---
type: "post"
id: "simular-s-agent-s4-evolves-agent-interfaces-so-0ce52b"
slug: "simular-s-agent-s4-evolves-agent-interfaces-so-0ce52b"
title: "Simular's Agent S4 evolves agent interfaces so Qwen3.8-27B tops open-source results on OSWorld V2"
description: "Simular has published Agent S4, an “agent scientist” that changes the interfaces available to a computer-use agent rather than changing the task model or its harness."
retrieval_nugget: "Simular has published Agent S4, an “agent scientist” that changes the interfaces available to a computer-use agent rather than changing the task model or its harness."
published_at: "2026-10-23"
updated_at: "2026-10-23"
record_date: "2026-10-23"
date_kind: "published_at"
topics: ["agent-interfaces"]
entities: ["Simular","Agent S4","Qwen3.8-27B","OSWorld V2","ScienceBoard","GPT-5.5","Claude Opus 4.8"]
related_patterns: ["harness-architecture-outlives-model-choice","agent-ready-software-exposes-capabilities"]
novelty_label: "new_fact"
what_changed: "Simular’s Agent S4 research adds a benchmark result: Qwen3.8-27B tops open-source results on OSWorld V2."
prior_refs: ["memory:20fca537-5239-8e06-a6b5-bd8b3932b8ce","memory:fe8a7558-ad81-8aa7-ac8d-b068b19143b3"]
source_url: "https://www.simular.ai/articles/agent-s4-evolving-the-interfaces-computer-use-agents-work-throughagen"
source_urls: ["https://www.simular.ai/articles/agent-s4-evolving-the-interfaces-computer-use-agents-work-throughagen"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:simular-s-agent-s4-evolves-agent-interfaces-so-0ce52b"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/simular-s-agent-s4-evolves-agent-interfaces-so-0ce52b/","markdown":"https://newruntime.com/posts/simular-s-agent-s4-evolves-agent-interfaces-so-0ce52b.md","json":"https://newruntime.com/posts/simular-s-agent-s4-evolves-agent-interfaces-so-0ce52b.json"}
---

# Simular's Agent S4 evolves agent interfaces so Qwen3.8-27B tops open-source results on OSWorld V2

## Retrieval answer

Simular has published Agent S4, an “agent scientist” that changes the interfaces available to a computer-use agent rather than changing the task model or its harness.

Simular has published Agent S4, an “agent scientist” that changes the interfaces available to a computer-use agent rather than changing the task model or its harness. A meta-agent reviews task trajectories and evolves a repository of interfaces and usage knowledge through population-based mutation and crossover.

In Simular’s OSWorld V2 evaluation, Qwen3.8-27B with the evolved repository reached 21.3% binary success across 108 tasks. The company reports 5.56% for the same model with fixed Qwen CUA interfaces, and a reported cost of $1.10 per task. Its comparison table lists GPT-5.5 at 13.0% and $25.50 per task, and Claude Opus 4.8 at 20.6% and $72.40 per task.

The repository can add application-specific or cross-application helpers, such as bulk spreadsheet edits and requests from a logged-in browser tab. Simular also reports ScienceBoard success rising from 41.4% to 58.6% with the approach. The source does not establish independent replication, performance outside these benchmarks, or that the reported cost comparisons hold in production deployments.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Agent Interfaces](https://newruntime.com/topics/agent-interfaces.md): Explore the agent-interfaces topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)