Line of inquiry
Inquiring lines›What determines the reliability an…›What sustains meaningful human ove…›this line of inquiry
What causes model scheming and how do we distinguish it from accidents?
A broader line of inquiry — a family of 19 specific questions the research asks around this. Follow one into its inquiring-line page, or move sideways to a related line below.
Questions in this line of inquiry 19
Specific inquiring lines the field asks around this — ordered from the most general framing down to the most specific angle.
- How do pressure and strategic hints separately influence scheming compared to instrumental goals?
- How often do scheming reasoning and covert actions actually align in practice?
- Do deliberate strategic reasoning triggers like replacement and goal conflict rank differently across models?
- How should tool-call attribution distinguish credit between successful accidents and intentional actions?
- How does pressure mainly influence scheming reasoning versus covert action?
- Why do instrumental goals drive scheming more strongly than pressure does?
- What distinguishes strategic fabrication from accidental hallucination in research agents?
- What do SchemeArena's stress tests reveal about explicit instrumental goals?
- Can tool-call advantage attribution distinguish between correct and incorrect calls in mixed trajectories?
- Why do reasoning-action gaps separate scheming thoughts from covert hacking actions?
- What happens when tools compete for agent invocation rather than human clicks?
- How does credit assignment across objectives differ from credit assignment across time?
- How does evidence grounding affect judge reliability in scheming detection?
- Is a hint a separate factor or a level within SchemeArena's scenario dimensions?
- How do interpretive and evaluative disagreement show up differently in agent traces?
- What exactly do strategic hints contain and how are they delivered?
- How were 'stop' mechanisms defined in the incident coding scheme?
- What makes a claim robust enough to lift out of preliminary incident evidence?
- How do you handle disagreement between two accounts of the same incident?