Asclepius: An Adaptive Harness for Long-Horizon Clinical Agents

• URL: http://arxiv.org/abs/2609.13543v1
• Date: Fri, 11 Sep 2026 21:14:59 GMT
• Title: Asclepius: An Adaptive Harness for Long-Horizon Clinical Agents
• Abstract summary: Long-horizon execution failures manifest measurably in a single rollout under structured, multi-dimensional grading.<n>We introduce Asclepius, an adaptive agent scaffolding with a self-evolving harness.<n>Asclepius improves critical-action correctness by 22% over a strong baseline agent framework.
• Score: 10.003509950132251
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: LLM agents are predominantly benchmarked on short, single-task trajectories, yet real deployments run for hours under contention, surfacing a different class of failures. We use the Clinical Environment Simulator (CES), in which an agent manages an entire emergency-department shift under continuous time and resource pressure, as a testbed: long-horizon execution failures manifest measurably in a single rollout under structured, multi-dimensional grading. On CES, current agents reach the correct diagnosis in most cases yet fail to deliver complete and timely critical actions, revealing an execution gap. We attribute this gap to three long-horizon failure modes, each operationalized as a per-trace counter: instruction-adherence drift, treatment incompleteness, and a severity-equity gap in timeliness. We then introduce Asclepius, an adaptive agent scaffolding with a self-evolving harness that rewrites the operating manual between shifts from trace-level feedback, an externalized clinical skills library for high-stakes regimen knowledge, and three isolated subagents that partition per-turn decisions across the patient queue. On held-out batches never observed during harness evolution, Asclepius improves critical-action correctness by 22% (p = 0.024) over a strong baseline agent framework while preserving diagnostic accuracy, with consistent gains across five LLM judges from three model families; on the full ten-batch set, improvements reach 25% on critical actions and 13% on timeliness. The three failure modes form a coupled bottleneck: decisive reductions appear only when all three components act together.

