# Fine-Tuning Is Often the Wrong First Move: Introducing Harneloop

When an agent repeatedly fails at a narrow task, changing model weights is often not the most direct fix.

The failure may come from missing context, weak tools, incomplete retrieval, poor validation, or an environment the agent cannot inspect. Those are harness problems.

I open-sourced [Harneloop](https://github.com/Ker102/Harneloop) to give agents a structured way to improve that system through real attempts and verifiable evidence.

## How Harneloop works

The operating agent attempts the target task, captures the resulting artifacts and traces, evaluates the outcome, and follows likely mistakes back through the run.

It then creates an isolated candidate change to the harness.

The candidate can change instructions, tools, retrieval, examples, validators, environment automation, skills, or other task-specific infrastructure. It is tested separately and promoted only if the evidence supports an improvement without unacceptable regressions.

This keeps experimentation flexible while preventing the agent from silently rewriting the current working harness.

## Artifact-aware evaluation

Many useful agent tasks produce outputs that cannot be judged from the transcript alone.

An interface can compile but be visually wrong. A generated document can be valid but ineffective. A scene can render while its spatial relationships are incorrect. A browser agent can execute every action but leave the application in the wrong state.

Harneloop treats those artifacts as evidence. It links them to the run that produced them so the agent can inspect the actual result and diagnose the likely system-level cause.

## Portable harness units

Harneloop stores each task-specific development environment as a **harness unit**.

A harness unit contains:

- the task goal and current operational map;
- reusable instructions, tools, retrieval, and validators;
- candidate changes and evidence references;
- regression cases and promoted versions;
- custom infrastructure the agent needs for that task.

The framework protects lifecycle state and promotion integrity without forcing every task into a single template. Successful harness units can be restored, continued, packaged, moved, or exported into another agent environment.

## Harness-first does not mean fine-tuning never matters

[SWE-agent](https://arxiv.org/abs/2405.15793), [Reflexion](https://arxiv.org/abs/2303.11366), and [Self-Refine](https://arxiv.org/abs/2303.17651) all provide evidence that interfaces, feedback, memory, and iterative refinement can materially change model performance without additional training.

The 2026 [Self-Harness](https://arxiv.org/abs/2606.09498) paper goes closer to Harneloop's core direction: agents mined weaknesses from execution traces, proposed harness modifications, and accepted them after regression testing.

Fine-tuning can still be useful for specialized behavior, style, latency, representations, or capabilities that cannot be supplied effectively at inference time. A fine-tuned model can also benefit from a strong harness.

The useful decision rule is:

> If failures come from context, tools, retrieval, feedback, validation, memory, or environment interaction, improve and measure the harness before changing model weights.

## The first measured use case

Harneloop was first used to develop ViperMesh, a Blender harness for spatial reasoning and scene generation.

The acting model was held constant at OpenAI GPT 5.5 High. Compared with the Anthropic x Blender MCP server baseline across seven comparable live tasks, the evolved ViperMesh harness:

- was faster on **6 of 7** tasks;
- achieved a **2.534x mean speedup**;
- improved preliminary neutral LLM visual evaluation by **8.19 points**.

Harneloop did not generate the scenes. It structured the evidence loop used to diagnose failures, develop the harness, and verify improvements.

The [full case study](https://www.kristoferjussmann.me/case-studies/vipermesh) includes the methodology and limits. This is one task family, not a universal comparison against every fine-tuning method.

## Try it

Harneloop is designed for agent-led onboarding. Give the [GitHub repository](https://github.com/Ker102/Harneloop) to a capable coding agent and describe the task you want to improve. The agent can install it, map the actual environment, and create the first harness unit.

I am looking for independent use cases beyond Blender, including negative results. Feedback about onboarding, environment mapping, evidence quality, token cost, candidate decisions, and capability limits will directly shape the framework.

**Repository:** https://github.com/Ker102/Harneloop  
**Case study:** https://www.kristoferjussmann.me/case-studies/vipermesh