer2 across up to 18 LLMs show that log‑probabilities are no longer the best signal, and that adding an overconfidence advisory and self‑debate further improves calibration and robustness. The authors note that these enhancements incur little accuracy loss on post‑2025 models but do affect pre‑2025 ones, highlighting a compatibility shift in how confidence should be measured.