mlsanityData to 14 Oct 2026

GRASP: Graph Reasoning Agents for Systems Pharmacology with Human-in-the-Loop

arXiv 2512.05502 ↗First posted 5 Dec 2025cs.LGcited by 0

On the map: LLM reasoning → Clinical and biomedical applications

also in 1 more
Abstract (arXiv)

Quantitative Systems Pharmacology (QSP) modeling is essential for drug development but it requires significant time investment that limits the throughput of domain experts. We present GRASP -- a multi-agent, graph-reasoning framework with a human-in-the-loop conversational interface -- that encodes QSP models as typed biological knowledge graphs and compiles them to executable MATLAB/SimBiology code while preserving units, mass balance, and physiological constraints. A two-phase workflow -- textscUnderstanding (graph reconstruction of legacy code) and textscAction (constraint-checked, language-driven modification) -- is orchestrated by a state machine with iterative validation. GRASP performs breadth-first parameter-alignment around new entities to surface dependent quantities and propose biologically plausible defaults, and it runs automatic execution/diagnostics until convergence. In head-to-head evaluations using LLM-as-judge, GRASP outperforms SME-guided CoT and ToT baselines across biological plausibility, mathematical correctness, structural fidelity, and code quality ((≈)9--10/10 vs. 5--7/10). BFS alignment achieves F1 = 0.95 for dependency discovery, units, and range. These results demonstrate that graph-structured, agentic workflows can make QSP model development both accessible and rigorous, enabling domain experts to specify mechanisms in natural language without sacrificing biomedical fidelity.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning. Builds on 11 of its 27 references that are in the map. First posted on arXiv 5 Dec 2025.

Builds on

11 of 27 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025MMedAgent-RL: Optimizing Multi-Agent Collaboration for Multimodal Medical Reasoning31 May
  2. 2025K-Paths: Reasoning over Graph Paths for Drug Repurposing and Drug Interaction Prediction18 Feb

Other references · 9

  1. 2025Multi-Agent Collaboration Mechanisms: A Survey of LLMscited by 431
  2. 2025MedRAG: Enhancing Retrieval-augmented Generation with Knowledge Graph-Elicited Reasoning for Healthcare Copilotcited by 83
  3. 2024DrugAgent: Automating AI-aided Drug Discovery Programming through LLM Multi-Agent Collaborationcited by 44
  4. 2024CodeJudge-Eval: Can Large Language Models be Good Judges in Code Understanding?cited by 30
  5. 2024Human-in-the-loop or AI-in-the-loop? Automate or Collaborate?cited by 23
  6. 2024KGARevion: An AI Agent for Knowledge-Intensive Biomedical QAcited by 20
  7. 2025GCoT: Chain-of-Thought Prompt Learning for Graphscited by 9
  8. 2024Collaborative Intelligence in Sequential Experiments: A Human-in-the-Loop Framework for Drug Discoverycited by 3
  9. 2025MAGIC: Multi-Agent Argumentation and Grammar Integrated Critiquercited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025DrugPilot: LLM-based Parameterized Reasoning Agent for Drug Discovery
  2. 2025MedRule-KG: A Knowledge-Graph--Steered Scaffold for Reliable Mathematical and Biomedical Reasoning
  3. 2026A hierarchical memory architecture overcomes context limits in long-horizon multi-agent computational modeling
  4. 2026Progressive Multi-Agent Reasoning for Biological Perturbation Prediction
  5. 2026M3OS: A Monte Carlo Graph Search-Orchestrated Multi-Agent LLM System for Evidence-Traced Molecular Optimization
  6. 2025LLM Agent Swarm for Hypothesis-Driven Drug Discovery
  7. 2025BioDisco: Multi-agent hypothesis generation with dual-mode evidence, iterative feedback and temporal evaluation
  8. 2026An AI agent for treatment reasoning over a biomedical tool universe