Adnan KhanAdnanProduct & AI
San Francisco Bay Area
Get in touch

Source note3 min read

LLM-Guided ODE Discovery and Parameter Inference from Small-Cohort Aggregate Data

Source

arXiv

arxiv.org/abs/2607.00733v1

Read the source

Source

Plain-Language Brief

The paper introduces AgentODE, a framework that uses large language models (LLM) to propose ODE structures for complex dynamics modeling in rare diseases. The framework operates on population-level summary statistics alone and can refine parameter distributions through a diagnosis--update loop. The authors evaluate AgentODE on several benchmark problems across different fields and clinical datasets, including recessive dystrophic epidermolysis bullosa (RDEB), where it demonstrates functional consistency and promotes mechanistically principled structure discovery even in sparse and noisy data settings.

What the Document Says

  • The paper discusses an end-to-end framework called AgentODE for discovering ODE structures and refining parameter distributions from population-level summary statistics in rare diseases.
  • AgentODE utilizes a large language model (LLM) to propose candidate ODE structures.
  • It employs a tool-augmented inference agent that iteratively refines parameter distributions through a diagnosis--update loop using population-level summary statistics alone.
  • The authors evaluate AgentODE on three benchmark problems across different fields and two clinical datasets, including RDEB with 231 observations across 46 patients.
  • AgentODE recovers functionally consistent ODE structures in all settings.
  • Experiments on RDEB data demonstrate that AgentODE promotes mechanistically principled structure discovery even in sparse and noisy data settings.
  • Baselines with individual-level data access recover implausible structures despite better predictive performance.

Key Concepts Mentioned

  • AgentODE
  • ODE structures
  • population-level summary statistics
  • large language models (LLM)
  • diagnosis--update loop
  • rare diseases
  • recessive dystrophic epidermolysis bullosa (RDEB)

Claims Made by the Document

  • AgentODE addresses the gap of jointly discovering ODE structure and refining parameter distributions from summary statistics.
  • AgentODE recovers functionally consistent ODE structures across all settings.
  • In sparse and noisy data settings, reasoning from summary statistics promotes mechanistically principled structure discovery.

Evidence Used

  • The text discusses AgentODE as an end-to-end framework that addresses the gap of jointly discovering ODE structure and refining parameter distributions.
  • The paper evaluates AgentODE on several benchmark problems and demonstrates its ability to recover functionally consistent ODE structures in all settings.
  • Experiments on RDEB data show improved structure discovery in sparse and noisy conditions when using summary statistics.

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

Mechanistic modeling via ordinary differential equations (ODEs) provides interpretable descriptions of complex dynamics and enables inference of underlying mechanisms, which is particularly valuable in clinical settings. However, in rare diseases, both the structure and parameters of the model are typically unknown, while individual-level data is scarce, noisy, heterogeneous, and subject to privacy constraints. In such settings, population-level summary statistics provide a practical privacy-preserving data representation, while capturing heterogeneity further requires modeling parameters as distributions rather than fixed values. Yet no existing method jointly discovers ODE structure and refines parameter distributions solely from summary statistics. We present AgentODE, an end-to-end framework that addresses this gap. An LLM proposes candidate ODE structures, while a tool-augmented inference agent iteratively refines parameter distributions through a diagnosis--update loop, operating on population-level summary statistics alone. We evaluate AgentODE on three benchmark problems across different fields and two clinical datasets, including the rare disease recessive dystrophic epidermolysis bullosa (RDEB), with only 231 observations across 46 patients. AgentODE recovers functionally consistent ODE structures across all settings, and experiments on RDEB demonstrates that in sparse and noisy data settings reasoning from summary statistics promotes mechanistically principled structure discovery, whereas baselines with individual-level data access recover implausible structures despite better predictive performance. AgentODE opens new possibilities for mechanistic modeling of rare diseases directly from population-level summary statistics, where data scarcity and privacy constraints have traditionally limited such analyses.