SciToolAgent-Evo: An Ontology-Aware Self-Evolving Agent for Open-World Scientific Tool Acquisition
arXiv AIArchived Aug 03, 2026✓ Full text saved
arXiv:2607.28692v1 Announce Type: new 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
Full text archived locally
✦ AI Summary· Claude Sonnet
Computer Science > Artificial Intelligence
[Submitted on 30 Jul 2026]
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
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.
Comments: 19 pages, 4 figures, under review
Subjects: Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
Cite as: arXiv:2607.28692 [cs.AI]
(or arXiv:2607.28692v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2607.28692
Focus to learn more
Submission history
From: Yuqi Tang [view email]
[v1] Thu, 30 Jul 2026 08:47:11 UTC (3,591 KB)
Access Paper:
HTML (experimental)
view license
Current browse context:
cs.AI
< prev | next >
new | recent | 2026-07
Change to browse by:
cs
cs.CL
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Export BibTeX Citation
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Demos
Related Papers
About arXivLabs
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)