SkillEarth: Teaching General-Purpose Agents to Act on Earth via Skill Evolution
cs.AI, cs.CV
Submitted: 2026-11-11
Updated: 2026-11-17
Project page: https://xinr-tang.github.io/SkillEarth-homepage/Detect-and-highlight-specific-text
Terminology
Sources
- CangLing-KnowFlow: A Unified Knowledge-and-Flow-fused Agent for Comprehensive Remote Sensing Applications
- Experience-Driven Multi-Agent Systems Are Training-free Context-aware Earth Observers
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Designing Domain-Specific Agents via Hierarchical Task Abstraction Mechanism
- MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation
- LHRS-Bot: Empowering Remote Sensing with VGI-Enhanced Large Multimodal Language Model
- Anything2Skill: Compiling External Knowledge into Reusable Skills for Agents
- Qwen2.5 Technical Report
- Qwen3 Technical Report
- OpenEarthAgent: A Unified Framework for Tool-Augmented Geospatial Agents
- RestGPT: Connecting Large Language Models with Real-World RESTful APIs
- AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution
- ExpeL: LLM Agents Are Experiential Learners
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