mlsanityData to 7 Oct 2026

From Voting to Agent Collaboration: Answer-Type-Aware LLM Pipelines for BioASQ 14b

arXiv 2607.06452 ↗First posted 7 Jul 2026cs.CL cs.AIcited by 0

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

Abstract (arXiv)

Biomedical question answering requires not only accurate extraction of information from scientific literature but also reliable integration of evidence across multiple documents. This study presents a question-type-specific large language model (LLM) framework for BioASQ 14b Task B, designed to improve answer robustness and evidence grounding in biomedical question answering. Rather than applying a single prompting strategy to all questions, the framework selects different inference procedures for yes/no, factoid, and list questions according to their distinct reasoning and evaluation requirements. For yes/no questions, snippet shuffling and self-reflection are used to reduce sensitivity to evidence ordering and improve decision stability. For factoid questions, full-snippet input is combined with chain-of-thought-based in-context learning to support accurate biomedical entity identification. For list questions, a multi-agent architecture is employed, in which evidence extraction, candidate generation, answer verification, and final aggregation are handled collaboratively. Preliminary experiments on BioASQ 13b were used to identify effective inference strategies for each question type, and the resulting framework was subsequently evaluated in the official BioASQ 14b Task B challenge. In the official evaluation, our framework showed competitive performance across multiple batches and achieved first place in the factoid subtask of Batch 4. These results demonstrate the effectiveness of combining question-type-specific inference, ensemble prediction, and agent-based verification for reliable biomedical question answering.

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 13 of its 30 references that are in the map. First posted on arXiv 7 Jul 2026.

Builds on

13 of 30 references.

References · 13

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  4. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  5. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  6. 2019BioBERT: a pre-trained biomedical language representation model for biomedical text miningcited by 1,935
  7. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,184
  8. 2023MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoningcited by 311
  9. 2022Can large language models reason about medical questions?cited by 194
  10. 2024Improving Medical Reasoning through Retrieval and Self-Reflection with Retrieval-Augmented Large Language Modelscited by 34
  11. 2026CLAG: Adaptive Memory Organization via Agent-Driven Clustering for Small Language Model Agentscited by 2
  12. 2025EvidenceMap: Learning Evidence Analysis to Unleash the Power of Small Language Models for Biomedical Question Answeringcited by 1
1 more
  1. 2026Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoningcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Harnessing Collective Intelligence of LLMs for Robust Biomedical QA: A Multi-Model Approach
  2. 2026A Multi-Agent Framework for Medical AI: Leveraging Fine-Tuned GPT, LLaMA, and DeepSeek R1 for Evidence-Based and Bias-Aware Clinical Query Processing
  3. 2025Knowledge-Driven Agentic Scientific Corpus Distillation Framework for Biomedical Large Language Models Training
  4. 2026Let LLMs Judge Each Other: Multi-Agent Peer-Reviewed Reasoning for Medical Question Answering
  5. 2024LLM-MedQA: Enhancing Medical Question Answering through Case Studies in Large Language Models
  6. 2026HypothesisMed: Inference-Time Answer Fusion and Structured Hypothesis-Space Reporting for Biomedical Question Answering
  7. 2026Adaptive Retrieval Strategies for Biomedical Question Answering
  8. 2026BELIEF: Structured Evidence Modeling and Uncertainty-Aware Fusion for Biomedical Question Answering