]> Alter Meridian Pty Ltd

blake@truealter.com

Applications and Real-Time Independent Submission autonomous agents belief resolution staleness provenance uncertainty A recurring class of autonomous-agent failure arises when an agent acts on a belief read from a cached, derived, or proxy copy that has silently diverged from the authority the belief claims to represent. This document describes a reference-resolution discipline for the working beliefs an agent reasons and acts from. Each belief is held as a reference to a single named lowest authority and is resolved live at the point of use, with verification. When the authority is unobservable or the resolved value is stale, the belief takes an explicit uncertainty state rather than a prior cached value; that state propagates to any belief derived from it, and an uncertain belief feeding a costly or irreversible act blocks or escalates rather than proceeding. Every resolution chain terminates in a single self-authorising root. The document is Informational. It records a discipline and a vocabulary; it does not define a wire protocol.

Introduction An autonomous agent holds many working beliefs: the current value of a configuration item, which record is authoritative, whether a code path is still live, what the present state of a shared resource is. A wide class of agent errors has one shape. The agent reads such a belief from a copy that once matched an authority but has since diverged, and acts on the copy as though it were the authority. Common instances include a stale index read in place of the canonical registry, an ambient assumption carried across calls, a retained but superseded code path treated as current, and a narrative document trusted for a value that a live system actually owns. Existing mechanisms address adjacent concerns. Capability systems govern the authority to act. Content-addressing and transparency logs govern the naming and integrity of data and artefacts. Message-signature schemes such as bind a request to a key. None of these govern the working beliefs an agent reasons from, and none defines what an agent should do when the authority for a belief cannot be observed at the moment the belief is needed. This document describes a discipline for that layer. It is deliberately narrow. It concerns the resolution of a belief against its authority, the handling of staleness, and the termination of resolution chains. It does not describe how any particular authority is implemented, how capabilities or credentials are provisioned, or how conflicting assertions from multiple agents are arbitrated.

Terminology The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT", "SHOULD", "SHOULD NOT", "RECOMMENDED", "NOT RECOMMENDED", "MAY", and "OPTIONAL" in this document are to be interpreted as described in BCP 14 when, and only when, they appear in all capitals, as shown here.

Belief:

A value on which an agent will act.

Authority:

The single named source that owns the current value of a belief. An authority is the lowest source in a precedence order that can answer for the belief: for a live value, a running system rather than a document describing it.

Reference:

A stable identifier for a belief together with the name of its authority, held in place of a stored value.

Resolution:

The act of dereferencing a reference against its named authority to obtain a current value, at the point of use.

Point of use:

The moment, contemporaneous with the act that consumes a belief, at which resolution occurs. Resolution performed earlier and cached is not resolution at the point of use.

Uncertainty state:

An explicit value a belief takes when its authority is unobservable, its resolved value fails verification, or a freshness bound is exceeded.

Constitutive root:

A self-authorising source that answers for itself, such as a cryptographic key or a ratified decision record, in which a resolution chain terminates.

The resolution discipline

Belief as reference An agent SHOULD hold a belief on which it will act as a reference rather than a stored value. The reference names the belief and its single lowest authority. Holding the belief as a reference is what makes live resolution possible; a value copied into the agent's state carries no way to detect that the authority has since changed.

Live resolution at the point of use An agent SHOULD resolve a reference at the point of use, contemporaneously with the act that consumes the belief, by dereferencing the named authority to obtain a current value and verifying that value against the authority. A cached, derived, or proxy copy of the belief SHOULD NOT stand in for a live dereference of the named authority at the point of an act. Where an authority is expensive to dereference on every use, an agent MAY apply a bounded exemption only when all of the following hold: the belief follows from an observed fact under current semantics, the cost of being wrong is small and readily reversible, and either a fail-closed check catches the wrong case or the belief decays at a boundary served by a live change-detection channel. A belief feeding a costly, irreversible, or externally visible act MUST NOT be exempted and MUST be re-resolved against its authority at the point of use.

Authority precedence Where more than one source could answer for a belief, the authority is the lowest source in a precedence order that places an executing system above an artefact generated or enforced by continuous integration, above a hand-maintained document. A value claimed by a lower-precedence source MUST NOT override a live dereference of a higher-precedence authority. A document labelling itself authoritative is not, by that label, the authority.

