Overview

Evidence selection asks which retrieved documents, passages, claims, or multimodal observations are sufficient to support a decision or answer. It matters in retrieval-augmented generation, long-context and video reasoning, clinical decision support, and systematic-review screening, where missing or irrelevant evidence can distort results. Methods include learned retrievers and rerankers, utility and uncertainty scoring, graph or discrete optimization, and agents that acquire, verify, or compress evidence under a cost or token budget. A central challenge is that topical relevance and answer accuracy do not guarantee complete, traceable support: evidence quality, model variability, and downstream effects need separate evaluation, and more or better-filtered evidence does not always improve outcomes.

Latest papers

CardsList

67 papers11 papers in the last four weeks, down 8% on the four weeks before. 0.1% of all new papers.

  1. Not All Evidence Is Admissible: Evidence Governance for Tool-Augmented Medical Agents

    Nov 17, 2026Runxun Zhang, Onofrio Antonio Catalano, Jinqiao Wang +1Medical AI AgentsTool-Augmented Reasoning

  2. HiVe-Mem: Interleaving Horizontal Memory Expansion and Vertical Evidence Composition for Multimodal Agents

    Nov 9, 2026Haozhen Zhang, Bohan Liu, Jianzhu Bao +5Multimodal MemoryEpisodic Memory for LLM Agents

  3. Two-Sided Conformal Evidence Sets for Retrieval-Augmented Generation

    Nov 7, 2026Ben Jenkins, Mihaela CardeiEvidence SelectionRAG Evaluation

  4. CoRA-Bench: Evaluating Evidence Preservation by Context Selectors Under Token Budgets

    Nov 6, 2026Huzaifa Pardawala, Siddhant Sukhani, Sudheer Chava +1Evidence SelectionLong-Context Language Model Evaluation

  5. Online Evidence-Containment Prediction over Text Spans under Distinct Queries

    Oct 30, 2026Xiang Liu, Haochen DingEvidence SelectionEvidence-Grounded QA

  6. Beyond the Evidence Coherence Trap: Agent-Driven Evidence Selection for Temporally Disordered Fake News Detection

    Oct 27, 2026Chi Wang, Min Gao, Yifei Zhang +3Fake News DetectionEvidence Selection

  7. DuQUAD: A Dual-View Framework with Quality-Aware Evidence Pruning for Multi-Document Question Answering

    Oct 25, 2026Yeonjun Choi, Seyeon Jeong, Jong Wook Kim +1Multi-Document QAEvidence-Grounded QA

  8. Temporal Evidence Allocation For Longitudinal Clinical Retrieval: A Position And Technical Report

    Oct 20, 2026Soumya Ranjan Sahoo, Divya Bharti, Sanand SasidharanTemporal IREvidence Selection

  9. EpiLens: Lightweight RAG for Epidemiological Knowledge Acquisition

    Oct 19, 2026Vincenzo Perri, Ciro Cattuto, Daniela PaolottiLLM Information ExtractionEvidence Selection

  10. Benefit-Targeted Routing and Bounded Revision for LLM-Based Evidence Screening in Manufacturing Supplier Discovery

    Oct 19, 2026Yijiashun Qi, Hanzhe Guo, Yuxuan LiLLM RoutingEvidence Selection

  11. ActiveEvidence: Decision-Focused Evidence Graphs with Verifiable Acquisition Gaps

    Oct 14, 2026Miaobo Hu, Shuhao Hu, Xiaobo Guo +4Evidence SelectionCost-Aware Inference

  12. Benchmarking and Training Reward Models for Cross-Source Evidence Grounding in Search Agents

    Oct 13, 2026Haochen Zhao, Minsheng Hao, Zheng Li +8Evidence-Grounded GenerationAI Agent Benchmarks

  13. From Sampled Evidence to Radiology Reports: Objectives, Constraints, and Realization

    Oct 12, 2026Kun Zhao, Haoteng Tang, Chenghua Lin +1Radiology Report GenerationEvidence-Grounded Generation

  14. Agent-Guided Evidence Acquisition for Emotion-Cause Pair Extraction

    Oct 10, 2026Zhuangzhuang Pan, Yan Xia, Chee Seng ChanEvidence SelectionRelation Extraction

  15. SEEDS: Preview-Guided Evidence Admission for Search Agents

    Oct 9, 2026Jiajin Liu, Chenxi Xu, Dongzhe Fan +2Evidence SelectionAgentic Search

  16. Has LLM Screening Performance Stalled in Software Engineering Systematic Reviews?

    Oct 7, 2026Aleksi Huotala, Miikka Kuutila, Mika MäntyläEvidence SelectionLLM Evaluation

  17. Highlight-Then-Summarize: Learning to Compress Evidence for Long-Context Understanding

    Sep 25, 2026Zhaoyuan Xia, Qinghongbing Xie, Yung Xiang Hue +7Query-Focused SummarizationLong-Context Reasoning in Language Models

  18. AVT-Fabric: Active Visuo-Tactile Perception via Adaptive Evidence Selection for Efficient Robotic Fabric Comparison

    Sep 18, 2026Chang Gao, Zhuo Chen, Suhang Xia +3Evidence SelectionRobotics

  19. A Benchmark Framework for Screening Automation in Systematic Reviews

    Sep 16, 2026Gauransh Kumar, Luciano Marchezan, Guillaume Genois +2LLM EvaluationEvidence Selection

  20. PAGE-RAG: Provenance-Aware Graph Evidence Promotion for Fixed-Budget Multi-hop Retrieval-Augmented Generation

    Aug 30, 2026Haokun Deng, Xunkai Li, Hongchao Qin +1Multi-Hop QARetrieval-Augmented Generation

  21. SciLitBench: Benchmark and Design Principles for LLM-Powered Systematic Literature Reviews

    Aug 29, 2026Miguel Zabaleta, Baihan LinSystematic Review AutomationLLM Evaluation