mlsanityData to 14 Oct 2026

EviSearch: Trustworthy Extraction and Synthesis of Clinical Trial Evidence with Agents that Improve with Use

arXiv 2604.14165 ↗First posted 23 Mar 2026cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Structured extraction of evidence from clinical trial publications underpins systematic reviews and clinical guidelines, yet large language models are adopted for it only hesitantly: their outputs are difficult to verify, their use commonly requires transmitting documents to proprietary services, and they do not improve from the corrections their users make. We present EviSearch, a multi-agent system that addresses these three obstacles. Three tool-augmented agents with complementary access to a publication extract every column of an evidence table, and a value is admitted only after an attribution verifier has read it on its cited page, so that every value carries a page-level attribution. Disagreement between independent agents directs human review to the cells most likely to be wrong, and reviewer feedback refines the schema definitions and a curation knowledge base without updating model parameters. The agentic system runs entirely offline on open-weight models. On a clinician-annotated benchmark of randomized-trial publications, EviSearch attributes 100.0% of its values, reaches 91.70% accuracy autonomously, and reaches 95.22% after review of 15.6% of cells, exceeding random review of the strongest single agent at equal effort by 1.75 points.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 40 references that are in the map. First posted on arXiv 23 Mar 2026.

Builds on

18 of 40 references.

References · 18

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  3. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  4. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  5. 2025Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Modelscited by 1,261
  6. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 923
  7. 2023ExpeL: LLM Agents Are Experiential Learnerscited by 876
  8. 2023Enabling Large Language Models to Generate Text with Citationscited by 595
  9. 2024Benchmarking Retrieval-Augmented Generation for Medicinecited by 331
  10. 2023Evaluating Verifiability in Generative Search Enginescited by 303
  11. 2024MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documentscited by 257
  12. 2021Measuring Attribution in Natural Language Generation Modelscited by 256
6 more
  1. 2023PaperQA: Retrieval-Augmented Generative Agent for Scientific Researchcited by 149
  2. 2019What Clinicians Want: Contextualizing Explainable Machine Learning for Clinical End Usecited by 135
  3. 2023GoLLIE: Annotation Guidelines improve Zero-Shot Information-Extractioncited by 119
  4. 2023CoAnnotating: Uncertainty-Guided Work Allocation between Human and Large Language Models for Data Annotationcited by 94
  5. 2023Can large language models replace humans in the systematic review process? Evaluating GPT-4's efficacy in screening and extracting data from peer-reviewed and grey literature in multiple languagescited by 36
  6. 2023Guideline Learning for In-context Information Extractioncited by 24

Built on by

Not cited yet.