arXiv (All)
open access
The Delegation Danger Band: Why Mid-Capability Sub-Agents Over-Trust Inherited Stale State
Agent frameworks increasingly delegate work by forking sub-agents; a common default makes the child inherit the parent's full working context. We measure how the effect of inherited state changes with capability, where $C_m$ denotes clean fork-fresh accuracy. We compare 3 inheritance policies: Reset
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
- Spawn Freely, Act Sparingly: Progressive Risk Vesting for Recursive LLM-Agent Trees#821023
- Simulate to Generalize: Scaling Stateful Supervision for API-calling Agents using LLM World Models#1052239
- Multi-agent Scaling Across Disjunctive and Compensatory Tasks#1106262
- NexForge: Scaling Agent Capabilities through Requirement-Driven Task Synthesis for LLMs#381815
- SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Research#267686
Record · ID 1154664
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