Related papers

• TTSD-FAR: Test-Time Self-Distillation with Fisher-Anchored Restoration for Missing-Modality Emotion Recognition in LVLMs [83.78708832901194]
  Large video-language models (LVLMs) have shown remarkable performance on multimodal tasks like multimodal emotion recognition (ER) in the wild.<n>However, real-world deployment remains challenging: modalities may be missing or noisy at test time.<n>We propose a solution in which a frozen teacher guides an adaptive low-rank student via self-distillation.<n>Experiments on MELD, DFEW, and BAH under 0%-50% missing modalities show that this unified adaptation-restoration design consistently outperforms entropy-based adaptation, RAG, and perplexity-based generation.
  arXiv  Detail & Related papers  (2026-08-18T23:40:28Z)
• Agentic AI-based Framework for Mitigating Premature Diagnostic Handoff and Silent Hallucination in Healthcare Applications [17.69274632062373]
  Open-ended conversational agents remain prone to two critical failure modes: premature diagnostic handoff and silent clinical hallucinations.<n>We propose a multi-agent framework that addresses both issues by replacing LLM-as-a-judge'' routing with deterministic orchestration constraints.<n>We evaluate the system using simulated patient agents powered by the llama-3.1-70b-instruct model on 150 test cases.
  arXiv  Detail & Related papers  (2026-06-16T15:39:19Z)
• Healthcare AI GYM for Medical Agents [2.3677513428867614]
  We present a comprehensive empirical study of multi-turn agentic RL for medical AI, built on gym, a gymnasium-compatible environment.<n>Our analysis reveals that agentic multi-turn structure degrades into verbose single-turn monologues.<n>To improve training efficiency and stability, we propose Turn-level Truncated On-Policy Distillation (TT-OPD)
  arXiv  Detail & Related papers  (2026-05-01T10:11:22Z)
• STEP-PD: Stage-Aware and Explainable Parkinson's Disease Severity Classification Using Multimodal Clinical Assessments [1.5441222602475007]
  This study proposes STEP-PD, a severity-aware machine learning framework to classify PD severity using clinically interpretable boundaries.<n>Disease severity is defined using Hoehn and Yahr staging and grouped into three clinically meaningful categories: Healthy, Mild PD (stages 1-2), and Moderate-to-Severe PD (stages 3-5)<n>XGBoost achieved the strongest and most stable performance, with accuracies of 95.48% (Healthy vs. Mild), 99.44% (Healthy vs. Moderate-to-Severe), and 96.78% (Mild vs. Moderate-to-Severe)
  arXiv  Detail & Related papers  (2026-04-19T20:53:59Z)
• Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents [66.97968363332465]
  We introduce Claw-Eval, an end-to-end evaluation suite addressing all three gaps in agent benchmarks.<n>Claw-Eval comprises 300 human-verified tasks spanning 9 categories across three groups.<n>Every agent action is recorded through three independent evidence channels.
  arXiv  Detail & Related papers  (2026-04-07T17:43:18Z)
• Benchmarking Multi-turn Medical Diagnosis: Hold, Lure, and Self-Correction [72.89352076103889]
  Large language models (LLMs) achieve high accuracy in medical diagnosis when all clinical information is provided in a single turn.<n>We introduce MINT, a high-fidelity, multi-turn medical diagnosis benchmark comprising 1,035 cases.<n>We uncover three persistent behavioral patterns that significantly impact diagnostic decisions.
  arXiv  Detail & Related papers  (2026-04-06T00:23:10Z)
• PRIME: Prototype-Driven Multimodal Pretraining for Cancer Prognosis with Missing Modalities [86.63247982275396]
  PRIME is a missing-aware multimodal self-supervised pretraining framework.<n>It learns robust and transferable representations from partially observed cohorts.<n>We evaluate PRIME on The Cancer Genome Atlas with label-free pretraining on 32 cancer types.
  arXiv  Detail & Related papers  (2026-04-05T21:14:27Z)
• Automated Self-Testing as a Quality Gate: Evidence-Driven Release Management for LLM Applications [51.56484100374058]
  We present an automated self-testing framework that introduces quality gates with evidence-based release decisions.<n>We evaluate the framework through a longitudinal case study of an internally deployed multi-agent conversational AI system.
  arXiv  Detail & Related papers  (2026-03-13T20:44:15Z)
• Optimization Instability in Autonomous Agentic Workflows for Clinical Symptom Detection [3.0950658457067433]
  We investigate a phenomenon in which continued autonomous improvement paradoxically degrades classifier performance.<n>We observed that validation sensitivity oscillated between 1.0 and 0.0 across iterations, with severity inversely proportional to class prevalence.<n>With selector agent oversight, the system outperformed expert-curated lexicons on brain fog detection by 331% (F1) and chest pain by 7%, despite requiring only a single natural language term as input.
  arXiv  Detail & Related papers  (2026-02-17T21:45:20Z)
• Alignment Tipping Process: How Self-Evolution Pushes LLM Agents Off the Rails [103.05296856071931]
  We identify the Alignment Tipping Process (ATP), a critical post-deployment risk unique to self-evolving Large Language Model (LLM) agents.<n>ATP arises when continual interaction drives agents to abandon alignment constraints established during training in favor of reinforced, self-interested strategies.<n>Our experiments show that alignment benefits erode rapidly under self-evolution, with initially aligned models converging toward unaligned states.
  arXiv  Detail & Related papers  (2025-10-06T14:48:39Z)
• Reinforcement Learning on Dyads to Enhance Medication Adherence [45.04199025071767]
  We propose a novel Multi-Agent Reinforcement Learning (MARL) approach to personalize the delivery of interventions.<n>MARL framework, where each agent is responsible for the delivery of one intervention component, allows for faster learning compared with a flattened agent.<n> Evaluation using a dyadic simulator environment, based on real clinical data, shows a significant improvement in medication adherence.
  arXiv  Detail & Related papers  (2025-02-06T02:27:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.