---
type: "post"
id: "corridor-introduces-argos-a-fine-tuned-qwen3-5-bf46d6"
slug: "corridor-introduces-argos-a-fine-tuned-qwen3-5-bf46d6"
title: "Corridor introduces Argos, a fine-tuned Qwen3.5-9B security model that tops 14 models on its SecReT benchmark"
description: "Corridor announced corridor-argos-1 on October 21, 2026, a security-context selection model used in its Agent Steering product."
retrieval_nugget: "Corridor announced corridor-argos-1 on October 21, 2026, a security-context selection model used in its Agent Steering product."
published_at: "2026-10-23"
updated_at: "2026-10-23"
record_date: "2026-10-23"
date_kind: "published_at"
topics: ["harness-engineering","agent-runtime"]
entities: ["Corridor","corridor-argos-1","Qwen3.5-9B","Agent Steering","SecReT","SusVibes","Baseten"]
related_patterns: ["harness-architecture-outlives-model-choice"]
novelty_label: "same_event"
what_changed: "Same event as .@corridor used smithtune’s trace-based workflow to build the training data for Argos, a fine-tuned 9B model that scores the highest of the 14 models they tested on their security context benchmark."
prior_refs: ["memory:dc85010b-9f8d-8952-a6a6-bf06026d409c"]
source_url: "https://www.corridor.dev/research/argos"
source_urls: ["https://www.corridor.dev/research/argos"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:corridor-introduces-argos-a-fine-tuned-qwen3-5-bf46d6"
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/corridor-introduces-argos-a-fine-tuned-qwen3-5-bf46d6/","markdown":"https://newruntime.com/posts/corridor-introduces-argos-a-fine-tuned-qwen3-5-bf46d6.md","json":"https://newruntime.com/posts/corridor-introduces-argos-a-fine-tuned-qwen3-5-bf46d6.json"}
---

# Corridor introduces Argos, a fine-tuned Qwen3.5-9B security model that tops 14 models on its SecReT benchmark

## Retrieval answer

Corridor announced corridor-argos-1 on October 21, 2026, a security-context selection model used in its Agent Steering product.

Corridor announced corridor-argos-1 on October 21, 2026, a security-context selection model used in its Agent Steering product. The model reads a coding agent’s plan and selects project-specific security guidance before code is written.

Argos is a fine-tuned Qwen3.5-9B model. Corridor says it trained the model using thousands of synthetic and internal traces, with Baseten Loops for managed fine-tuning and reinforcement learning. The post does not state a standalone price, public weights release, or separate access terms for Argos.

On Corridor’s SecReT benchmark, Argos scored 0.655 micro F1 across 272 requests and 1,910 plan-item pairs. Corridor reports 77.8% recall, 56.5% precision, and a 740 ms mean time to first answer token; the base Qwen3.5-9B scored 0.480 micro F1.

In a SusVibes experiment using GPT-6 Sol to implement changes, Corridor says plan-selected security context raised security correctness from 32.8% with random context items to 53.2%. These are Corridor’s reported evaluations, not independent evidence that the model improves security across repositories or coding agents.

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: [Harness Engineering](https://newruntime.com/topics/harness-engineering.md): Explore the harness-engineering topic hub.
- topic hub: [Agent Runtime](https://newruntime.com/topics/agent-runtime.md): Explore the agent-runtime 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)