CorpusQA: A 10 Million Token Benchmark for Corpus-Level Analysis and Reasoning

• URL: http://arxiv.org/abs/2601.14952v1
• Date: Wed, 21 Jan 2026 12:52:30 GMT
• Title: CorpusQA: A 10 Million Token Benchmark for Corpus-Level Analysis and Reasoning
• Authors: Zhiyuan Lu, Chenliang Li, Yingcheng Shi, Weizhou Shen, Ming Yan, Fei Huang,
• Abstract summary: We introduce CorpusQA, a new benchmark scaling up to 10 million tokens, generated via a novel data synthesis framework.<n>We show that finetuning on our synthesized data effectively enhances an LLM's general long-context reasoning capabilities.<n>Our findings indicate that memory-augmented agentic architectures offer a more robust alternative.
• Score: 48.56088080889236
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While large language models now handle million-token contexts, their capacity for reasoning across entire document repositories remains largely untested. Existing benchmarks are inadequate, as they are mostly limited to single long texts or rely on a "sparse retrieval" assumption-that answers can be derived from a few relevant chunks. This assumption fails for true corpus-level analysis, where evidence is highly dispersed across hundreds of documents and answers require global integration, comparison, and statistical aggregation. To address this critical gap, we introduce CorpusQA, a new benchmark scaling up to 10 million tokens, generated via a novel data synthesis framework. By decoupling reasoning from textual representation, this framework creates complex, computation-intensive queries with programmatically guaranteed ground-truth answers, challenging systems to perform holistic reasoning over vast, unstructured text without relying on fallible human annotation. We further demonstrate the utility of our framework beyond evaluation, showing that fine-tuning on our synthesized data effectively enhances an LLM's general long-context reasoning capabilities. Extensive experiments reveal that even state-of-the-art long-context LLMs struggle as input length increases, and standard retrieval-augmented generation systems collapse entirely. Our findings indicate that memory-augmented agentic architectures offer a more robust alternative, suggesting a critical shift is needed from simply extending context windows to developing advanced architectures for global information synthesis.

Related papers

• 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)
• BoundRL: Efficient Structured Text Segmentation through Reinforced Boundary Generation [26.825801831400003]
  BoundRL performs token-level text segmentation and label prediction for long structured texts.<n>Instead of generating complete contents for each segment, it generates only a sequence of starting tokens.<n>It reconstructs the complete contents by locating these tokens within the original texts.
  arXiv  Detail & Related papers  (2025-10-23T02:56:10Z)
• LLM-guided Hierarchical Retrieval [54.73080745446999]
  LATTICE is a hierarchical retrieval framework that enables an LLM to reason over and navigate large corpora with logarithmic search complexity.<n>A central challenge in such LLM-guided search is that the model's relevance judgments are noisy, context-dependent, and unaware of the hierarchy.<n>Our framework achieves state-of-the-art zero-shot performance on the reasoning-intensive BRIGHT benchmark.
  arXiv  Detail & Related papers  (2025-10-15T07:05:17Z)
• Who Gets Cited Most? Benchmarking Long-Context Language Models on Scientific Articles [81.89404347890662]
  SciTrek is a novel question-answering benchmark designed to evaluate the long-context reasoning capabilities of large language models (LLMs) using scientific articles.<n>Our analysis reveals systematic shortcomings in models' abilities to perform basic numerical operations and accurately locate specific information in long contexts.
  arXiv  Detail & Related papers  (2025-09-25T11:36:09Z)
• Loong: Synthesize Long Chain-of-Thoughts at Scale through Verifiers [103.4410890572479]
  We introduce the Loong Project: an open-source framework for scalable synthetic data generation and verification.<n>LoongBench is a curated seed dataset containing 8,729 human-vetted examples across 12 domains.<n>LoongEnv is a modular synthetic data generation environment that supports multiple prompting strategies to produce new question-answer-code triples.
  arXiv  Detail & Related papers  (2025-09-03T06:42:40Z)
• A Controllable Examination for Long-Context Language Models [62.845852724511964]
  This study introduces $textbfLongBioBench, a benchmark for evaluating long-context language models.<n>We show that most models still exhibit deficiencies in semantic understanding and elementary reasoning over retrieved results.<n>Our further analysis indicates some design choices employed by existing synthetic benchmarks, such as contextual non-coherence.
  arXiv  Detail & Related papers  (2025-06-03T14:23:06Z)
• ELITE: Embedding-Less retrieval with Iterative Text Exploration [5.8851517822935335]
  Large Language Models (LLMs) have achieved impressive progress in natural language processing.<n>Their limited ability to retain long-term context constrains performance on document-level or multi-turn tasks.
  arXiv  Detail & Related papers  (2025-05-17T08:48:43Z)
• Reasoning with LLMs for Zero-Shot Vulnerability Detection [0.9208007322096533]
  We present textbfVulnSage, a comprehensive evaluation framework and a curated dataset from diverse, large-scale open-source system software projects.<n>The framework supports multi-granular analysis across function, file, and inter-function levels.<n>It employs four diverse zero-shot prompt strategies: Baseline, Chain-of-context, Think, and Think & verify.
  arXiv  Detail & Related papers  (2025-03-22T23:59:17Z)

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.