cs.LGNov 14, 2026

The Critic Can Hurt: On the Safety of Critics in LLM-Guided AutoML Search

Authors: Gaoyuan Du, Xiaoyang Liu, Rex Zhou, Dengdu Jiang, Rong Fu, Meng Ding, Defu Cao

Organizations: Amazon · Independent Researcher · University of Massachusetts Boston · University of Southern California

Abstract

LLM critics increasingly steer iterative search in agentic AutoML, prompt optimization, and self-refinement--evaluated for whether they help, but rarely for whether they can hurt. We isolate the critic's marginal effect through a four-arm audit and characterize the loop's tolerance through controlled fault injection. We show a naive 8B critic drives search below the no-critic random-search floor on 7 of 8 tabular datasets, losing up to 0.245 AUC in the worst case; the magnitude varies strongly with dataset, frontier, and budget. When: stronger critics attenuate the loss on the evaluated suite, without establishing a universal capability threshold. Why: controlled fault injection shows that non-directional errors are nearly costless under best-so-far search, whereas directional errors consume finite search opportunities; an idealized effective-sample calculation yields a necessary condition, q(m−1)>βq(m-1) > β, not a deployment certificate. How: a simple observable validation gate and a learned detector can reduce realized loss, but neither is guaranteed to preserve the full-budget no-critic baseline. We will release CRITFAULT, to our knowledge the first benchmark for detecting harmful critic feedback in AutoML. A critic is not a free addition: audit before trusting, and gate when capability or verification is insufficient.

Figures & tables

Appendix figures & tables15 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Sep 30, 2025

When LLMs Benchmark Themselves: Deconstructing Self-Bias in Automated Evaluation

As LLMs rapidly saturate existing benchmarks, automated benchmark creation using LLMs (LLM as a benchmark) where a model generates test inputs (LLM as a testset) and evaluates outputs (LLM as an evaluator) has gained traction as a cheap alternative to human curation. We show that this paradigm has a fundamental problem: LLM-generated benchmarks systematically favor the model that created them. Using machine translation as our primary testbed, we find that self bias arises from two compounding sources, LLM as a testset and LLM as an evaluator, and their combination amplifies the effect. Crucially, even when test data is generated with explicit diversity controls, each modelś implicit stylistic tendencies produce homogeneous, model-specific outputs that inflate its own scores. Increasing source text diversity, using our proposed diversity metric, partially mitigates this bias. Self bias is strong enough to cause each model to rank itself first, overriding the peer consensus ordering. We confirm that the phenomenon extends to open-ended generation on the Chatbot Arena task.
Aug 5, 2026

SearchAuditor: Auditing and Attributing Failures in Long-Horizon Search Agents

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. Diagnosing such failures is difficult, requiring the manual inspection of extremely long execution traces, which could be beyond human capacity. We therefore introduce SearchAuditBench, a benchmark that evaluates whether LLM auditors can localize, attribute, and repair these failures, thereby reducing the human burden. SearchAuditBench comprises 1,243 failed trajectories, averaging 73.1 messages and 65.1K tokens, collected from eight open-weight models on five deep-search benchmarks, each expert-annotated with the critical error step, a search-specific root cause, and a reference repair with grading rubrics. We further propose SearchAuditor, a multi-perspective auditing framework that effectively localizes, attributes, and repairs search-agent failures through evidence-grounded adjudication. Experimental results show that even the strongest baseline, when powered by a frontier model like GPT-5.5, attains only a 26.6% end-to-end pass rate. In contrast, our SearchAuditor consistently outperforms all baselines across different frontier models, achieving an end-to-end pass rate of 32.3%, and resuming failed runs with its repairs enables agents to better recover from errors.
Feb 17, 2026

LLM-as-Judge on a Budget

LLM-as-a-judge has emerged as a cornerstone technique for evaluating large language models by leveraging LLM reasoning to score prompt-response pairs. Since LLM judgments are stochastic, practitioners commonly query each pair multiple times to estimate mean scores accurately. This raises a critical challenge: given a fixed computational budget BB, how to optimally allocate queries across KK prompt-response pairs to minimize estimation error? We present a principled variance-adaptive approach leveraging multi-armed bandit theory and concentration inequalities. Our method dynamically allocates queries based on estimated score variances, concentrating resources where uncertainty is highest. Further, our algorithm is shown to achieve a worst-case score-estimation error of O~(∑i=1Kσi2B)\tilde{O}\left(\sqrt{\frac{\sum_{i=1}^K σ_i^2}{B}}\right), σi2σ_i^2 being the unknown score variance for pair i∈[K]i \in [K] with near-optimal budget allocation. Experiments on Summarize-From-Feedback and HelpSteer2 demonstrate that our method significantly outperforms uniform allocation, reducing worst-case estimation error while maintaining identical budgets. Our work establishes a theoretical foundation for efficient LLM evaluation with practical implications for AI safety, model alignment, and automated assessment at scale.