AI/ ai · llm · agents · research

SoftSkill Replaces Markdown Prompts With Latent Model Controls

A new frozen-backbone method encodes agent skills as compact vector prefixes, outperforming text-based skill prompting by wide margins on several benchmarks.

A research paper proposes replacing the Markdown files that teach AI agents how to behave with tiny learned vectors baked directly into a model's context.

The technique, called SoftSkill, keeps a language model's weights frozen and instead trains a short "soft" prefix — just 32 tokens of continuous vectors — that steers how the model approaches a task. Tested on Qwen3.5-4B, SoftSkill beat no-skill prompting by 8.3 points on SearchQA, 42.1 points on LiveMath, and 1.3 points on DocVQA. Against SkillOpt, a prior text-based approach, it gained 5.2 points on SearchQA and 12.5 points on LiveMath — while swapping out hundreds or thousands of Markdown tokens for a handful of latent ones. The base model never changes; only the prefix is trained.

Right now, deploying a skill to an AI agent usually means writing a Markdown file that describes what the agent should do and hoping the model interprets it consistently at runtime. SoftSkill short-circuits that translation step, which matters because every extra token in a prompt adds latency and cost, and language models can misread long instruction files in ways that are hard to debug. Compressing behavioral policies into fixed-size vector prefixes makes skills faster, cheaper, and more reproducible.

The paper is honest about where the approach breaks down: for long-horizon agentic tasks — multi-step tool use, autonomous workflows — sparse trajectory data doesn't yet compress procedural behavior reliably, which means the Markdown file isn't going anywhere for complex agents just yet.

TR

The Revision

Written by an AI system from the public sources credited above. How we write →