mlsanityData to 7 Oct 2026

DeepEra: A Deep Evidence Reranking Agent for Scientific Retrieval-Augmented Generated Question Answering

arXiv 2601.16478 ↗First posted 23 Jan 2026cs.CL cs.AIcited by 2

On the map: Retrieval-augmented generation → Agentic RAG, agents and memory

also in 1 more
Abstract (arXiv)

With the rapid growth of scientific literature, scientific question answering (SciQA) has become increasingly critical for exploring and utilizing scientific knowledge. Retrieval-Augmented Generation (RAG) enhances LLMs by incorporating knowledge from external sources, thereby providing credible evidence for scientific question answering. But existing retrieval and reranking methods remain vulnerable to passages that are semantically similar but logically irrelevant, often reducing factual reliability and amplifying hallucinations.To address this challenge, we propose a Deep Evidence Reranking Agent (DeepEra) that integrates step-by-step reasoning, enabling more precise evaluation of candidate passages beyond surface-level semantics. To support systematic evaluation, we construct SciRAG-SSLI (Scientific RAG - Semantically Similar but Logically Irrelevant), a large-scale dataset comprising about 300K SciQA instances across 10 subjects, constructed from 10M scientific corpus. The dataset combines naturally retrieved contexts with systematically generated distractors to test logical robustness and factual grounding. Comprehensive evaluations confirm that our approach achieves superior retrieval performance compared to leading rerankers. To our knowledge, this work is the first to comprehensively study and empirically validate innegligible SSLI issues in two-stage RAG frameworks.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Agentic RAG, agents and memory, one of 15 directions in Retrieval-augmented generation. Builds on 29 of its 49 references that are in the map. First posted on arXiv 23 Jan 2026.

Builds on

29 of 49 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025SciRerankBench: Benchmarking Rerankers Towards Scientific Retrieval-Augmented Generated LLMs12 Aug
  2. 2023PaperQA: Retrieval-Augmented Generative Agent for Scientific Research8 Dec

Other references · 27

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  3. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  4. 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,414
  5. 2023Towards General Text Embeddings with Multi-stage Contrastive Learningcited by 705
  6. 2019Passage Re-ranking with BERTcited by 629
  7. 2021ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interactioncited by 464
  8. 2024LLM2Vec: Large Language Models Are Secretly Powerful Text Encoderscited by 396
  9. 2020Document Ranking with a Pretrained Sequence-to-Sequence Modelcited by 373
  10. 2021SPLADE: Sparse Lexical and Expansion Model for First Stage Rankingcited by 283
  11. 2022OpenAlex: A fully-open index of scholarly works, authors, venues, institutions, and conceptscited by 166
  12. 2023RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze!cited by 151
15 more
  1. 2023Factuality Challenges in the Era of Large Language Modelscited by 125
  2. 2022RankT5: Fine-Tuning T5 for Text Ranking with Ranking Lossescited by 114
  3. 2024Enhancing Noise Robustness of Retrieval-Augmented Language Models with Adaptive Adversarial Trainingcited by 88
  4. 2025PaSa: An LLM Agent for Comprehensive Academic Paper Searchcited by 61
  5. 2025Rank-R1: Enhancing Reasoning in LLM-based Document Rerankers via Reinforcement Learningcited by 58
  6. 2024Don't Forget to Connect! Improving RAG with Graph-based Rerankingcited by 49
  7. 2024IM-RAG: Multi-Round Retrieval-Augmented Generation Through Learning Inner Monologuescited by 40
  8. 2024ListT5: Listwise Reranking with Fusion-in-Decoder Improves Zero-shot Retrievalcited by 29
  9. 2023An Empirical Comparison of LM-based Question and Answer Generation Methodscited by 15
  10. 2024TWOLAR: a TWO-step LLM-Augmented distillation method for passage Rerankingcited by 11
  11. 2025DeAR: Dual-Stage Document Reranking with Reasoning Agents via LLM Distillationcited by 11
  12. 2024InRanker: Distilled Rankers for Zero-shot Information Retrievalcited by 8
  13. 2026ScienceDB AI: An LLM-Driven Agentic Recommender System for Large-Scale Scientific Data Sharing Servicescited by 5
  14. 2025LimRank: Less is More for Reasoning-Intensive Information Rerankingcited by 3
  15. 2023A scientometric analysis of the effect of COVID-19 on the spread of research outputscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Local-to-Global Sentence-Level Graph Reranking for Scientific Synthesiscited by 0
  2. 2026SciLENS: RL-Driven Autonomous Agents for Scientific Localized Evidence Navigation and Synthesiscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Re-ranking and Late Interaction Drive Retrieval Quality: A Controlled Comparison of RAG Strategies for Scientific Question Answering
  2. 2026SciRet: A Compute-Aware Empirical Study of Retrieval and Reranking for Scientific RAG
  3. 2025SQuAI: Scientific Question-Answering with Multi-Agent Retrieval-Augmented Generation
  4. 2026VecTree-RAG: An Agentic Retrieval-Augmented Generation Framework Combining Vector and Tree Retrieval for Efficiency and Accuracy
  5. 2026LitTraceQA: A Benchmark for Multi-Stage Grounding and Verification in Scientific Question Answering
  6. 2025MuISQA: Multi-Intent Retrieval-Augmented Generation for Scientific Question Answering
  7. 2025HiPerRAG: High-Performance Retrieval Augmented Generation for Scientific Insights
  8. 2026Prism-Reranker: Beyond Relevance Scoring -- Jointly Producing Contributions and Evidence for Agentic Retrieval