skill-composition

Tag

Cards List
#skill-composition

@rohanpaul_ai: New Google DeepMind Paper. Model weights do not have to remain static artifacts that can only be fine-tuned or averaged…

X AI KOLs Following · 2026-08-02 Cached

A new Google DeepMind paper, SkillSmith, treats prefix key-value caches as an input modality, composing textual knowledge and existing weights into a fresh prefix cache for a frozen Gemma 3 4B model at inference time, improving adaptation without a target-specific training run.

0 favorites 0 likes
#skill-composition

@omarsar0: New research from Google DeepMind. (bookmark it) SkillSmith treats model weights as an additional modality the LLM read…

X AI KOLs Following · 2026-08-02 Cached

Google DeepMind introduces SkillSmith, which treats model weights as an additional modality that LLMs can natively reason over, enabling instruction-steered parametric synthesis for composing skills at inference time. The approach outperforms text-only and weight-only baselines.

0 favorites 0 likes
#skill-composition

SkillSmith: Learning to Compose Parametric Skills and Textual Knowledge

arXiv cs.CL · 2026-07-31 Cached

This paper introduces SkillSmith, an LLM augmented to reason over both prefix weights and textual knowledge, enabling instruction-steered synthesis of new parametric skills that outperform text-only and weight-only baselines.

0 favorites 0 likes
#skill-composition

SkillCoach: Self-Evolving Rubrics for Evaluating and Enhancing Agentic Skill-Use

Hugging Face Daily Papers · 2026-07-02 Cached

SkillCoach introduces a self-evolving rubric framework that evaluates and enhances LLM agent skill-use by analyzing skill selection, following, composition, and reflection, providing process-level supervision beyond outcome-only metrics.

0 favorites 0 likes
← Back to home

Submit Feedback