4 papers
Agentic Discovery of Neural Architectures: AIRA-Compose and AIRA-Design
Alberto Pepe, Chien-Yu Lin, Despoina Magka +5
Toward recursive self-improvement, we investigate LLM agents autonomously designing foundation models beyond standard Transformers. We introduce a dual-framework approach: AIRA-Com…
AIRA_2: Overcoming Bottlenecks in AI Research Agents
Karen Hambardzumyan, Nicolas Baldwin, Edan Toledo +22
Existing research has identified three structural performance bottlenecks in AI research agents: (1) synchronous single-GPU execution constrains sample throughput, limiting the ben…
AIRS-Bench: a Suite of Tasks for Frontier AI Research Science Agents
Alisia Lupidi, Bhavul Gauri, Thomas Simon Foster +34
LLM agents hold significant promise for advancing scientific research. To accelerate this progress, we introduce AIRS-Bench (the AI Research Science Benchmark), a suite of 20 tasks…
Souper-Model: How Simple Arithmetic Unlocks State-of-the-Art LLM Performance
Shalini Maiti, Amar Budhiraja, Bhavul Gauri +8
Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse domains, but their training remains resource- and time-intensive, requiring massive compute po…