SOURCE-LINKED INTELLIGENCE

Toward Latent Language Model Skills Steering and Optimization: An Empirical Study

arXiv · AI, language, vision and robotics · article · Aug 29, 2026 · UTC

Skills, as a useful abstraction for the procedural capabilities of large language models (LLMs), capture how models perform structured, multi-step reasoning and program execution. Existing approaches typically treat skills as explicit, surface-level constructs specified through prompts or programs, leaving open the question of how such procedural capabilities are represented inside the model and whether they can be manipulated as structured objects in latent space. In this empirical study, we investigate whether procedural LLM skills can be represented as directions in activation space and whe

Read original source ↗ Open in workspace

recordType

paper

region

Global