Not All Experience Belongs in the Weights: Component Routing for Self-Improving GUI Agents
cs.AI, cs.GR
Submitted: 2026-10-01
Updated: 2026-10-01
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- From Confident Closing to Silent Failure: Characterizing False Success in LLM Agents
- Qwen3-VL Technical Report
- Rethinking Continual Experience Internalization for Self-Evolving LLM Agents
- EASE: Federated Multimodal Unlearning via Entanglement-Aware Anchor Closure
- Skill-Guided Continuation Distillation for GUI Agents
- Shared Spatial Memory Through Predictive Coding
- Sample-Efficient Learning from Agent Experience
- Are Online Skill and Memory Modules Always Worth Their Tokens? A Budget-Constrained Study of Web Agents
- SCAFFOLD: Self-Improving Web Agents via Recursive Parametric Skill Abstraction
- From Interaction Traces to Persistent Skills: Online Evolution for Computer-Use Agents
- Learning What to Remember and What to Internalize in LLM Self-Evolution via Adaptive Memory-Parameter Coordination
- WHALE: A Simple Recipe for Joint Harness-Weight Optimization
- Learn from Weaknesses: Automated Domain Specialization for Small Computer-Use Agents
- Multi-Agent Transactive Memory
- On the generalization of language models from in-context learning and finetuning: a controlled study
- Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents
- SkillLens: Visual Skill Cards for Retrieval-Augmented GUI Action Prediction and On-Policy Distillation
- Learning to Learn from Multimodal Experience
- FedSceneX: Time-to-Target Orchestration for Same-Scene Multimodal Federated Edge Learning
- CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents
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