# Beyond "AI Helps Humans": Decision-Targeted Evaluation Design for Human-Agent Teams in the Agentic Era

arXiv: https://arxiv.org/abs/2609.05527 · HTML: https://mlsanity.com/paper/2609.05527/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 9 of its 25 references that are in the map.
- First posted on arXiv 1 Sep 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 9 of 9)

- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [BetterBench: Assessing AI Benchmarks, Uncovering Issues, and Establishing Best Practices](https://mlsanity.com/paper/2411.12990/) (2024)
- [Optimal and Adaptive Off-policy Evaluation in Contextual Bandits](https://mlsanity.com/paper/1612.01205/) (2016)
- [Cost-Optimal Active AI Model Evaluation](https://mlsanity.com/paper/2506.07949/) (2025)
- [Dermatologist-like explainable AI enhances trust and confidence in diagnosing melanoma](https://mlsanity.com/paper/2303.12806/) (2023)
- [Targeted Active Learning for Bayesian Decision-Making](https://mlsanity.com/paper/2106.04193/) (2021)
- [CentaurEval: Benchmarking Human-in-the-Loop Value in Agentic Coding](https://mlsanity.com/paper/2512.04111/) (2025)
- [Logging Policy Design for Off-Policy Evaluation](https://mlsanity.com/paper/2605.15108/) (2026)
- [Action-BED: Task-Driven Bayesian Experimental Design with Singly Intractable Objectives](https://mlsanity.com/paper/2606.23662/) (2026)

## Abstract (arXiv)

Wherever a coding agent works under engineer supervision, or a clinical model assists a radiologist, the deployment question is whether to keep the human-AI workflow or replace it with the human alone or the agent alone. The human-AI workflow is worth keeping only if it beats both of those alternatives. Yet once it is deployed, neither alternative outcome is observed: recovering one means replaying the task under that alternative, and every replay costs expert time or compute. Under a fixed replay budget, the design question is therefore which tasks should be more likely to receive a human-only replay, and which an agent-only replay. Existing methods do not directly target this decision. Agent benchmarks do not choose which missing baseline to measure, variance-based sampling ignores which of the two comparisons is closer to failing, and Bayesian information methods focus on learning model parameters instead of making the deployment decision. We propose TEAM-Design, a rule that gives every task two replay probabilities, one per baseline. It raises a probability where the missing baseline outcome is hard to predict from what is already known about the task and where that comparison is harder to establish, and lowers it where replay is expensive. We prove that the rule solves this budgeted design problem, and that drawing the replays at random from recorded probabilities still controls the chance of wrongly declaring that the workflow beats both. We reanalyze 6 clinical settings, where no human-AI workflow beats both alternatives, and a coding benchmark, where one does, then evaluate TEAM-Design on synthetic designs and on a semi-synthetic design built from a real chest X-ray reader study. TEAM-Design works best when one of the two comparisons is clearly harder to settle than the other, and can do worse than variance-based allocation when the two are similarly difficult.