# Modeling Clinical Concern Trajectories in Language Model Agents

arXiv: https://arxiv.org/abs/2604.27872 · HTML: https://mlsanity.com/paper/2604.27872/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 9 of its 21 references that are in the map.
- First posted on arXiv 30 Apr 2026.

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 9 of 9)

- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Unifying Cardiovascular Modelling with Deep Reinforcement Learning for Uncertainty Aware Control of Sepsis Treatment](https://mlsanity.com/paper/2101.08477/) (2021)
- [ArgMed-Agents: Explainable Clinical Decision Reasoning with LLM Disscusion via Argumentation Schemes](https://mlsanity.com/paper/2403.06294/) (2024)
- [Adaptive Reasoning and Acting in Medical Language Agents](https://mlsanity.com/paper/2410.10020/) (2024)
- [A Demonstration of Adaptive Collaboration of Large Language Models for Medical Decision-Making](https://mlsanity.com/paper/2411.00248/) (2024)
- [Controlling Long-Horizon Behavior in Language Model Agents with Explicit State Dynamics](https://mlsanity.com/paper/2601.16087/) (2026)
- [Personalized and Reliable Decision Sets: Enhancing Interpretability in Clinical Decision Support Systems](https://mlsanity.com/paper/2107.07483/) (2021)
- [Evaluating the impact of an explainable machine learning system on the interobserver agreement in chest radiograph interpretation](https://mlsanity.com/paper/2304.01220/) (2023)
- [A New Deep State-Space Analysis Framework for Patient Latent State Estimation and Classification from EHR Time Series Data](https://mlsanity.com/paper/2307.11487/) (2023)

## Abstract (arXiv)

Large language model (LLM) agents deployed in clinical settings often exhibit abrupt, threshold-driven behavior, offering little visibility into accumulating risk prior to escalation. In real-world care, however, clinicians act on gradually rising concern rather than instantaneous triggers. We study whether explicit state dynamics can expose such pre-escalation signals without delegating clinical authority to the agent. We introduce a lightweight agent architecture in which a memoryless clinical risk encoder is integrated over time using first- and second-order dynamics to produce a continuous escalation pressure signal. Across synthetic ward scenarios, stateless agents exhibit sharp escalation cliffs, while second-order dynamics produce smooth, anticipatory concern trajectories despite similar escalation timing. These trajectories surface sustained unease prior to escalation, enabling human-in-the-loop monitoring and more informed intervention. Our results suggest that explicit state dynamics can make LLM agents more clinically legible by revealing how long concern has been rising, not just when thresholds are crossed.