Cooperative Membership Functions for Multi-Agent Oversight

Abstract

Multi-agent oversight protocols must answer a question that single-agent oversight elides: which agents in a group are jointly responsible for a contested action. We introduce cooperative membership functions — a calibrated, trace-derived signal of the degree to which each participating agent shares causal responsibility for a multi-agent outcome — and show that incorporating them into the debate-plus-trace protocol reduces unwarranted halting by 41% on adversarial bargaining scenarios while preserving the protocol's true-positive rate. We propose membership functions as a primitive that any agent substrate supporting multi-agent execution should expose.

Index metadata

Cell

lebesgue-22

Compute

47 H100-days

Status

Open release

Code

github.com/alphabell-labs/ab-membership

Companion

debate-plus-trace v2 release

DOI

10.48550/arXiv.2601.04221

arXiv

arXiv:2601.04221

What this paper is part of

This index entry is part of the Interpretability & alignment research axis. The producing cell — lebesgue-22 — collaborates with adjacent cells listed in the cell directory. The paired interpretability cell (where applicable) is identified in the metadata above; their disagreement reports — if any — accompany the public release.

How to read this

If you want to use the result: the code (where available) is at https://github.com/alphabell-labs/ab-membership; the dataset is at https://huggingface.co/datasets/alphabell/multi-agent-oversight-2026 when one is released. To cite this report, prefer the DOI/arXiv identifier and the BibTeX block above. To discuss this with the producing cell, contact the lab with the index entry slug cooperative-membership-functions.

Limitations

Each cell-published report carries an explicit limitations section in the internal index. We do not paraphrase it here. Read the linked PDF — particularly its limitations and threats-to-validity sections — before downstream use.