mlsanityData to 7 Oct 2026

AgenticSum: An Agentic Inference-Time Framework for Faithful Clinical Text Summarization

arXiv 2602.20040 ↗First posted 23 Feb 2026cs.CL cs.AIcited by 0

On the map: LLM agents and tool use → Medical and scientific domain agents

Abstract (arXiv)

Large language models (LLMs) offer substantial promise for automating clinical text summarization, yet maintaining factual consistency remains challenging due to the length, noise, and heterogeneity of clinical documentation. We present AgenticSum, an inference-time, agentic framework that separates context selection, generation, verification, and targeted correction to reduce hallucinated content. The framework decomposes summarization into coordinated stages that compress task-relevant context, generate an initial draft, identify weakly supported spans using internal attention grounding signals, and selectively revise flagged content under supervisory control. We evaluate AgenticSum on two public datasets, using reference-based metrics, LLM-as-a-judge assessment, and human evaluation. Across various measures, AgenticSum demonstrates consistent improvements compared to vanilla LLMs and other strong baselines. Our results indicate that structured, agentic design with targeted correction offers an effective inference time solution to improve clinical note summarization using LLMs.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use. Builds on 36 of its 64 references that are in the map. First posted on arXiv 23 Feb 2026.

Builds on

36 of 64 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Enhancing Diagnostic Accuracy through Multi-Agent Conversations: Using Large Language Models to Mitigate Cognitive Bias26 Jan

Other references · 35

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  4. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  5. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  6. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  7. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  8. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,582
  9. 2023SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shotcited by 1,090
  10. 2020Domain-Specific Language Model Pretraining for Biomedical Natural Language Processingcited by 996
  11. 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 895
  12. 2023LLM-Pruner: On the Structural Pruning of Large Language Modelscited by 643
23 more
  1. 2019Evaluating the Factual Consistency of Abstractive Text Summarizationcited by 578
  2. 2022BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Miningcited by 531
  3. 2022Large Language Models Are Reasoning Teacherscited by 318
  4. 2022Teaching Small Language Models to Reasoncited by 279
  5. 2018Scalable and accurate deep learning for electronic health recordscited by 275
  6. 2023Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedbackcited by 202
  7. 2023Sources of Hallucination by Large Language Models on Inference Taskscited by 168
  8. 2024Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Mapscited by 140
  9. 2024Rho-1: Not All Tokens Are What You Needcited by 132
  10. 2025Medical Hallucinations in Foundation Models and Their Impact on Healthcarecited by 89
  11. 2021Fine-Tuning Large Neural Language Models for Biomedical Natural Language Processingcited by 57
  12. 2024Attribute First, then Generate: Locally-attributable Grounded Text Generationcited by 54
  13. 2024Sparser is Faster and Less is More: Efficient Sparse Attention for Long-Range Transformerscited by 51
  14. 2024ChatCite: LLM Agent with Human Workflow Guidance for Comparative Literature Summarycited by 30
  15. 2024FactPICO: Factuality Evaluation for Plain Language Summarization of Medical Evidencecited by 18
  16. 2025Correctness Assessment of Code Generated by Large Language Models Using Internal Representationscited by 17
  17. 2025HICD: Hallucination-Inducing via Attention Dispersion for Contrastive Decoding to Mitigate Hallucinations in Large Language Modelscited by 7
  18. 2025MaLei at MultiClinSUM: Summarisation of Clinical Documents using Perspective-Aware Iterative Self-Prompting with LLMscited by 6
  19. 2024Automatic Summarization of Doctor-Patient Encounter Dialogues Using Large Language Model through Prompt Tuningcited by 5
  20. 2025MedFactEval and MedAgentBrief: A Framework and Workflow for Generating and Evaluating Factual Clinical Summariescited by 4
  21. 2024HealthGAT: Node Classifications in Electronic Health Records using Graph Attention Networkscited by 3
  22. 2025ConTextual: Improving Clinical Text Summarization in LLMs with Context-preserving Token Filtering and Knowledge Graphscited by 3
  23. 2024Optimal path for Biomedical Text Summarization Using Pointer GPTcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Large Language Models with Temporal Reasoning for Longitudinal Clinical Summarization and Prediction
  2. 2026Ten Headache Specialists versus Artificial Intelligence for Clinical Literature Summarization: A Critical Evaluation and Comparison
  3. 2026Configurable Clinical Information Extraction with Agentic RAG: What Works, What Breaks, and Why
  4. 2026ASCRIBE: Atomic and Significance-Based Reasoning for Thai Clinical SOAP Note Generation
  5. 2025HARMON-E: Hierarchical Agentic Reasoning for Multimodal Oncology Notes to Extract Structured Data
  6. 2026Toward Workflow-Aware Benchmarking for Healthcare NLP Agents
  7. 2023Synthetic Imitation Edit Feedback for Factual Alignment in Clinical Summarization
  8. 2026From Attribution to Abstention: Training-Free Attention-Based Auditing for Clinical Summarization