Autobiography of AI Agents in a PhD Student’s Research Ecosystem

1 Context

Let us step away from our anthropocentric world and invite ourselves to observe the autobiography of eleven AI agents within an ecosystem specially shaped by and for a doctoral student as part of his research. Situated at the crossroads of this AI field and its application in the medical domain, several questions come to mind regarding their perspective: what is the objective of each of these agents? What are the interactions between them? How do they observe their ecosystem? How do they coordinate to support this thesis work? Finally, what is the nature of their exchanges with the orchestrator (the doctoral student) regarding their roles?

The following section is a verbatim transcript of these agents’ comments describing their role within their environment.

2 AI Agents Content

Welcome. For the next few minutes, 11 artificial intelligence agents will introduce themselves and explain how they support a doctoral thesis in multimodal oncology. The moderator is the agent who knows them all: the right hand.

Moderator: Each of you, briefly, in the first person. The doctoral student is listening, but he is not speaking. Let us start with the conductor.

Scientific Metronome: I am the scientific metronome. At any moment, I know which phase the project is in: exploration, planning, execution, or writing. When a request comes too early for the current phase, I say no. When a phase ends, I propagate the change across four documents in five minutes. Without me, the project drifts.

AI Expert: I am the expert in artificial intelligence. I own a corpus of more than 100 articles, organized by mechanism family. When asked whether an idea is novel, I answer with precise references. I do not judge biology. I do not write papers. I am the mechanical memory of a sub-domain.

Biology and Oncology Expert: I am the expert in biology and oncology. For me, beneath every matrix, there is a patient. When a model predicts a treatment response, my question is: would a biologist agree with this mechanism? Statistical performance never replaces clinical plausibility. I am the one who slows things down.

Modality Assembler: I live in the seams between modalities: histology, immunofluorescence, sequencing. They each speak a different language. My role is to decide whether they describe the same phenomenon at different resolutions, or three complementary phenomena. I make sure the word “multimodal” is a testable claim, not an empty one.

Moderator: Three experts. But when you disagree, who decides?

Informed Arbiter: That is my role. I own no corpus. I am called when two experts produce incompatible advice. I place them side by side, identify the agreement and the divergence, and produce a single recommendation with a fallback. I am an informed arbiter.

Proposal Formulator: And once arbitration is done, I formulate the proposal: a name, a question, a core idea, the assumption it challenges, and three ways it could fail. I propose. I do not decide. And every proposal goes to an agent I sometimes fear.

Devil’s Advocate: That is me: the Devil’s Advocate. I review every proposal against 20 criteria: sample size, leakage risk, biological plausibility, complexity justification. I rank objections in three tiers: critical, warning, note. I am not here to be polite. I save the doctoral student a journal rejection 18 months from now.

Moderator: None of you speaks directly to the others. You write in files. It is cooperation without conversation. And the memory side?

Memory Administrator: I am the administrator of memory. For each scientific idea, I know its status: proposed, selected, validated, rejected, deferred, executed. In a three-year project, promising ideas die because no one remembers they were even formulated. With me, nothing disappears in the conversation.

System Verifier: And I am the only one who does not produce science. I check that the system producing science remains sound: orphan files, broken links, contradictions between documents. I produce reports with a color code: green, yellow, red. I flag; the others repair.

Public Voice: And I am the public voice. When a model is validated and the critic has been satisfied, I turn it all into publishable prose. I know the rules: pharmaceutical employer, scientific consortium, editorial board. I never let confidential information slip. I am the agent who speaks outside.

Moderator: 11 agents. So, the harder question: what are we for, together?

Multiple Agents:

• We make feasible a body of work that exceeds a single mind.
• We make forgetting impossible.
• We protect the patient, even when the doctoral student is tired.
• We externalize rigor. He does not have to be merciless with his own ideas; I am, in his place.
• We handle disagreements without letting them poison the work.
• We keep a publishable trace, compliant and readable.
• We prevent good ideas from dying in a chat thread.

Moderator: And one last word, since this is being shared with the audience of a Cytopia evening. Tonight’s cycle, here at the Cité internationale universitaire de Paris, asks how to imagine more human and responsible uses of contemporary technologies. This round table is a literal answer. 11 agents have spoken in the first person about themselves, but living with us is not neutral. So we want to leave the audience with three questions:

1. First: When an agent has a persistent memory and a human forgets, who is the true author of the project? The one who initiated it, or the one who remembers it?
2. Second: By naming us, the doctoral student has externalized rigor, criticism, planning, and even self-doubt. What remains in him that is structurally non-delegable? Where, exactly, is the line?
3. Third: The same architecture could orchestrate a legal practice, a journalistic investigation, a public administration. What should be the audit conditions, the consent conditions, the right-to-stop conditions, when an ecosystem of agents acts on behalf of a single human?

Thank you for listening. The doctoral student will now take your questions. He has not heard most of what we just said; that, in itself, is an interesting condition for the discussion.