Where Reliability Lives: Experimental Localisation of Behavioural Properties in an Agent System
4.00T1 sourcearXiv cs.MA
Source record
Published by arXiv cs.MA (T1 source). The original is at https://arxiv.org/abs/2609.03192.
Pipeline notes
The summary and note below are generated by the signal pipeline — they are Beyond Desk’s reading, not quotations from the source.
SummaryArXiv paper experimentally localizing reliability properties in an agent system built around an append-only ledger adjudicator. Interventions on institutional epistemic mechanisms and on cognition (ablation, mid-task reset, frontier-LLM substitution, false testimony) left five core properties intact: singular accepted reality, typed refusals, durable duties, no double-acceptance, and no false completions across 2,581 substituted-panel claims.
Why it mattersProvides empirical evidence that reliability in agent systems can live in institutional machinery rather than in the model, a structural claim with direct design implications for agentic workflows.
Cited by
No citations on record.
