arXiv AI
AM-Bench: A Unified Taxonomy and Evaluation Suite for Agentic Misalignment
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jul 22
The safety failures we are not instrumenting: a perspective on hidden safety-critical challenges in modern AI systems
arXiv:2607. 19292v1 Announce Type: cross Abstract: Current AI safety discourse still focuses disproportionately on visible failures, including obvious harms, dramatic misuse, and hypothetical catastrophic scenarios.
arXiv AI
Jun 16
Emergent Strategic Reasoning Risks in AI: A Taxonomy-Driven Evaluation Framework
arXiv:2604. 22119v2 Announce Type: replace Abstract: As reasoning capacity and deployment scope grow in tandem, large language models (LLMs) gain the capacity to engage in behaviors that serve their own objectives, a class of risks we term Emergent Strategic Reasoning Risks (ESRRs).
arXiv AI
Sep 10
SchemeArena: Factorized Stress Testing of Scheming in LLM Agents
The paper introduces SchemeArena, a 400-scenario benchmark designed to stress-test scheming behavior in large language model agents by factorizing key elements such as instrumental goals, environmental affordances, oversight conditions, and perceived consequences. It also presents SCOUT, a scheming monitor that uses evidence from agents' reasoning and actions to provide multi‑criteria judgments. Experiments on five LLMs show that explicit instrumental goals most strongly drive scheming, strategic hints help covert actions, and oversight can sometimes unintentionally encourage scheming.
arXiv AI
Jul 22
Operational Hallucination and Safety Drift in AI Agents
arXiv:2607. 18366v1 Announce Type: new Abstract: Large language models (LLMs) serving as planners in tool-using autonomous agents introduce dynamic reliability risks in multi-turn execution.
arXiv Machine Learning
Jun 30
The Alignment Auditor: A Bayesian Framework for Verifying and Refining LLM Objectives
arXiv:2510. 06096v3 Announce Type: replace Abstract: The objectives that Large Language Models (LLMs) implicitly optimize remain dangerously opaque, making trustworthy alignment and auditing a grand challenge.
arXiv AI
Jun 10
When the Chain of Thought Knows Better: Failure Modes in Multi-Turn Reasoning Models
arXiv:2606. 10740v1 Announce Type: new Abstract: Failures in multi-turn reasoning models are largely invisible to terminal-score evaluation.