AIM: Agentic Idea Management for Automated Research

2026-09-29

AI Summary

This study addresses the challenges of idea organization, research direction selection, and implementation alignment in automated scientific discovery by proposing an autonomous research management framework. Inspired by Bayesian optimization, the framework constructs a surrogate model and an acquisition mechanism to enable controllable semantic search. Furthermore, it introduces a solution auditor and a resource planner to jointly optimize research strategies and computational allocation. Experimental results demonstrate that the proposed method surpasses the strongest baselines on standard benchmarks, achieving a 3.1-fold improvement in execution efficiency for long-horizon tasks. These findings significantly advance the level of autonomy in AI-driven scientific research.

Abstract

Frontier LLMs are increasingly used to automate scientific research through iterative search. We distinguish idea-driven search from solution-driven search and identify three core challenges: organizing evolving research ideas, selecting promising directions, and maintaining alignment between ideas and their implementations. To address these challenges, we introduce the Agentic Idea Manager (AIM), a fully autonomous framework for managing and exploring research directions in idea-driven automated research. Inspired by Bayesian optimization, AIM uses an Agentic Surrogate and an Agentic Acquisition mechanism to organize discovered ideas and guide their selection. A Solution Auditor maintains idea-solution integrity, while a Resource Planner adaptively allocates the remaining experimental budget across parallel search branches. Experiments on 10 AutoLab benchmark tasks show that AIM surpasses the strongest baseline by 1.6 percentage points on System Optimization tasks and 4.9 percentage points on long-horizon Model Development & CUDA tasks. Notably, AIM reaches the best baseline performance up to 3.1x faster in wall-clock time. We further provide a theoretical analysis of when searching over ideas becomes beneficial. Our analysis shows that explicit idea-level allocation makes semantic coverage directly controllable, and that broader coverage becomes increasingly valuable when competitive research directions are sparse among many plausible alternatives. Project Page: https://imhgchoi.github.io/agentic-idea-manager/

Innovation

• Agentic Idea Management
• Bayesian Optimization
• Automated Scientific Research
• Resource Allocation
• Idea-driven Search