ScienceCUA: Resource-to-Skill Construction and Execution-Guided Skill Evolution for Scientific Computer Use Agents
cs.AI
Submitted: 2026-11-02
Updated: 2026-11-02
Project page: https://texstudio-org.github.io
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- SciVisAgentBench: A Benchmark for Evaluating Scientific Data Analysis and Visualization Agents
- EvoSkill: Automated Skill Discovery for Multi-Agent Systems
- Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale
- MMG2Skill: Can Agents Distill In-the-Wild Guides into Self-Evolving Skills?
- SkillCAT: Contrastive, Assessment-Augmented and Topology-AwareSkill Self-Evolution for LLM Agents
- RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources
- VISUALSKILL: Multimodal Skills for Computer-Use Agents
- SkillForge: Forging Domain-Specific, Self-Evolving Agent Skills in Cloud Technical Support
- Qwen-CUA: Native Computer Use for (almost) Everything
- SCALECUA: Scaling Computer Use Agents with Verifiable Task Synthesis and Efficient Online RL
- Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
- UI-TARS: Pioneering Automated GUI Interaction with Native Agents
- Bioinfoysis Technical Report
- SKILLFOUNDRY: Building Self-Evolving Agent Skill Libraries from Heterogeneous Scientific Resources
- SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience
- SkillOpt: Executive Strategy for Self-Evolving Agent Skills
- CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- 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
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents