Agentic-Ideation: Sample Efficient Agentic Trajectories Synthesis for Scientific Ideation Agents

• URL: http://arxiv.org/abs/2606.31229v1
• Date: Tue, 30 Jun 2026 07:07:51 GMT
• Title: Agentic-Ideation: Sample Efficient Agentic Trajectories Synthesis for Scientific Ideation Agents
• Abstract summary: Ideation plays a pivotal role in scientific discovery.<n>Agentic-Ideation is a novel framework comprising an automated trajectory synthesis pipeline and a specialized agentic LLM trained for scientific ideation.
• Score: 9.918296068965665
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 \textbf{11.91\%} in overall quality. Furthermore, our approach improves the sample efficiency of high-quality data synthesis by \textbf{over 10$\times$}.

Related papers

• From Atomic Actions to Standard Operating Procedures: Iterative Tool Optimization for Self-Evolving LLM Agents [90.3279207163486]
  EvoSOP is a framework that empowers agents to extract SOPs from execution trajectories and iteratively optimize the toolset.<n>We show that EvoSOP significantly boosts task success rates while substantially reducing the number of interaction rounds.
  arXiv  Detail & Related papers  (2026-07-08T12:09:49Z)
• Assistance to Autonomy: A Systematic Literature Review of Agentic AI across the Software Development Life Cycle [4.241377338556251]
  This study contributes a comprehensive characterization of the current literature on agentic systems in software product development.<n>It also provides a methodological contribution in the form of an AI-assisted tool to automate the screening phase in high-volume SLR domains.
  arXiv  Detail & Related papers  (2026-05-14T10:46:51Z)
• Understanding by Reconstruction: Reversing the Software Development Process for LLM Pretraining [66.89012795621349]
  Large Language Models (LLMs) often struggle with the deep, long-horizon reasoning required for complex software engineering.<n>We propose a novel paradigm: understanding via reconstruction.<n>We introduce a framework that synthesizes latent agentic trajectories using a multi-agent simulation.
  arXiv  Detail & Related papers  (2026-03-11T09:23:20Z)
• Towards Agentic Intelligence for Materials Science [73.4576385477731]
  This survey advances a unique pipeline-centric view that spans from corpus curation and pretraining to goal-conditioned agents interfacing with simulation and experimental platforms.<n>To bridge communities and establish a shared frame of reference, we first present an integrated lens that aligns terminology, evaluation, and workflow stages across AI and materials science.
  arXiv  Detail & Related papers  (2026-01-29T23:48:43Z)
• ASTRA: Automated Synthesis of agentic Trajectories and Reinforcement Arenas [13.919124676472022]
  ASTRA is an end-to-end framework for training tool-augmented language model agents.<n>ASTRA integrates scalable data synthesis and verifiable reinforcement learning.<n> Experiments on multiple agentic tool-use benchmarks demonstrate that ASTRA-trained models achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-01-29T11:22:23Z)
• Simple Agents Outperform Experts in Biomedical Imaging Workflow Optimization [69.36509281190662]
  Adapting production-level computer vision tools to bespoke scientific datasets is a critical "last mile" bottleneck.<n>We consider using AI agents to automate this manual coding, and focus on the open question of optimal agent design.<n>We demonstrate that a simple agent framework consistently generates adaptation code that outperforms human-expert solutions.
  arXiv  Detail & Related papers  (2025-12-02T18:42:26Z)
• Demystifying Reinforcement Learning in Agentic Reasoning [90.3737088727791]
  We conduct a comprehensive and systematic investigation to demystify reinforcement learning in agentic reasoning.<n>We highlight our key insights: (i) replacing stitched synthetic trajectories with real end-to-end tool-use trajectories yields a far stronger SFT.<n> Exploration-friendly techniques are crucial for agentic RL, such as clip higher, overlong reward shaping, and maintaining adequate policy entropy could improve the training efficiency.
  arXiv  Detail & Related papers  (2025-10-13T17:57:15Z)
• SFR-DeepResearch: Towards Effective Reinforcement Learning for Autonomously Reasoning Single Agents [93.26456498576181]
  This paper focuses on the development of native Autonomous Single-Agent models for Deep Research.<n>Our best variant SFR-DR-20B achieves up to 28.7% on Humanity's Last Exam benchmark.
  arXiv  Detail & Related papers  (2025-09-08T02:07:09Z)
• LARC: Towards Human-level Constrained Retrosynthesis Planning through an Agentic Framework [11.438071610913163]
  We present LARC, the first LLM-based Agentic framework for Retrosynthesis planning under Constraints.<n>LARC incorporates agentic constraint evaluation, through an Agent-as-a-Judge, directly into the retrosynthesis planning process.<n>We rigorously evaluate LARC on a carefully curated set of 48 constrained retrosynthesis planning tasks across 3 constraint types.
  arXiv  Detail & Related papers  (2025-08-16T01:05:26Z)
• LaMDAgent: An Autonomous Framework for Post-Training Pipeline Optimization via LLM Agents [3.6117068575553595]
  We introduce LaMDAgent, a framework that autonomously constructs and optimize full post-training pipelines.<n>LaMDAgent improves tool-use accuracy by 9.0 points while preserving instruction-following capabilities.<n>It uncovers effective post-training strategies that are often overlooked by conventional human-driven exploration.
  arXiv  Detail & Related papers  (2025-05-28T04:30:51Z)
• Tool-Star: Empowering LLM-Brained Multi-Tool Reasoner via Reinforcement Learning [63.31585771716123]
  Large language models (LLMs) have shown remarkable reasoning capabilities via large-scale reinforcement learning (RL)<n>We introduce Tool-Star, an RL-based framework designed to empower LLMs to autonomously invoke multiple external tools during stepwise reasoning.<n>Tool-Star integrates six types of tools and incorporates systematic designs in both data synthesis and training.
  arXiv  Detail & Related papers  (2025-05-22T09:00:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.