mlsanityData to 14 Oct 2026

Taking the PULSE of Medical Reasoning: Step-Level Retrieval Timing for Knowledge-Grounded Inference

arXiv 2610.20292 ↗First posted 14 Oct 2026cs.CLcited by 0

On the map: LLM reasoning → Clinical and biomedical applications

Abstract (arXiv)

Reliable medical reasoning requires LLMs to dynamically access external biomedical evidence to improve factual trustworthiness and reasoning accuracy. However, indiscriminate retrieval can introduce noise and latency, raising a critical retrieval-timing problem: at each reasoning step, the system must decide whether the model's internal knowledge is reliable or external evidence is needed. We propose PUlSE, a lightweight probing method that uses the model's internal representations as intrinsic signals for step-level retrieval control. Our posterior trajectory analysis reveals that erroneous steps exhibit substantially higher inter-layer volatility than correct ones, suggesting unstable internal knowledge. Based on this finding, PUlSE trains a compact probe on inter-layer geometric features to detect factual errors upon step completion, and uses it as an adaptive trigger for retrieval and step regeneration. Across four medical benchmarks, PUlSE-timed retrieval matches exhaustive per-step retrieval in accuracy while reducing retrieval calls by 72%, and can transfer to an unseen legal domain, indicating potential domain-agnostic generality. Overall, our study provides an initial step toward shifting retrieval-trigger design from surface-level confidence estimates to internal activation dynamics for adaptive access.

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 21 of its 34 references that are in the map. First posted on arXiv 14 Oct 2026.

Builds on

21 of 34 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025Reasoning LLMs in the Medical Domain: A Literature Survey26 Aug
  2. 2025ReasonMed: A 370K Multi-Agent Generated Dataset for Advancing Medical Reasoning11 Jun
  3. 2025MedReason: Eliciting Factual Medical Reasoning Steps in LLMs via Knowledge Graphs1 Apr

Other references · 18

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2022Locating and Editing Factual Associations in GPTcited by 2,691
  3. 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmarkcited by 1,848
  4. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  5. 2022Large Language Models Encode Clinical Knowledgecited by 1,830
  6. 2020What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Examscited by 1,356
  7. 2020Transformer Feed-Forward Layers Are Key-Value Memoriescited by 1,336
  8. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 923
  9. 2023The Internal State of an LLM Knows When It's Lyingcited by 659
  10. 2024Benchmarking Retrieval-Augmented Generation for Medicinecited by 331
  11. 2022Prompting GPT-3 To Be Reliablecited by 260
  12. 2024Benchmarking Large Language Models on Answering and Explaining Challenging Medical Questionscited by 109
6 more
  1. 2024Uncertainty Estimation and Quantification for LLMs: A Simple Supervised Approachcited by 76
  2. 2024Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluationcited by 57
  3. 2023FLEEK: Factual Error Detection and Correction with Evidence Retrieved from External Knowledgecited by 25
  4. 2025The Geometry of Self-Verification in a Task-Specific Reasoning Modelcited by 13
  5. 2025ReProbe: Efficient Test-Time Scaling of Multi-Step Reasoning by Probing Internal States of Large Language Modelscited by 10
  6. 2025DoctorRAG: Medical RAG Fusing Knowledge with Patient Analogy through Textual Gradientscited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Proactive Reasoning-with-Retrieval Framework for Medical Multimodal Large Language Models
  2. 2026When Retrieval Helps and Distracts: Evaluating Evidence-Generating LLMs for Biomedical Claim Verification
  3. 2026PubMed Reasoner: Dynamic Reasoning-based Retrieval for Evidence-Grounded Biomedical Question Answering
  4. 2026MedRAGChecker: Claim-Level Verification for Biomedical Retrieval-Augmented Generation
  5. 2026Learning When to Trust Medical Knowledge: Regression-Safe Routing for Clinical Reasoning
  6. 2026From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAG
  7. 2025m1: Unleash the Potential of Test-Time Scaling for Medical Reasoning with Large Language Models
  8. 2025R2MED: A Benchmark for Reasoning-Driven Medical Retrieval