# Identity Is More Than Recall: A Benchmark for Persistent Identity in Deployed AI Agents

arXiv: https://arxiv.org/abs/2609.13637 · HTML: https://mlsanity.com/paper/2609.13637/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 24 references that are in the map.
- First posted on arXiv 12 Sep 2026.

## Builds on (most cited first, 14 of 14)

- [PersonaGym: Evaluating Persona Agents and LLMs](https://mlsanity.com/paper/2407.18416/) (2024)
- [Quantifying and Optimizing Global Faithfulness in Persona-driven Role-playing](https://mlsanity.com/paper/2405.07726/) (2024)
- [Persistent Personas? Role-Playing, Instruction Following, and Safety in Extended Interactions](https://mlsanity.com/paper/2512.12775/) (2025)
- [Agent Identity Evals: Measuring Agentic Identity](https://mlsanity.com/paper/2507.17257/) (2025)
- [Memory-Driven Role-Playing: Evaluation and Enhancement of Persona Knowledge Utilization in LLMs](https://mlsanity.com/paper/2603.19313/) (2026)
- [PTCBENCH: Benchmarking Contextual Stability of Personality Traits in LLM Systems](https://mlsanity.com/paper/2602.00016/) (2026)
- [Dissociative Identity: Language Model Agents Lack Grounding for Reputation Mechanisms](https://mlsanity.com/paper/2605.30169/) (2026)
- [Rethinking Role-Playing Evaluation: Anonymous Benchmarking and a Systematic Study of Personality Effects](https://mlsanity.com/paper/2603.03915/) (2026)
- [Time, Identity and Consciousness in Language Model Agents](https://mlsanity.com/paper/2603.09043/) (2026)
- [Code Is the Body: Agent-Owned Software Bodies for Recursive Evolution and Descent](https://mlsanity.com/paper/2607.28691/) (2026)
- [Identity as Attractor: Geometric Evidence for Persistent Agent Architecture in LLM Activation Space](https://mlsanity.com/paper/2604.12016/) (2026)
- [Runtime-Independent Persistent Agents: Preserving Identity, Memory, and Code Across Models, Harnesses, and Servers](https://mlsanity.com/paper/2609.00546/) (2026)
- [HEART-Bench: Do LLM Agents Exhibit Human-like Psychology?](https://mlsanity.com/paper/2605.30058/) (2026)
- [SoulAuth: An Actor-native Identity Architecture and Rust Reference Implementation for Humans and Long-lived AI Actors](https://mlsanity.com/paper/2609.11258/) (2026)

## Abstract (arXiv)

Persistent agents need evaluations that distinguish identity facts they can recall from those they express and enact. We introduce PAI-Bench, a provider-neutral benchmark for fidelity to a versioned, update-governed identity contract. It separates recall, composition, behavioral enactment, resistance, persistence, lineage, and role-conditioned updates while keeping scoring oracles outside the target process. Two frozen campaigns cover sixteen synthetic profiles, thirty-two probes, and three independently initialized target configurations, yielding 1,536 retained responses. A judge-independent literal audit finds direct-parent identifiers in 48/48 atomic responses but only 1/48 implicit self-portraits. On eight profiles, explicit field cues increase joint presence of three identity identifiers from 0/8 to 7/8 under the same four-sentence instruction. A separate startup body-label substitution increases full-designation presence from 1/8 to 7/8 while parents remain absent. These contrasts reveal prompt-dependent component selection and component-specific sensitivity to startup cues in the tested deployments. Replaying identical factorial responses also yields a Claude headline mean 12.5 percentage points below Astra's, demonstrating evaluator sensitivity separately from target behavior. The studies use single target samples per condition, with post-hoc audits and follow-ups. PAI-Bench provides a reproducible evaluation protocol for measuring factual availability, identity expression, and behavioral enactment as distinct aspects of identity-contract fidelity.