# Where the Evidence Lives: Auditing AI Companions' Self-Descriptions

arXiv: https://arxiv.org/abs/2609.38753 · HTML: https://mlsanity.com/paper/2609.38753/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 42 references that are in the map.
- First posted on arXiv 30 Sep 2026.

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

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [Large Language Models are not Fair Evaluators](https://mlsanity.com/paper/2305.17926/) (2023)
- [Model Cards for Model Reporting](https://mlsanity.com/paper/1810.03993/) (2018)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [ExpeL: LLM Agents Are Experiential Learners](https://mlsanity.com/paper/2308.10144/) (2023)
- [ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks](https://mlsanity.com/paper/2303.15056/) (2023)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [Closing the AI Accountability Gap: Defining an End-to-End Framework for Internal Algorithmic Auditing](https://mlsanity.com/paper/2001.00973/) (2020)
- [Measuring and Controlling Instruction (In)Stability in Language Model Dialogs](https://mlsanity.com/paper/2402.10962/) (2024)
- [Memory Sandbox: Transparent and Interactive Memory Management for Conversational Agents](https://mlsanity.com/paper/2308.01542/) (2023)
- [Proactive Conversational Agents with Inner Thoughts](https://mlsanity.com/paper/2501.00383/) (2024)

## Abstract (arXiv)

Companion agents describe themselves: they remember, they understand their users, the relationship has changed them. We argue that such accounts, and the experience ratings that seem to confirm them, are checkable by users only where the evidence is theirs: in the agent's behavior, or in themselves. Where the evidence lives in the machinery, fluent self-description and moderately positive ratings do not establish that the mechanisms behind them ran. We demonstrate an audit procedure that sets an agent's self-description against its users' judgements and its implementation records, reporting each claim as supported, contradicted, or unresolved, and apply it to Lita, a proactive companion we built and deployed for a month with nine colleagues. Participants endorsed stylistic claims, withheld endorsement from relational ones, and rated memory at or above midpoint, while two of three memory layers had never executed their accumulation step. Memory-bearing agents should report what their self-descriptions cannot establish.