safety security
Every Agent Was Right. The Team Was Still Wrong.
A study argues that missing shared state, not weaker reasoning, sets a hard boundary on multi-agent coordination.
Summary
A study argues that missing shared state, not weaker reasoning, sets a hard boundary on multi-agent coordination.
The global-coherence study formalizes a failure in which every agent's local choice is valid but the combined action violates a shared constraint because decisive state is invisible. In controlled tests, a frontier model scored 40 of 40 when the deciding event was visible, fell to 12–17 of 40 when it was hidden, and returned to 40 of 40 when one authoritative fact was restored. On a shared-budget task, ordinary teams exceeded the limit in all five runs; a visible live count still left four violations, while commit enforcement left none. The results support the paper's architectural claim for its tested settings: models may propose, but a harness that owns shared state must govern commit.
Why it matters
A study argues that missing shared state, not weaker reasoning, sets a hard boundary on multi-agent coordination.
Limits and context
No additional limitation was separately recorded.
Key claims
A study argues that missing shared state, not weaker reasoning, sets a hard boundary on multi-agent coordination.
Evidence: source-2026-10-03-002
Sources
- arXiv preprint 2610.02036arXiv · primary research
Corrections
No corrections have been recorded for this story.