# Beyond single-channel agentic benchmarking

arXiv: https://arxiv.org/abs/2602.18456 · HTML: https://mlsanity.com/paper/2602.18456/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 10 of its 21 references that are in the map.
- First posted on arXiv 5 Feb 2026.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 10 of 10)

- [Effect of Confidence and Explanation on Accuracy and Trust Calibration in AI-Assisted Decision Making](https://mlsanity.com/paper/2001.02114/) (2020)
- [Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs](https://mlsanity.com/paper/2502.17424/) (2025)
- [When combinations of humans and AI are useful: A systematic review and meta-analysis](https://mlsanity.com/paper/2405.06087/) (2024)
- [Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?](https://mlsanity.com/paper/2407.21792/) (2024)
- [Towards Accountable AI: Hybrid Human-Machine Analyses for Characterizing System Failure](https://mlsanity.com/paper/1809.07424/) (2018)
- [Principles of Explanation in Human-AI Systems](https://mlsanity.com/paper/2102.04972/) (2021)
- [LabSafety Bench: Benchmarking LLMs on Safety Issues in Scientific Labs](https://mlsanity.com/paper/2410.14182/) (2024)
- [SciSafeEval: A Comprehensive Benchmark for Safety Alignment of Large Language Models in Scientific Tasks](https://mlsanity.com/paper/2410.03769/) (2024)
- [Towards Effective Human-AI Decision-Making: The Role of Human Learning in Appropriate Reliance on AI Advice](https://mlsanity.com/paper/2310.02108/) (2023)
- [Trust in AI emerges from distrust in humans: A machine learning study on decision-making guidance](https://mlsanity.com/paper/2511.16769/) (2025)

## Abstract (arXiv)

Contemporary benchmarks for agentic artificial intelligence (AI) frequently evaluate safety through isolated task-level accuracy thresholds, implicitly treating autonomous systems as single points of failure. This single-channel paradigm diverges from established principles in safety-critical engineering, where risk mitigation is achieved through redundancy, diversity of error modes, and joint system reliability. This paper argues that evaluating AI agents in isolation systematically mischaracterizes their operational safety when deployed within human-in-the-loop environments. Using a recent laboratory safety benchmark as a case study demonstrates that even imperfect AI systems can nonetheless provide substantial safety utility by functioning as redundant audit layers against well-documented sources of human failure, including vigilance decrement, inattentional blindness, and normalization of deviance. This perspective reframes agentic safety evaluation around the reliability of the human-AI dyad rather than absolute agent accuracy, with a particular emphasis on uncorrelated error modes as the primary determinant of risk reduction. Such a shift aligns AI benchmarking with established practices in other safety-critical domains and offers a path toward more ecologically valid safety assessments.