CureAgent: A Training-Free Executor-Analyst Framework for Clinical Reasoning

• URL: http://arxiv.org/abs/2512.05576v1
• Date: Fri, 05 Dec 2025 09:56:58 GMT
• Title: CureAgent: A Training-Free Executor-Analyst Framework for Clinical Reasoning
• Abstract summary: Executor-Analyst Framework is a modular architecture that decouples the syntactic precision of tool execution from the semantic robustness of clinical reasoning.<n>Our approach underscores the potential of training-free architectural engineering, achieving state-of-the-art performance on CURE-Bench without the need for expensive end-to-end finetuning.
• Score: 23.353757415071104
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Current clinical agent built on small LLMs, such as TxAgent suffer from a \textit{Context Utilization Failure}, where models successfully retrieve biomedical evidence due to supervised finetuning but fail to ground their diagnosis in that information. In this work, we propose the Executor-Analyst Framework, a modular architecture that decouples the syntactic precision of tool execution from the semantic robustness of clinical reasoning. By orchestrating specialized TxAgents (Executors) with long-context foundation models (Analysts), we mitigate the reasoning deficits observed in monolithic models. Beyond simple modularity, we demonstrate that a Stratified Ensemble strategy significantly outperforms global pooling by preserving evidentiary diversity, effectively addressing the information bottleneck. Furthermore, our stress tests reveal critical scaling insights: (1) a \textit{Context-Performance Paradox}, where extending reasoning contexts beyond 12k tokens introduces noise that degrades accuracy; and (2) the \textit{Curse of Dimensionality} in action spaces, where expanding toolsets necessitates hierarchical retrieval strategies. Crucially, our approach underscores the potential of training-free architectural engineering, achieving state-of-the-art performance on CURE-Bench without the need for expensive end-to-end finetuning. This provides a scalable, agile foundation for the next generation of trustworthy AI-driven therapeutics. Code has been released on https://github.com/June01/CureAgent.

Related papers

• The Large Cancer Assistant (LCA): A Model-Agnostic Orchestration Framework for Scalable Clinical Decision Support in Oncology [0.0]
  Large Cancer Assistant (LCA) is a model-agnostic, post-hoc orchestration framework designed for scalable clinical decision support.<n>LCA is mathematically formalized as a 7-tuple architecture grounded in the principle of Algorithmic Impermeability.<n>System dynamically orchestrates data via a Cancer Switching Module and intentionally isolates the core AI execution from volatile hospital IT infrastructures.
  arXiv  Detail & Related papers  (2026-07-07T17:38:47Z)
• A Multi-Agent Audit Framework for High-Stakes Reasoning: Evaluation and Interpretability in Clinical Mental Health Screening [0.8758828205574085]
  We propose a Multi-Agent Audit Framework that simulates a collaborative, multi-step verification process.<n>We empirically validate this architecture in the sensitive domain of clinical mental health screening.<n>Our framework decomposes the reasoning process into a Perception Agent, Knowledge Retrieval-Augmented Generation (RAG), Chain-of-Thought (CoT) clinical inference, and a critical Audit verification stage.
  arXiv  Detail & Related papers  (2026-06-19T05:51:03Z)
• Provably Secure Agent Guardrail [89.79561918065122]
  Existing defense architectures rely on empirical semantic guardrails and probabilistic large model adjudicators.<n>This paper proposes a new security paradigm for agents based on the fundamental limitations of logical reasoning.
  arXiv  Detail & Related papers  (2026-05-28T02:12:41Z)
• Towards a Virtual Neuroscientist: Autonomous Neuroimaging Analysis via Multi-Agent Collaboration [53.772014300855375]
  We introduce NIAgent, a multi-agent system for autonomous end-to-end neuroimaging analysis.<n>Unlike conventional flat tool-calling agents, NIAgent adopts a code-centric execution paradigm.<n>We propose a hierarchical verification framework for autonomous quality control, integrating cohort-level metric screening with agentic visual inspection.
  arXiv  Detail & Related papers  (2026-05-10T06:30:19Z)
• From Synthesis to Clinical Assistance: A Strategy-Aware Agent Framework for Autism Intervention based on Real Clinical Dataset [5.158237631119026]
  textscASDAgent is a strategy-aware framework designed to unify high-fidelity intervention dialogue synthesis and clinical decision support.<n>In real autism intervention, textscASDAgent achieves nearly 80% strategic consistency with human experts.
