Published August 4, 2026 | Version 7.00
Publication Open

Non-Markovian Trajectory Modeling in Multi-Agent Biological Information Systems

Authors/Creators

  • 1. Research & Development Department, Scalar Logic Group

Contributors

  • 1. Scalar Logic Group

Description

Real biology—especially immunology and translational oncology—is fundamentally stochastic, non-Markovian, and constantly evolving, making traditional static or linear pipeline approaches highly prone to error. This paper introduces a multi-agent, state-space architecture designed to model volatile biological behavior and bridge the gap to deterministic software through the Bio-Stochastic Continuum (BSC) Engine. By utilizing Non-Parametric Bayesian Swarms that calculate dynamic probability distributions in real time, our methodology moves past standard Large Language Models (LLMs) to rigorously quantify uncertainty across messy Real-World Evidence (RWE).
We deploy a competitive multi-agent choreography featuring a “Clinician Proxy Agent” and a “Biochemist Proxy Agent” operating in an active feedback loop to model cellular adaptation to immunotherapies, predicting T-cell exhaustion and resistance mechanisms over time. In baseline simulation testing of a synthetic cohort of 10,000 non-small cell lung cancer (NSCLC) patient profiles, the engine successfully predicted immunotherapeutic resistance pathways an average of 22 days before traditional clinical biomarkers registered any observable change.
To ensure system stability under high data volatility and eliminate telemetry cascade failures, we implemented a hard Non-Parametric Bayesian Throttling Gate (acting as a ≥ 95% confidence filter). Under an artificial 400% stress surge, the modified engine maintained 100% uptime, accelerated continuous processing latency to < 45 ms (representing a 62.5% faster execution speed), automated multi-agent mapping to reduce clinical data-ingestion friction by 84%, and achieved a 41% reduction in total compute expenditure through logarithmic stabilization. These results demonstrate the viability of using self-correcting multi-agent stochastics to translate clinical observations into high-fidelity biological simulations.

Files

Non-Markovian_Trajectory_Modeling_BSC_Engine-v7 (1).pdf

Files (164.7 kB)

Additional details

Identifiers

Other
BIORXIV/2026/741360

Related works

Is supplemented by
Software: https://github.com/scalarlogicgroup/scalar-bio-choreography (URL)
Dataset: https://huggingface.co/datasets/scalarlogicgroup/synthetic-nsclc-10k (URL)
Other: https://huggingface.co/scalarlogicgroup/scalar-clinical-metadata-tokenizer (URL)

Dates

Accepted
2026-08-03

Software

Repository URL
https://huggingface.co/datasets/scalarlogicgroup/synthetic-nsclc-10k
Programming language
Python
Development Status
Active

References

  • Noble, W. S. (2009). A Quick Guide to Organizing Computational Biology Projects. PLoS Computational Biology, 5(7), e1000424. Gikhman, I. I., & Skorokhod, A. V. (1969). Introduction to the Theory of Random Processes. Courier Corporation. Skorokhod, A. V. (1961). Studies in the Theory of Random Processes (Stochastic Differential Equations and Markov Processes). Kiev University. Manolakos, E. S., & Kouskoumvekakis, E. (2017). StochSoCs: High performance biocomputing simulations for large scale Systems Biology. Proceedings of the 2017 International Conference on High Performance Computing & Simulation (HPCS 2017), IEEE. Ranftl, S., Rolf, M., Holzapfel, G. A., & Kuhl, E. (2026). Uncertainty quantification in mechanics: A unified Bayesian perspective. arXiv preprint arXiv:2607.18734v1. Wang, M. et al. (2025). Generative AI for Biosciences: Emerging Threats and Roadmap to Biosecurity. arXiv preprint.