arXiv (All)
open access
Calibration Is Not Control: Intervention Value for LLM-Agent Oversight
Runtime oversight often intervenes when an LLM agent's calibrated failure score crosses a threshold. Yet states with the same failure risk can differ in whether intervention helps. Strictly increasing recalibration preserves the threshold policy class and cannot recover this distinction. We formaliz
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
- Re-executing Coding-Agent Evaluations: Unchanged Decisions and Unresolved Policy Risk#1325356
- Identification of causal policy effects for spatial exposure fields#1084450
- Auditable Agents#1291895
- Memory That Changes Action Is Not Memory That Guides It: Counterfactual Auditing of History-Conditioned Robot Policies#1063458
- Who Tests the Testers? Systematic Enumeration and Coverage Audit of LLM Agent Tool Call Safety#614959
Record · ID 1217499
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