  arXiv  Detail & Related papers  (2026-04-09T03:28:46Z)
• ClinicalAgents: Multi-Agent Orchestration for Clinical Decision Making with Dual-Memory [17.805771452487612]
  We introduce ClinicalAgents, a novel multi-agent framework designed to simulate the cognitive workflow of expert clinicians.<n>Unlike rigid sequential chains, ClinicalAgents employs a dynamic orchestration mechanism modeled as a Monte Carlo Tree Search (MCTS) process.<n>This allows an Orchestrator to iteratively generate hypotheses, actively verify evidence, and trigger backtracking when critical information is missing.
  arXiv  Detail & Related papers  (2026-03-27T08:52:19Z)
• Dynamic analysis enhances issue resolution [53.50448142467294]
  DAIRA (Dynamic Analysis-enhanced Issue Resolution Agent) is an automated repair framework that embeds dynamic analysis into the agent's reasoning cycle.<n> Driven by a Test Tracing-Driven methodology, DAIRA utilizes lightweight monitors to extract critical runtime data.<n>When powered by Gemini 3 Flash Preview, DAIRA establishes a new state-of-the-art (SOTA) performance, achieving a 79.4% resolution rate on the SWE-bench Verified dataset.
  arXiv  Detail & Related papers  (2026-03-23T14:48:54Z)
• Understanding by Reconstruction: Reversing the Software Development Process for LLM Pretraining [66.89012795621349]
  Large Language Models (LLMs) often struggle with the deep, long-horizon reasoning required for complex software engineering.<n>We propose a novel paradigm: understanding via reconstruction.<n>We introduce a framework that synthesizes latent agentic trajectories using a multi-agent simulation.
  arXiv  Detail & Related papers  (2026-03-11T09:23:20Z)
• Mozi: Governed Autonomy for Drug Discovery LLM Agents [21.429647382651677]
  In dependency-heavy pharmaceutical pipelines, autonomous agents often drift into irreproducible trajectories.<n>We present Mozi, a dual-layer architecture that bridges the flexibility of generative AI with the deterministic rigor of computational biology.<n>We demonstrate Mozi's ability to navigate massive chemical spaces, enforce stringent toxicity filters, and generate highly competitive in silico candidates.
  arXiv  Detail & Related papers  (2026-03-04T02:22:21Z)
• LAMMI-Pathology: A Tool-Centric Bottom-Up LVLM-Agent Framework for Molecularly Informed Medical Intelligence in Pathology [14.427602956098099]
  We propose LAMMI-Pathology (LVLM-Agent System for Molecularly Informed Medical Intelligence in Pathology), a scalable agent framework for domain-specific agent tool-calling.<n>LAMMI-Pathology adopts a tool-centric, bottom-up architecture in which customized domain-adaptive tools serve as the foundation.
  arXiv  Detail & Related papers  (2026-02-21T09:51:32Z)
• OMG-Agent: Toward Robust Missing Modality Generation with Decoupled Coarse-to-Fine Agentic Workflows [9.617220633655716]
  We present textbfunderlineOmni-textbfunderlineModality textbfunderlineGeneration Agent (textbfOMG-Agent)
  arXiv  Detail & Related papers  (2026-02-04T02:25:40Z)
• MedSAM-Agent: Empowering Interactive Medical Image Segmentation with Multi-turn Agentic Reinforcement Learning [53.37068897861388]
  MedSAM-Agent is a framework that reformulates interactive segmentation as a multi-step autonomous decision-making process.<n>We develop a two-stage training pipeline that integrates multi-turn, end-to-end outcome verification.<n>Experiments across 6 medical modalities and 21 datasets demonstrate that MedSAM-Agent achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-02-03T09:47:49Z)
• Towards Efficient Agents: A Co-Design of Inference Architecture and System [66.59916327634639]
  This paper presents AgentInfer, a unified framework for end-to-end agent acceleration.<n>We decompose the problem into four synergistic components: AgentCollab, AgentSched, AgentSAM, and AgentCompress.<n>Experiments on the BrowseComp-zh and DeepDiver benchmarks demonstrate that through the synergistic collaboration of these methods, AgentInfer reduces ineffective token consumption by over 50%.
  arXiv  Detail & Related papers  (2025-12-20T12:06:13Z)
• NEBULA: Do We Evaluate Vision-Language-Action Agents Correctly? [10.307093355903232]
  We introduce NEBULA, a unified ecosystem for single-arm manipulation that enables diagnostic and reproducible evaluation.<n>NEBULA features a novel dual-axis evaluation protocol that combines capability tests for precise skill diagnosis with systematic stress tests that measure robustness.<n>A standardized API and a large-scale, aggregated dataset are provided to reduce fragmentation and support cross-dataset training and fair comparison.
