GxP-Agent is a multi‑agent system that transforms clinical trial protocols into CDISC‑compliant datasets by encoding the regulatory workflow as a directed acyclic graph (DAG). Each node in the DAG represents a domain‑specific task executed by a worker agent with specialized skill context, validation gates, and conditional retry logic. On the CDISC‑Bench benchmark, GxP-Agent with Claude Sonnet 4.6 achieved a perfect 100 % structural match for 49 variables across 254 records, outperforming single‑agent and flat multi‑agent baselines and enabling weaker models like GPT‑4.1 to reach 59.2 % under the same DAG.
arXiv:2609.21859v1 Announce Type: new Abstract: Nearly 90% of drugs entering clinical development ultimately fail, despite billions of dollars in investment. Pharmaceutical companies therefore rely o...
arXiv:2607. 22555v1 Announce Type: new Abstract: Medical diagnosis is a multi-stage process: extract facts, consult knowledge, generate a differential analysis, and select the best diagnosis with explanations.
arXiv:2607. 04907v1 Announce Type: new Abstract: Deploying Large Language Models (LLMs) in high-stakes clinical settings remains limited by structural hallucinations, weak deterministic reasoning over tabular patient data, and omissions in vector retrieval.
arXiv:2606. 04494v1 Announce Type: new Abstract: Biomedical agents promise to automate complex biological workflows, yet current systems face two fundamental bottlenecks: bioinformatics tools are highly heterogeneous in interfaces and execution environments, while agent planning still relies on flat prompt-retrieved tool descriptions.
DAGent introduces an Evaluate‑then‑Grow planning approach for deep research agents, building directed acyclic graphs incrementally based on confidence and uncertainty from completed tasks. The framework includes a hierarchical context layer for efficient query handling and a structural reinforcement learning component, DAGRPO, that rewards topology‑conditioned execution. Experiments on BrowseComp‑Plus, GAIA, and xbench‑DeepSearch show DAGent outperforming strong baselines across multiple backbones and scaling to large language models.
arXiv:2607. 11084v1 Announce Type: new Abstract: Agentic research systems are emerging as a new paradigm for coordinating scientific workflows beyond isolated model inference, code generation, or statistical analysis.
arXiv:2606. 31179v1 Announce Type: new Abstract: As AI agents become increasingly capable of complex, long-horizon reasoning, rigorous and holistic evaluation is essential for measuring progress toward real-world healthcare applications.
arXiv:2607. 20499v1 Announce Type: new Abstract: Large Language Models generate plausible backend code, but a single-pass paradigm provides no guarantee of correctness or runtime reliability.
arXiv:2512. 11682v2 Announce Type: replace Abstract: Therapeutic decision-making in clinical medicine constitutes a high-stakes domain in which AI guidance interacts with complex interactions among patient characteristics, disease processes, and pharmacological agents.
AgentJudgeBench is a new benchmark that evaluates the reliability of large language model (LLM) judges on agentic tool‑calling tasks involving workflow directed acyclic graphs (DAGs). It contains 3,808 instances across six DAG topologies and three difficulty tiers, tested with five generators (3B–70B open‑weight models and GPT‑5.4) and six judges (20B to frontier scale) under both paired‑with‑and‑without‑ground‑truth conditions. The study finds that judge alignment degrades with task difficulty, ground‑truth exposure can sometimes hurt alignment, and structured evaluation rubrics provide modest improvements, revealing a structural ceiling that model capacity alone cannot surpass.
arXiv:2607. 13411v1 Announce Type: cross Abstract: Clinical AI models can expose patients to harm when adversarial vulnerabilities go undetected, yet formal security auditing requires statistical expertise, specialized tools, and significant time.
arXiv:2608.21864v1 Announce Type: cross Abstract: The current progress of Clinical Vision Large Language Models (C-VLLMs) has substantially improved digital diagnostics, still these frameworks often...