Uncertainty

The uncertainty state When the named authority is unobservable, the resolved value fails verification, or a declared freshness bound is exceeded, the belief MUST take the explicit uncertainty state rather than a prior cached value. Freshness MAY be expressed per authority as a maximum staleness interval or a monotonically-advancing epoch, and crossing the bound triggers the uncertainty state without requiring an affirmative invalidation message from the authority. The uncertainty state is a first-class value that a belief carries, not the absence of a value and not a low numeric confidence attached to an asserted value.

Contagion The uncertainty state is contagious. An agent MUST propagate it to every belief derived, in whole or in part, from an uncertain belief, so that the state is carried across the agent's belief graph rather than terminating at the belief that first became uncertain. Two warranted beliefs that resolve to contradictory values cancel to the uncertainty state rather than being reconciled by a precedence pick, forcing re-resolution or escalation.

The consumer contract Uncertainty is default-closed at the point of consumption. When an uncertain belief is an input to an act classified as costly or irreversible, the agent MUST block the act or escalate for resolution rather than proceed on the uncertain belief. The classification of an act as costly or irreversible is itself a belief resolved under this discipline. The obligation applies to the conjunction of several uncertain inputs, so that two or more individually marginal uncertainties compound into the obligation to block. This consumer contract is the point of the discipline. Marking a belief uncertain achieves nothing unless a downstream consumer is obliged to act on the mark. Making the obligation explicit and mechanical answers the objection that degrading a belief to uncertainty merely moves the problem downstream.

Chain termination Every resolution chain MUST terminate in exactly one constitutive root, a self-authorising source drawn from a closed set such as a cryptographic key or a ratified decision record. A constitutive root answers for itself and fails closed; it is conferred from outside the belief graph rather than being another belief inside it. Before an act, an agent SHOULD reject a reference whose resolution chain is circular or fails to terminate in such a root, and SHOULD record which reference was rejected. This gives resolution a static termination guarantee and rejects un-rooted or circular belief references before they can drive an act. A ratified decision that supersedes an implementation outranks a retained but unmarked instance of that implementation. A belief in the liveness of the superseded implementation takes the uncertainty state until the implementation is removed or carries a machine-readable supersession marker.

The resolution result An agent that exposes belief resolution to other components SHOULD return, with the value and atomically bound to it, at least: the identifier of the authority that answered, a freshness indicator, and a provenance type. Binding these to the value means no consumer can obtain the value without also obtaining its authority, its recency, and how it was known. A provenance type is drawn from a closed set. This document does not define the set normatively, but distinguishing at least a direct read of an authority, a presumption, and an unverified inference is RECOMMENDED. A value carrying a presumption or an unverified-inference provenance type MUST NOT be relabelled as a direct read by any downstream consumer.

Relationship to other work This discipline is complementary to, and distinct from, several adjacent mechanisms. It concerns beliefs, not the authority to act; it therefore complements capability and delegation systems rather than replacing them. It concerns live resolution and staleness handling, not the integrity of static artefacts; it therefore composes with content-addressing and transparency logs. The provenance type introduced here generalises the per-observation provenance tags described in . Arbitration among several already-emitted and conflicting assertions, and the provisioning of capabilities or credentials, are out of scope for this document.

Security Considerations The discipline relocates trust rather than removing it. An agent following this discipline trusts its authorities and the freshness bounds it declares for them. The gains are that the trust is placed in a single named source per belief, that the source is re-checked at the point of use, and that failure to observe the source degrades to an explicit blocking state rather than to silent use of a stale value. An implementation that declares over-generous freshness bounds, or that permits a lower-precedence source to answer for a belief, weakens these gains. Constitutive roots are the base of trust. Compromise of a cryptographic key or subversion of the process that ratifies a decision record compromises every belief whose chain terminates in that root. Roots therefore warrant the protections appropriate to keying material and to governance records. The uncertainty state is a denial surface. An adversary who can make an authority unobservable can drive dependent beliefs to uncertainty and thereby block costly acts. This is a fail-closed outcome and is preferable to silent action on stale values, but implementers should ensure that the escalation path for a blocked act cannot itself be starved.

IANA Considerations This document has no IANA actions.

&RFC2119; &RFC8174; &RFC9421; Alter Meridian Pty Ltd

Acknowledgements This discipline was distilled from operational failure patterns observed in autonomous coding agents.