  arXiv  Detail & Related papers  (2025-10-17T23:22:57Z)
• Reimagining Agent-based Modeling with Large Language Model Agents via Shachi [16.625794969005966]
  The study of emergent behaviors in large language model (LLM)-driven multi-agent systems is a critical research challenge.<n>We introduce Shachi, a formal methodology and modular framework that decomposes an agent's policy into core cognitive components.<n>We validate our methodology on a comprehensive 10-task benchmark and demonstrate its power through novel scientific inquiries.
  arXiv  Detail & Related papers  (2025-09-26T04:38:59Z)
• Following the TRACE: A Structured Path to Empathetic Response Generation with Multi-Agent Models [19.450298798183166]
  Empathetic response generation is a crucial task for creating more human-like and supportive conversational agents.<n>Existing methods face a core trade-off between the analytical depth of specialized models and the generative fluency of Large Language Models.<n>We propose TRACE, a novel framework that models empathy as a structured cognitive process by decomposing the task into a pipeline for analysis and synthesis.
  arXiv  Detail & Related papers  (2025-09-26T04:20:37Z)
• STARec: An Efficient Agent Framework for Recommender Systems via Autonomous Deliberate Reasoning [54.28691219536054]
  We introduce STARec, a slow-thinking augmented agent framework that endows recommender systems with autonomous deliberative reasoning capabilities.<n>We develop anchored reinforcement training - a two-stage paradigm combining structured knowledge distillation from advanced reasoning models with preference-aligned reward shaping.<n>Experiments on MovieLens 1M and Amazon CDs benchmarks demonstrate that STARec achieves substantial performance gains compared with state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-08-26T08:47:58Z)
• White-Basilisk: A Hybrid Model for Code Vulnerability Detection [45.03594130075282]
  We introduce White-Basilisk, a novel approach to vulnerability detection that demonstrates superior performance.<n>White-Basilisk achieves results in vulnerability detection tasks with a parameter count of only 200M.<n>This research establishes new benchmarks in code security and provides empirical evidence that compact, efficiently designed models can outperform larger counterparts in specialized tasks.
  arXiv  Detail & Related papers  (2025-07-11T12:39:25Z)
• An autonomous agent for auditing and improving the reliability of clinical AI models [11.225863068085266]
  We introduce ModelAuditor, a self-reflective agent that converses with users.<n>ModelAuditor simulates context-dependent, clinically relevant distribution shifts.<n>It then generates interpretable reports explaining how much performance likely degrades during deployment.
  arXiv  Detail & Related papers  (2025-07-08T07:58:52Z)
• Model Hemorrhage and the Robustness Limits of Large Language Models [119.46442117681147]
  Large language models (LLMs) demonstrate strong performance across natural language processing tasks, yet undergo significant performance degradation when modified for deployment.<n>We define this phenomenon as model hemorrhage - performance decline caused by parameter alterations and architectural changes.
  arXiv  Detail & Related papers  (2025-03-31T10:16:03Z)
• Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Compute [61.00662702026523]
  We propose a unified Test-Time Compute scaling framework that leverages increased inference-time instead of larger models.<n>Our framework incorporates two complementary strategies: internal TTC and external TTC.<n>We demonstrate our textbf32B model achieves a 46% issue resolution rate, surpassing significantly larger models such as DeepSeek R1 671B and OpenAI o1.
  arXiv  Detail & Related papers  (2025-03-31T07:31:32Z)
• Factored Agents: Decoupling In-Context Learning and Memorization for Robust Tool Use [4.437184840125514]
  We propose a novel factored agent architecture designed to overcome the limitations of traditional single-agent systems in agentic AI.<n>Our approach decomposes the agent into two specialized components: (1) a large language model that serves as a high level planner and in-context learner, and (2) a smaller language model which acts as a memorizer of tool format and output.<n> Empirical evaluations demonstrate that our factored architecture significantly improves planning accuracy and error resilience, while elucidating the inherent trade-off between in-context learning and static memorization.
  arXiv  Detail & Related papers  (2025-03-29T01:27:11Z)
• Provable Guarantees for Generative Behavior Cloning: Bridging Low-Level Stability and High-Level Behavior [51.60683890503293]
  We propose a theoretical framework for studying behavior cloning of complex expert demonstrations using generative modeling. We show that pure supervised cloning can generate trajectories matching the per-time step distribution of arbitrary expert trajectories.
  arXiv  Detail & Related papers  (2023-07-27T04:27:26Z)

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.