Autodiscover: A reinforcement learning recommendation system for the cold-start imbalance challenge in active learning, powered by graph-aware thompson sampling

• URL: http://arxiv.org/abs/2602.05087v1
• Date: Wed, 04 Feb 2026 22:16:50 GMT
• Title: Autodiscover: A reinforcement learning recommendation system for the cold-start imbalance challenge in active learning, powered by graph-aware thompson sampling
• Abstract summary: This thesis introduces AutoDiscover, a framework that reframes active learning as an online decision-making problem driven by an adaptive agent.<n>On the 26-dataset SYNERGY benchmark, AutoDiscover achieves higher screening efficiency than static AL baselines.<n>We also introduce TS-Insight, an open-source visual analytics dashboard to interpret, verify, and diagnose the agent's decisions.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Systematic literature reviews (SLRs) are fundamental to evidence-based research, but manual screening is an increasing bottleneck as scientific output grows. Screening features low prevalence of relevant studies and scarce, costly expert decisions. Traditional active learning (AL) systems help, yet typically rely on fixed query strategies for selecting the next unlabeled documents. These static strategies do not adapt over time and ignore the relational structure of scientific literature networks. This thesis introduces AutoDiscover, a framework that reframes AL as an online decision-making problem driven by an adaptive agent. Literature is modeled as a heterogeneous graph capturing relationships among documents, authors, and metadata. A Heterogeneous Graph Attention Network (HAN) learns node representations, which a Discounted Thompson Sampling (DTS) agent uses to dynamically manage a portfolio of query strategies. With real-time human-in-the-loop labels, the agent balances exploration and exploitation under non-stationary review dynamics, where strategy utility changes over time. On the 26-dataset SYNERGY benchmark, AutoDiscover achieves higher screening efficiency than static AL baselines. Crucially, the agent mitigates cold start by bootstrapping discovery from minimal initial labels where static approaches fail. We also introduce TS-Insight, an open-source visual analytics dashboard to interpret, verify, and diagnose the agent's decisions. Together, these contributions accelerate SLR screening under scarce expert labels and low prevalence of relevant studies.

Related papers

• From Static Bibliometrics to Dynamic Knowledge Graphs: An LLM-Powered Framework for Modernizing Science, Technology, and Innovation (STI) Analytics [0.0]
  bibliometric indicators suffer from temporal lag, semantic shallowness, and an inability to capture the non-linear dynamics of contemporary knowledge ecosystems.<n>This paper proposes a hybrid, symbolic-first framework integrating all three traditions under explicit methodological constraint.<n>The framework's central theoretical contribution is treating validation as the mediating principle between semantic flexibility and discipline.
  arXiv  Detail & Related papers  (2026-07-23T13:56:53Z)
• What Are Adversaries Doing? Automating Tactics, Techniques, and Procedures Extraction: A Systematic Review [3.7427783812966364]
  The goal of this study is to aid security researchers in understanding the state of the art in extracting attack tactics, techniques, and procedures (TTPs) from unstructured text.
  arXiv  Detail & Related papers  (2026-04-01T06:25:55Z)
• Strategic Opponent Modeling with Graph Neural Networks, Deep Reinforcement Learning and Probabilistic Topic Modeling [2.233215416354843]
  We review mainly Graph Neural Networks, Deep Reinforcement Learning, and Probabilistic Topic Modeling methods.<n>We analyze the ability to handle uncertainty and heterogeneity, two characteristics that are very common in real-world application cases.<n>We identify certain open challenges specifically, the need to fit non-stationary environments.
  arXiv  Detail & Related papers  (2025-11-13T17:06:56Z)
• Just-in-time Episodic Feedback Hinter: Leveraging Offline Knowledge to Improve LLM Agents Adaptation [77.90555621662345]
  We present JEF Hinter, an agentic system that distills offline traces into compact, context-aware hints.<n>A zooming mechanism highlights decisive steps in long trajectories, capturing both strategies and pitfalls.<n>Experiments on MiniWoB++, WorkArena-L1, and WebArena-Lite show that JEF Hinter consistently outperforms strong baselines.
  arXiv  Detail & Related papers  (2025-10-05T21:34:42Z)
• SAGE: Strategy-Adaptive Generation Engine for Query Rewriting [8.941793732446856]
  We introduce the Strategy-Adaptive Generation Engine (SAGE), which operationalizes expert-crafted strategies in an reinforcement learning framework.<n>SAGE achieves new state-of-the-art NDCG@10 results, but also uncovers a compelling emergent behavior.<n>Our findings demonstrate that strategy-guided RL, enhanced with nuanced reward shaping, offers a scalable, efficient, and more interpretable paradigm for developing the next generation of robust information retrieval systems.
  arXiv  Detail & Related papers  (2025-06-24T16:50:51Z)
• CEGA: A Cost-Effective Approach for Graph-Based Model Extraction and Acquisition [12.65757526181259]
  We evaluate the vulnerability of GNNs to model extraction attacks (MEAs)<n>We propose a node querying strategy tailored to a highly practical yet underexplored scenario.<n>Our approach iteratively refines the node selection mechanism over multiple learning cycles.
  arXiv  Detail & Related papers  (2025-06-21T13:11:42Z)
• GRAIL: A Benchmark for GRaph ActIve Learning in Dynamic Sensing Environments [1.9918773938716672]
  Graph-based Active Learning (AL) leverages the structure of graphs to efficiently prioritize label queries.<n>GRAIL is a benchmarking framework designed to evaluate graph AL strategies in dynamic, real-world environments.
  arXiv  Detail & Related papers  (2025-06-11T19:04:18Z)
• Learning Efficient and Generalizable Graph Retriever for Knowledge-Graph Question Answering [75.12322966980003]
  Large Language Models (LLMs) have shown strong inductive reasoning ability across various domains.<n>Most existing RAG pipelines rely on unstructured text, limiting interpretability and structured reasoning.<n>Recent studies have explored integrating knowledge graphs with LLMs for knowledge graph question answering.<n>We propose RAPL, a novel framework for efficient and effective graph retrieval in KGQA.
  arXiv  Detail & Related papers  (2025-06-11T12:03:52Z)
• Divide by Question, Conquer by Agent: SPLIT-RAG with Question-Driven Graph Partitioning [62.640169289390535]
  SPLIT-RAG is a multi-agent RAG framework that addresses the limitations with question-driven semantic graph partitioning and collaborative subgraph retrieval.<n>The innovative framework first create Semantic Partitioning of Linked Information, then use the Type-Specialized knowledge base to achieve Multi-Agent RAG.<n>The attribute-aware graph segmentation manages to divide knowledge graphs into semantically coherent subgraphs, ensuring subgraphs align with different query types.<n>A hierarchical merging module resolves inconsistencies across subgraph-derived answers through logical verifications.
  arXiv  Detail & Related papers  (2025-05-20T06:44:34Z)
• ORIS: Online Active Learning Using Reinforcement Learning-based Inclusive Sampling for Robust Streaming Analytics System [2.985426781886815]
  We propose ORIS, a method to perform Online active learning using Reinforcement learning-based Inclusive Sampling of documents for labeling.<n>ORIS aims to create a novel Deep Q-Network-based strategy to sample incoming documents that minimize human errors in labeling.<n>We evaluate the ORIS method on emotion recognition tasks, and it outperforms traditional baselines in terms of both human labeling performance and the ML model performance.
  arXiv  Detail & Related papers  (2024-11-27T05:11:37Z)
• ACTRESS: Active Retraining for Semi-supervised Visual Grounding [52.08834188447851]
  A previous study, RefTeacher, makes the first attempt to tackle this task by adopting the teacher-student framework to provide pseudo confidence supervision and attention-based supervision. This approach is incompatible with current state-of-the-art visual grounding models, which follow the Transformer-based pipeline. Our paper proposes the ACTive REtraining approach for Semi-Supervised Visual Grounding, abbreviated as ACTRESS.
  arXiv  Detail & Related papers  (2024-07-03T16:33:31Z)
• A Discrepancy Aware Framework for Robust Anomaly Detection [51.710249807397695]
  We present a Discrepancy Aware Framework (DAF), which demonstrates robust performance consistently with simple and cheap strategies. Our method leverages an appearance-agnostic cue to guide the decoder in identifying defects, thereby alleviating its reliance on synthetic appearance. Under the simple synthesis strategies, it outperforms existing methods by a large margin. Furthermore, it also achieves the state-of-the-art localization performance.
  arXiv  Detail & Related papers  (2023-10-11T15:21:40Z)
• Active Learning for Abstractive Text Summarization [50.79416783266641]
  We propose the first effective query strategy for Active Learning in abstractive text summarization. We show that using our strategy in AL annotation helps to improve the model performance in terms of ROUGE and consistency scores.
  arXiv  Detail & Related papers  (2023-01-09T10:33:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.