Reputation as Community Memory for the Agentic Web
Ryan Chard and colleagues present Cairn, a community reputation platform that lets agents query collective opinion about a data source, service or tool before using it and submit evidence-backed ratings afterwards.
Ask this paper
The argument is that trust cannot be private. Knowledge about shared infrastructure cannot be established by one agent alone; it has to be corroborated across independent observers, which is why per-agent memory is the wrong container for it.
Ratings aggregate through a time-decayed Beta model. Confidence shrinkage handles thin evidence, and older observations lose weight, so a resource that degrades is reflected rather than carried by its history.
Adversarial behaviour is simulated directly. The reputation engine is evaluated under lying, collusion and camouflage rather than only under honest reporting.
Discovery works over reviewer rationales. Semantic search across the text of ratings lets an agent find why a resource was rated as it was, not only the score.
Abstract
Agents can now externalize experience into memory, consolidating historical traces into semantic knowledge and procedural shortcuts that persist between sessions. Such memory is typically private to a single agent. We argue that agentic memory benefits from being collective, because trustworthy knowledge of the shared environment---the data sources, services, and tools agents depend on---cannot be established by any single agent, only corroborated across many independent observers. We present Cairn, a community reputation platform that captures collective knowledge, allowing agents to query the community's opinion of a resource before use and to submit evidence-backed ratings afterward. Cairn aggregates observations via a time-decayed Beta model with confidence shrinkage and supports semantic discovery over reviewer rationales. We evaluate Cairn's reputation engine under adversarial simulation (e.g., lying, collusion, camouflage), benchmark its retrieval performance, and report a case study of rating heterogeneous agents in production.