Paper page - AIM: Agentic Idea Management for Automated Research

Source: https://huggingface.co/papers/2609.38445

Implementing and evaluating research ideas is expensive. As agents generate more candidates, choosing what to explore and learning from previous experiments becomes increasingly important. Numerous approaches have been proposed for automated research. We distinguish two ways to organize those approaches: solution-driven search, which searches directly over executable implementations, and idea-driven search, which explicitly selects research directions before delegating their implementation.

In this work, we introduce the Agentic Idea Manager (AIM), a framework that makes managing these ideas a central part of the research process. This is what AIM does:

💡 Organizes evolving ideas into semantic clusters and estimates their promise using experimental evidence. 🔍 Balances exploration of new directions with refinement of promising ones. 🔧 Audits whether implementations faithfully realize their intended ideas. ⚙️ Adaptively allocates the experimental budget across parallel search branches.

Across 10 AutoLab tasks, AIM improves average scores over the strongest baseline by: • +1.6 percentage points on System Optimization. • +4.9 percentage points on long-horizon Model Development & CUDA. It also reaches the best baseline performance up to 3.1x faster in wall-clock time.

On top of empirical results, our theoretical analysis examines when idea-level search is useful, highlighting the value of broader coverage when plausible directions to study into are sparse.