Durable Agent Substrate v1: persistent state, learned tool affordances, and verifiable execution traces

Abstract

We introduce v1 of the alphabell agent substrate, a runtime that treats agents as first-class computational entities with persistent state, structured memory, and execution traces verifiable against a content-addressed log. Trained on 11,200 long-horizon trajectories drawn from twelve cell-managed environments, agents trained on the substrate complete 14-day open-ended tasks with 64% completion under partial observability — vs. 38% for the best published react/plan baseline at matched parameter count. We show that exposing memory and resource budgets as first-class primitives removes 70% of the prompt-engineering effort previously needed to maintain agent identity over multi-week deployments.

Index metadata

Cell

fourier-67

Compute

82 H100-days

Status

Open release — substrate v1 SDK published

Pre-registration

2025-04-12

Companion

Interpretability report ab-int-031

DOI

10.48550/arXiv.2510.16245

arXiv

arXiv:2510.16245

What this paper is part of

This index entry is part of the Agentic engineering research axis. The producing cell — fourier-67 — 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-durable; the dataset is at TBD 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 durable-agents-substrate-v1.

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.