arXiv (All)
open access
Spawn Freely, Act Sparingly: Progressive Risk Vesting for Recursive LLM-Agent Trees
Recursive LLM agents can broaden their search by spawning specialists. Some branches later request tools that send data or deploy code. When should a branch receive authority to act? We distinguish sandbox spawning, in which external controls prevent the specified harm, from capability activation, i
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
- Understanding Agent-Reactive Bugs at the Model-Harness Boundary: An Empirical Study of LLM Agent Issue Reports#381813
- The Delegation Danger Band: Why Mid-Capability Sub-Agents Over-Trust Inherited Stale State#1154664
- LLMs for Executable Multi-Agent System Specification Generation#1128881
- LLM Agent Capabilities Should Follow Task Intent and Context Source#1084570
- LLM Agent Capabilities Should Follow Task Intent and Context Source#919502
Record · ID 821023
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