🤖 AI Summary
This study addresses critical trust challenges in enterprise AI agents, including privilege escalation, data misuse, and audit deficiencies, by proposing a formal policy algebra framework. The approach defines reliable capability envelopes through compositional security constraints, integrating mechanisms for runtime obligation composition, budget tightening, and evidence accumulation to enable multi-agent trust propagation and cost-aware artifact materialization. Experimental evaluations demonstrate that the system intercepts 94.8% of violation events while achieving an 86.9% task completion rate and 98.6% audit integrity. These results indicate that the framework effectively eliminates critical security vulnerabilities, significantly enhancing both the reliability and auditability of agent execution while maintaining strict regulatory compliance.
📝 Abstract
Large language model-based agentic frameworks primarily optimize capability: whether an agent can reason, retrieve information, call tools, delegate work, and complete a goal. Enterprise execution requires a stronger property. A successful result is not reliable if it was produced through unauthorized data access, widened delegated authority, unapproved side effects, unrecoverable budget consumption, or incomplete evidence. This paper defines reliable capability as a path property: an agent is reliably capable only when it completes a task through action events that remain admissible under identity, profile, tool, data, memory, budget, artifact, approval, and audit constraints. We propose a policy algebra that defines the reliability envelope within which agent capability may be exercised. Security profiles and runtime obligations compose through joins, intersections, budget narrowing, approval inheritance, and evidence accumulation; the resulting composition is both trust-preserving and the least restrictive state satisfying all governing inputs. The algebra also propagates restrictions across multi-agent calls and introduces cost-aware artifact materialization, which redirects open-ended execution toward a recoverable outcome as budget exposure grows. The evaluation is interpreted as a reliability-capability trade-off rather than a capability benchmark: the policy-algebra runtime intervenes on 94.8% of policy-violating events while retaining an 86.9% task-completion rate, eliminates the observed profile-monotonicity and zero-artifact-exhaustion violations, and increases audit completeness to 98.6%. The method provides researchers and practitioners with formal correctness conditions, executable decision semantics, and trace evidence for building agents that are not only capable, but reliably capable.