# Agentic-Ideation: Sample Efficient Agentic Trajectories Synthesis for Scientific Ideation Agents arXiv: https://arxiv.org/abs/2606.31229 · HTML: https://mlsanity.com/paper/2606.31229/ ## Key facts - Cited by 3 papers in the map (data through 14 Oct 2026). - Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. - Builds on 27 of its 34 references that are in the map. - First posted on arXiv 30 Jun 2026. ## Placed in - LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/) ## Builds on (most cited first, 27 of 27) - [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025) - [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024) - [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025) - [Agent Laboratory: Using LLM Agents as Research Assistants](https://mlsanity.com/paper/2501.04227/) (2025) - [The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search](https://mlsanity.com/paper/2504.08066/) (2025) - [FireAct: Toward Language Agent Fine-tuning](https://mlsanity.com/paper/2310.05915/) (2023) - [ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models](https://mlsanity.com/paper/2404.07738/) (2024) - [WebDancer: Towards Autonomous Information Seeking Agency](https://mlsanity.com/paper/2505.22648/) (2025) - [SciMON: Scientific Inspiration Machines Optimized for Novelty](https://mlsanity.com/paper/2305.14259/) (2023) - [ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning](https://mlsanity.com/paper/2503.19470/) (2025) - [AgentSquare: Automatic LLM Agent Search in Modular Design Space](https://mlsanity.com/paper/2410.06153/) (2024) - [WebShaper: Agentically Data Synthesizing via Information-Seeking Formalization](https://mlsanity.com/paper/2507.15061/) (2025) - [AutoSurvey: Large Language Models Can Automatically Write Surveys](https://mlsanity.com/paper/2406.10252/) (2024) - [WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agent](https://mlsanity.com/paper/2508.05748/) (2025) - [AI-Researcher: Autonomous Scientific Innovation](https://mlsanity.com/paper/2505.18705/) (2025) - [Chain of Ideas: Revolutionizing Research Via Novel Idea Development with LLM Agents](https://mlsanity.com/paper/2410.13185/) (2024) - [AgentRxiv: Towards Collaborative Autonomous Research](https://mlsanity.com/paper/2503.18102/) (2025) - [Many Heads Are Better Than One: Improved Scientific Idea Generation by A LLM-Based Multi-Agent System](https://mlsanity.com/paper/2410.09403/) (2024) - [WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning](https://mlsanity.com/paper/2509.13305/) (2025) - [Towards General Agentic Intelligence via Environment Scaling](https://mlsanity.com/paper/2509.13311/) (2025) - [SurveyForge: On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automated Survey Writing](https://mlsanity.com/paper/2503.04629/) (2025) - [ResearchTown: Simulator of Human Research Community](https://mlsanity.com/paper/2412.17767/) (2024) - [SurveyX: Academic Survey Automation via Large Language Models](https://mlsanity.com/paper/2502.14776/) (2025) - [PiFlow: Principle-Aware Scientific Discovery with Multi-Agent Collaboration](https://mlsanity.com/paper/2505.15047/) (2025) - [SciPIP: An LLM-based Scientific Paper Idea Proposer](https://mlsanity.com/paper/2410.23166/) (2024) - [Agent models: Internalizing Chain-of-Action Generation into Reasoning models](https://mlsanity.com/paper/2503.06580/) (2025) - [Scientific judgment drifts over time in AI ideation](https://mlsanity.com/paper/2511.04964/) (2025) ## Built on by (most cited first, 3 of 3) - [IdeaTrail: Full-Process Agent Trajectories for Scientific Ideation](https://mlsanity.com/paper/2607.10144/) (2026) - [ShadowMiner v1 - An Experience Report on Implementing and Measuring a Problem-and-Hypothesis Discovery Engine](https://mlsanity.com/paper/2610.04339/) (2026) - [Priced Guidance: Can Language Models Generate Future Research Ideas?](https://mlsanity.com/paper/2610.04976/) (2026) ## Abstract (arXiv) Ideation plays a pivotal role in scientific discovery. Recent LLM, especially AI Scientist systems, show promising potential for automated ideation. However, existing approaches predominantly rely on pre-defined agentic workflows. This constraint severely limits the flexibility required to navigate the vast search space of scientific literature and the complex action space of research reasoning. Recently, training Agentic LLMs has emerged as a promising direction, offering flexible reasoning frameworks and the capability for autonomous tool utilization. However, there remains a non-trivial challenge: applying previous agentic data synthesis methods to scientific ideation suffers from prohibitively high data synthesis cost. To bridge this gap, we propose Agentic-Ideation, a novel framework comprising an automated trajectory synthesis pipeline and a specialized agentic LLM trained for scientific ideation. Specifically, we first define a comprehensive tool space incorporating three external tools and three cognitive tools. Then we introduce an Oracle-Guided Data Synthesis strategy. By leveraging a reference idea as oracle guidance, this approach steers the multi-agent system to efficiently reconstruct the logical reasoning and tool invocation paths, transforming aimless trial-and-error into directed trajectory generation. Finally, we train the agent on these synthesized trajectories, employing a masking strategy on tool execution results. This ensures the model focuses on decision-making logic without interference from external feedback. Experimental results demonstrate that our method outperforms the SOTA workflow-based baseline by 11.91% in overall quality. Furthermore, our approach improves the sample efficiency of high-quality data synthesis by over 10×.