Teams on a Fixed Model: Two Months of Harness Experiments with The One

How much can an agent-team harness add when the model is fixed? We report eight weeks (28 September to 20 November 2026) of controlled experiments on The One, a product that runs teams of language-model agents on a person's computer. Three programs ran back to back: V1 on a task suite of our own (over 120 batches), V8 on Terminal-Bench 4.0 through the Harbor framework (315 jobs and 6,223 graded trials, with 30 tasks held out and never read), and a final Terminal-Bench 4.1 run under the Artificial Analysis protocol. The configuration we kept, a single lead agent on GPT-6.2 Sol at maximum reasoning effort, scored 60.9% on the 63 tasks we could run and 58.1% with the three GPU tasks counted as failures. That ties the model vendor's own agent (Codex) on the same model and effort while using about 30% fewer input tokens, at $1.35 per attempt at list price. Three findings carry the paper. Append-only context cut cost by a third to a half with no change in accuracy. On tasks that one context can hold, a single strong owner matched or beat every team structure we built, and same-model second opinions confirmed the shared misreading instead of catching it. The model's choice at a decision point moved when facts were placed in front of it, never with advice. Most levers that won on the tasks they were designed on failed on held-out tasks; we describe the held-out discipline that caught them, and report the negative results in full.

Authors

Institutions

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-21
DOI
https://doi.org/10.5281/zenodo.24410339
Primary Topic
Artificial Intelligence Applications
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Teams on a Fixed Model: Two Months of Harness Experiments with The One

Ziyang Zhang
Zenodo (CERN European Organization for Nuclear Research)
Artificial Intelligence Applications
preprint

Teams on a Fixed Model: Two Months of Harness Experiments with The One

Ziyang Zhang
preprint en

Abstract

How much can an agent-team harness add when the model is fixed? We report eight weeks (28 September to 20 November 2026) of controlled experiments on The One, a product that runs teams of language-model agents on a person's computer. Three programs ran back to back: V1 on a task suite of our own (over 120 batches), V8 on Terminal-Bench 4.0 through the Harbor framework (315 jobs and 6,223 graded trials, with 30 tasks held out and never read), and a final Terminal-Bench 4.1 run under the Artificial Analysis protocol. The configuration we kept, a single lead agent on GPT-6.2 Sol at maximum reasoning effort, scored 60.9% on the 63 tasks we could run and 58.1% with the three GPU tasks counted as failures. That ties the model vendor's own agent (Codex) on the same model and effort while using about 30% fewer input tokens, at $1.35 per attempt at list price. Three findings carry the paper. Append-only context cut cost by a third to a half with no change in accuracy. On tasks that one context can hold, a single strong owner matched or beat every team structure we built, and same-model second opinions confirmed the shared misreading instead of catching it. The model's choice at a decision point moved when facts were placed in front of it, never with advice. Most levers that won on the tasks they were designed on failed on held-out tasks; we describe the held-out discipline that caught them, and report the negative results in full.

Zenodo (CERN European Organization for Nuclear Research)
Zero Emissions Resource Organisation (NO)
Artificial Intelligence Applications
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon