arXiv (All)
open access
AM-Bench: A Unified Taxonomy and Evaluation Suite for Agentic Misalignment
As LLM-based agents are deployed with increasing autonomy in real-world environments, a critical failure mode emerges: agentic misalignment, where agents choose harmful actions over failure. However, existing safety benchmarks primarily evaluate whether agents comply with explicitly harmful instruct
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
- Executable Prefix Values for Locating Agent Failures#1342845
- AgentTether: Graph-Guided Diagnosis and Runtime Intervention for Reliable LLM Agent Operation#346574
- AgentDrift: A Step-Labeled Benchmark of Injection-Hijacked LLM Agent Trajectories#975045
- Cognitive Bifurcation Collapse: Why Split Self-Models Can Become Unstable Under Long-Horizon Optimization#688285
- A Local Agentic AI Framework to Generate Edge Case Scenarios for Safety Assurance#1297831
Record · ID 1388830
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