Episodic-to-Semantic Consolidation Without Identity Drift

2026-07-02

AI Summary

This work addresses the challenge of identity drift in long-running adaptive agents, which often arises from model or policy modifications during knowledge integration and undermines auditability and certification in regulated environments. The authors propose an identity-preserving knowledge integration mechanism that formalizes memory consolidation as a deterministic mapping from episodic memories to semantic knowledge, generating independently addressable semantic layers without altering the agent’s core identity. By leveraging a structural lemma to prove invariance of the identity hash, and integrating a deterministic aggregation algorithm, a formal agent representation, and a queryable semantic knowledge base, the approach enables auditable updates with quantified confidence and full event traceability. Experiments demonstrate byte-level consistency in agent identity and a 79.82% average reduction (95% BCa CI [78.02%, 81.49%]) in invalid planning attempts, with correctness verified across all knowledge fields.

Abstract

Long-running adaptive intelligent agents face a structural tension between knowledge consolidation and information integrity. Memory consolidation is conventionally treated as an agent-changing operation: a model is fine-tuned, a prompt rewritten, a policy distilled, or a reflection appended to the context that governs future behaviour. In regulated autonomic deployment this is a liability because the agent operates under commitments and audit contracts that bind to a specific, cryptographically certified identity. We propose to treat consolidation not as a mutation of the planner or the identity manifest, but as a deterministic function f: M^ep -> M^sem over episodic memory whose output is a separately addressable semantic knowledge layer; the identity hash does not read M^sem, so consolidation updates knowledge without changing the agent's certified identity. We give a formal account of the agent representation, prove identity invariance through a structural lemma on the manifest's hash-input set, specify a deterministic aggregation algorithm whose outputs are auditable database rows with explicit confidence and supporting-event provenance, and validate the construction with synthetic experiments demonstrating per-field correctness, byte-equal identity across consolidation passes, and a mean 79.82% reduction in unproductive planner attempts (95% BCa CI [78.02%, 81.49%] across 10 seeds) against a calibrated Bayesian-shrunk baseline. The construction is a knowledge-update discipline for autonomic agents in which lessons accumulate as queryable facts while the agent's certified identity remains byte-equal across its operational lifetime, with an embodied service agent as the running case study.

Problem

• identity drift
• memory consolidation
• autonomic agents
• certified identity
• knowledge integrity

Innovation

• identity invariance
• episodic-to-semantic consolidation
• deterministic knowledge aggregation
• autonomic agents
• auditable memory