Arthur Szlam
Famous AuthorPublications
SkillSmith: Learning to Compose Parametric Skills and Textual Knowledge
Agentic systems driven by large language models (LLMs) regularly feature two key mechanisms to autonomously solve complex problems: synthesizing text-based knowledge and procedures from past experiences and building parametric (weight-space) skill libraries for recurring sub-goals. To date, research has largely treated these as orthogonal pursuits: either organizing textual knowledge through composition and reflection, or consolidating parametric skills via weight-space merging. Consequently, the seamless integration of text and model weights for targeted performance improvements remains largely unexplored. This work bridges this modality gap by treating model weights as an additional modality that an LLM can natively reason over. We instantiate parametric learning via prefix-tuning and augment an LLM to ingest both prefix weights and rich textual data which capture relationships to a target capability. Our augmented LLM, which we call SkillSmith, synthesizes these inputs to perform instruction-steered parametric synthesis, directly outputting new prefix weights that manifest the target skill. We demonstrate that our approach significantly outperforms both text-only and weight-space-only baselines, unlocking performance gains that are out of reach for uni-modal (text-only or weight-only) adaptations.
Latent Space Communication via K-V Cache Alignment
Solving increasingly complex problems with large language models (LLMs) necessitates a move beyond individual models and towards multi-model systems that can effectively collaborate. While text has traditionally served as the medium for inter-model communication, a richer and more efficient exchange is possible if models can access each other's internal states directly. In this paper, we propose learning a shared representation space that aligns the k-v caches of multiple models, creating a high-bandwidth channel for collaboration without altering the underlying pre-trained parameters. We do so by augmenting each model with adapters to translate its state into and out of this shared space. Via a suite of experiments with Gemma-2 models, we demonstrate that this approach not only enables seamless inter-model communication but also improves individual model performance. We also show that the shared space allows for the direct transfer of learned skills, such as soft prompts, between different models. Our work represents a significant step towards a future where models can fluidly share knowledge and capabilities.