arXiv CS
open access
LEASH: Uncertainty-Aware Weak-to-Strong Escalation and Oversight for Computer-Use Agents
Computer-use agents increasingly tackle long-horizon tasks, where running a frontier model at every step is expensive and a small open-weight model alone often fails. Weak-to-strong escalation offers a middle ground where a weak agent acts by default and hands control to a strong one only when neede
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- LEASH: Uncertainty-Aware Weak-to-Strong Escalation and Oversight for Computer-Use Agents#1357935
- Modeling and analysis of uncertain time-critical tasking problems (UTCTP)#1227764
- Teaching Agents to Code Reliably#1199258
- A Self-Defining Operator for Distributed Applications#1325443
- Recursive Admissibility Corridors - Dynamic Tolerance Expansion and Convergence Under Weighted Cognitive Traversal#704224
Record · ID 1348892
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive