SciToolAgent-Evo: An Ontology-Aware Self-Evolving Agent for Open-World Scientific Tool Acquisition
Yuqi Tang, Chenyi Zhou, Libin Wang, Keyan Ding, Qiang Zhang, Huajun Chen
cs.AI, cs.CL
Submitted: 2026-07-30
Comments: 19 pages, 4 figures, under review
License: http://creativecommons.org/licenses/by/4.0/
The gist: Large language model (LLM) agents have been increasingly adopted in scientific research for organizing and invoking specialized computational tools.
Terminology
Abstract
Large language model (LLM) agents have been increasingly adopted in scientific research for organizing and invoking specialized computational tools. However, their reliance on predefined tool spaces with static semantics limits their applicability to open-world scientific workflows, where tool requirements, capabilities, and boundaries evolve dynamically. To this end, we propose SciToolAgent-Evo, an ontology-aware self-evolving agent for open-world scientific tool acquisition. Driven by an evolving memory of skills, experiences, and an ontologized tool graph, it distills generalizable knowledge from contrastive trajectories during accumulation, whereas during inference, it formulates active requests and utilizes a LinUCB-based bandit gate to dynamically balance exploration and exploitation. Once a novel tool is acquired, its scientific ontology is completed online for seamless integration into the known graph. Moreover, we introduce OpenSciToolBench, a benchmark containing 900 realistic tasks across four difficulty levels. Extensive evaluations show that SciToolAgent-Evo achieves state-of-the-art performance, validating its robustness and generalization.
Sources
- XSkill: Continual Learning from Experience and Skills in Multimodal Agents
- ART: Automatic multi-step reasoning and tool-use for large language models
- RestGPT: Connecting Large Language Models with Real-World RESTful APIs
- ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases
- Learning an Efficient Multi-Turn Dialogue Evaluator from Multiple LLM Judges
- Gemini: A Family of Highly Capable Multimodal Models
- Qwen3 Technical Report
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems