ScholarGym: Benchmarking Deep Research Workflows on Academic Literature Retrieval

• URL: http://arxiv.org/abs/2601.21654v1
• Date: Thu, 29 Jan 2026 12:51:44 GMT
• Title: ScholarGym: Benchmarking Deep Research Workflows on Academic Literature Retrieval
• Authors: Hao Shen, Hang Yang, Zhouhong Gu,
• Abstract summary: We present ScholarGym, a simulation environment for reproducible evaluation of deep research on academic literature.<n>Built on a static corpus of 570K papers with deterministic retrieval, ScholarGym provides 2,536 queries with expert-annotated ground truth.
• Score: 11.41528830724814
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Tool-augmented large language models have advanced from single-turn question answering to deep research workflows that iteratively plan queries, invoke external tools, and synthesize information to address complex information needs. Evaluating such workflows presents a fundamental challenge: reliance on live APIs introduces non-determinism, as tool invocations may yield different results across runs due to temporal drift, rate limiting, and evolving backend states. This variance undermines reproducibility and invalidates cross-system comparisons. We present ScholarGym, a simulation environment for reproducible evaluation of deep research workflows on academic literature. The environment decouples workflow components into query planning, tool invocation, and relevance assessment, enabling fine-grained analysis of each stage under controlled conditions. Built on a static corpus of 570K papers with deterministic retrieval, ScholarGym provides 2,536 queries with expert-annotated ground truth. Experiments across diverse backbone models reveal how reasoning capabilities, planning strategies, and selection mechanisms interact over iterative refinement.

Related papers

• AnalyticsGPT: An LLM Workflow for Scientometric Question Answering [1.5658704610960574]
  AnalyticsGPT is an intuitive and efficient large language model (LLM)-powered workflow for scientometric question answering.<n>This paper introduces AnalyticsGPT, an intuitive and efficient large language model (LLM)-powered workflow for scientometric question answering.
  arXiv  Detail & Related papers  (2026-02-10T14:23:55Z)
• MADE: Benchmark Environments for Closed-Loop Materials Discovery [26.575933886112157]
  We introduce MAterials Discovery Environments (MADE), a novel framework for benchmarking end-to-end autonomous materials discovery pipelines.<n>We formalize discovery as a search for thermodynamically stable compounds relative to a given convex hull, and evaluate efficacy and efficiency via comparison to baseline algorithms.<n>We demonstrate this by conducting systematic experiments across a family of systems, enabling ablation of components in discovery pipelines, and comparison of how methods scale with system complexity.
  arXiv  Detail & Related papers  (2026-01-28T19:46:46Z)
• AgentLongBench: A Controllable Long Benchmark For Long-Contexts Agents via Environment Rollouts [78.33143446024485]
  We introduce textbfAgentLongBench, which evaluates agents through simulated environment rollouts based on Lateral Thinking Puzzles.<n>This framework generates rigorous interaction trajectories across knowledge-intensive and knowledge-free scenarios.
  arXiv  Detail & Related papers  (2026-01-28T16:05:44Z)
• DeepResearchEval: An Automated Framework for Deep Research Task Construction and Agentic Evaluation [56.886936435727854]
  DeepResearchEval is an automated framework for deep research task construction and agentic evaluation.<n>For task construction, we propose a persona-driven pipeline generating realistic, complex research tasks anchored in diverse user profiles.<n>For evaluation, we propose an agentic pipeline with two components: an Adaptive Point-wise Quality Evaluation that dynamically derives task-specific evaluation dimensions, criteria, and weights conditioned on each generated task, and an Active Fact-Checking that autonomously extracts and verifies report statements via web search, even when citations are missing.
  arXiv  Detail & Related papers  (2026-01-14T18:38:31Z)
• DeepSynth-Eval: Objectively Evaluating Information Consolidation in Deep Survey Writing [53.85037373860246]
  We introduce Deep Synth-Eval, a benchmark designed to objectively evaluate information consolidation capabilities.<n>We propose a fine-grained evaluation protocol using General Checklists (for factual coverage) and Constraint Checklists (for structural organization)<n>Our results demonstrate that agentic plan-and-write significantly outperform single-turn generation.
  arXiv  Detail & Related papers  (2026-01-07T03:07:52Z)
• LLM Agents for Interactive Workflow Provenance: Reference Architecture and Evaluation Methodology [3.470217255779291]
  We introduce an evaluation methodology, reference architecture, and open-source implementation that leverages interactive Large Language Model (LLM) agents for runtime data analysis.<n>Our approach uses a lightweight, metadata-driven design that translates natural language into structured provenance queries.<n> Evaluations across LLaMA, GPT, Gemini, and Claude, covering diverse query classes and a real-world chemistry workflow, show that modular design, prompt tuning, and Retrieval-Augmented Generation (RAG) enable accurate and insightful agent responses.
  arXiv  Detail & Related papers  (2025-09-17T13:51:29Z)
• Benchmarking Deep Search over Heterogeneous Enterprise Data [73.55304268238474]
  We present a new benchmark for evaluating a form of retrieval-augmented generation (RAG)<n>RAG requires source-aware, multi-hop reasoning over diverse, sparsed, but related sources.<n>We build it using a synthetic data pipeline that simulates business across product planning, development, and support stages.
  arXiv  Detail & Related papers  (2025-06-29T08:34:59Z)
• Pointwise Mutual Information as a Performance Gauge for Retrieval-Augmented Generation [78.28197013467157]
  We show that the pointwise mutual information between a context and a question is an effective gauge for language model performance.<n>We propose two methods that use the pointwise mutual information between a document and a question as a gauge for selecting and constructing prompts that lead to better performance.
  arXiv  Detail & Related papers  (2024-11-12T13:14:09Z)
• NeedleBench: Evaluating LLM Retrieval and Reasoning Across Varying Information Densities [51.07379913779232]
  NeedleBench is a framework for assessing retrieval and reasoning performance in long-context tasks.<n>It embeds key data points at varying depths to rigorously test model capabilities.<n>Our experiments reveal that reasoning models like Deep-R1 and OpenAI's o3 struggle with continuous retrieval and reasoning in information-dense scenarios.
  arXiv  Detail & Related papers  (2024-07-16T17:59:06Z)
• Deep Learning Schema-based Event Extraction: Literature Review and Current Trends [60.29289298349322]
  Event extraction technology based on deep learning has become a research hotspot. This paper fills the gap by reviewing the state-of-the-art approaches, focusing on deep learning-based models.
  arXiv  Detail & Related papers  (2021-07-05T16:32:45Z)

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.