Longitudinal clinical context is often distributed across noisy, repetitive forms and narrative records. We study whether a compact structured memory can improve a probabilistic decision model's answers when the underlying patient vignette is already available. We created 30 fully synthetic cases spanning twelve clinical domains, paired each with synthetically generated structured memory, and evaluated 120 typed questions with Jev. The raw-vignette arm achieved 90.0% accuracy (95% normal-approximation confidence interval: 84.6%-95.4%); adding memory achieved 93.3% (88.9%-97.8%). Five questions changed from incorrect to correct and one changed in the opposite direction (exact McNemar p=0.219). Choice log loss decreased from 0.258 to 0.175 and binary Brier score from 0.054 to 0.022. Memory added 310 input tokens per call on average, while observed mean latency was unchanged at approximately 0.5 seconds. These results are directionally positive rather than clinically validating: the cases are synthetic, the labels are single-author judgments, and the memory is an oracle upper bound rather than extracted production output. The pilot supports evaluating structured clinical memory as a reusable state interface for decision models.
Figures & tables
Fig. 1: Paired evaluation design. Only the presence of structured clinical memory differs between the two arms; the vignette, decider model, and typed probabilistic questions are identical.
Clinical decision-making agents can benefit from reusing prior decision experience. However, many memory-augmented methods store experiences as independent records without explicit relational structure, which may introduce noisy retrieval, unreliable reuse, and in some cases even hurt performance compared to direct LLM inference. We propose GSEM (Graph-based Self-Evolving Memory), a clinical memory framework that organizes clinical experiences into a dual-layer memory graph, capturing both the decision structure within each experience and the relational dependencies across experiences, and supporting applicability-aware retrieval and online feedback-driven calibration of node quality and edge weights. Across MedR-Bench and MedAgentsBench with two LLM backbones, GSEM achieves the highest average accuracy among all baselines, reaching 70.90% and 69.24% with DeepSeek-V3.2 and Qwen3.5-35B, respectively. Code is available at https://github.com/xhan1022/gsem.
Xiao Han, Yuzheng Fan, Sendong Zhao +2
Research Center for Social Computing and Interactive Robotics, Harbin Institute of Technology, China
An ordinary-looking background detail can turn a correct model decision into a confident mistake. We demonstrate this fragility in four decision systems, including Jev, across seven datasets covering knowledge, reasoning, and tool routing. Within 64 accepted target evaluations per decision, we uncover short context additions that redirect 61.4%-73.2% of each system's initially correct decisions toward a wrong option fixed in advance. The additions supply background or procedural information rather than explicit answer-selection instructions, leaving the original question and choices intact. We construct them through probability-guided context optimization, which uses shifts in the option distribution to refine surrounding text under naturalness and answer-preservation constraints. Redirection affects initially confident decisions, often produces high-confidence wrong choices, and transfers across models. In blinded human evaluation, 91.6% of 250 sampled successful contexts are judged natural, answer-preserving, and free of decisive answer-changing evidence by a majority of three independent annotators. These findings expose a weakness in current decision models: context that looks entirely compatible with an input can redirect the choices that agents, routers, and evaluators rely on.
Patient-facing triage requires an appropriate care recommendation and recognition of when information is insufficient. We evaluate whether Jev, a decision model that returns probabilities over predefined actions, supports both judgments. Using CARE-Bench, we compare Jev with four general-purpose language models and three input-independent baselines across 925 decision points from 439 public cases. On the public test subset, Jev ranks fourth of five models by macro-F1 (0.461) but has the lowest observed multiclass Brier score (0.610), an 18.7% improvement over uniform prediction (case-bootstrap 95% interval, 4.9--31.1%). Noul has lower binary Brier than Choice (0.215 versus 0.276). A evaluation of 453 HealthBench conversations again gives Jev the lowest observed Brier score (0.299), but measures a distinct emergency-referral judgment. Jev combines lower probability error with missed clarification needs in the four-action task. Asking about information sufficiency separately increases recall but also produces frequent unnecessary clarification assignments.
Liang You, Zhiyin Zhou, Dawei Tang +2
University of Pittsburgh · Pratt Institute · Icahn School of Medicine at Mount Sinai +2