A Benchmark for Deep Information Synthesis

• URL: http://arxiv.org/abs/2602.21143v1
• Date: Tue, 24 Feb 2026 17:43:32 GMT
• Title: A Benchmark for Deep Information Synthesis
• Authors: Debjit Paul, Daniel Murphy, Milan Gritta, Ronald Cardenas, Victor Prokhorov, Lena Sophia Bolliger, Aysim Toker, Roy Miles, Andreea-Maria Oncescu, Jasivan Alex Sivakumar, Philipp Borchert, Ismail Elezi, Meiru Zhang, Ka Yiu Lee, Guchun Zhang, Jun Wang, Gerasimos Lampouras,
• Abstract summary: DEEPSYNTH is a novel benchmark designed to evaluate large language model (LLM)-based agents on realistic, time-consuming problems.<n>It contains 120 tasks collected across 7 domains and data sources covering 67 countries.<n>When evaluated on DEEPSYNTH, 11 state-of-the-art LLMs and deep research agents achieve a maximum F1 score of 8.97 and 17.5 on the LLM-judge metric.
• Score: 27.87976801124957
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language model (LLM)-based agents are increasingly used to solve complex tasks involving tool use, such as web browsing, code execution, and data analysis. However, current evaluation benchmarks do not adequately assess their ability to solve real-world tasks that require synthesizing information from multiple sources and inferring insights beyond simple fact retrieval. To address this, we introduce DEEPSYNTH, a novel benchmark designed to evaluate agents on realistic, time-consuming problems that combine information gathering, synthesis, and structured reasoning to produce insights. DEEPSYNTH contains 120 tasks collected across 7 domains and data sources covering 67 countries. DEEPSYNTH is constructed using a multi-stage data collection pipeline that requires annotators to collect official data sources, create hypotheses, perform manual analysis, and design tasks with verifiable answers. When evaluated on DEEPSYNTH, 11 state-of-the-art LLMs and deep research agents achieve a maximum F1 score of 8.97 and 17.5 on the LLM-judge metric, underscoring the difficulty of the benchmark. Our analysis reveals that current agents struggle with hallucinations and reasoning over large information spaces, highlighting DEEPSYNTH as a crucial benchmark for guiding future research.

Related papers

• GISA: A Benchmark for General Information-Seeking Assistant [102.30831921333755]
  GISA is a benchmark for General Information-Seeking Assistants comprising 373 human-crafted queries.<n>It integrates both deep reasoning and broad information aggregation within unified tasks, and includes a live subset with periodically updated answers to resist memorization.<n>Experiments on mainstream LLMs and commercial search products reveal that even the best-performing model achieves only 19.30% exact match score.
  arXiv  Detail & Related papers  (2026-02-09T11:44:15Z)
• LongDA: Benchmarking LLM Agents for Long-Document Data Analysis [55.32211515932351]
  LongDA targets real-world settings in which navigating long documentation and complex data is the primary bottleneck.<n>LongTA is a tool-augmented agent framework that enables document access, retrieval, and code execution.<n>Our experiments reveal substantial performance gaps even among state-of-the-art models.
  arXiv  Detail & Related papers  (2026-01-05T23:23:16Z)
• ConDABench: Interactive Evaluation of Language Models for Data Analysis [10.177407781044279]
  We introduce ConDABench, a framework for generating conversational data analysis (ConDA) benchmarks and evaluating external tools.<n>bench consists of (a) a multi-agent workflow for generating realistic benchmarks from articles describing insights gained from public datasets, (b) 1,420 ConDA problems generated using this workflow, and (c) an evaluation harness that, for the first time, makes it possible to systematically evaluate conversational data analysis tools on the generated ConDA problems.
  arXiv  Detail & Related papers  (2025-10-10T15:54:51Z)
• 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)
• IDA-Bench: Evaluating LLMs on Interactive Guided Data Analysis [60.32962597618861]
  IDA-Bench is a novel benchmark evaluating large language models in multi-round interactive scenarios.<n>Agent performance is judged by comparing its final numerical output to the human-derived baseline.<n>Even state-of-the-art coding agents (like Claude-3.7-thinking) succeed on 50% of the tasks, highlighting limitations not evident in single-turn tests.
  arXiv  Detail & Related papers  (2025-05-23T09:37:52Z)
• MIMDE: Exploring the Use of Synthetic vs Human Data for Evaluating Multi-Insight Multi-Document Extraction Tasks [0.0]
  We define a set of tasks, Multi-Insight Multi-Document Extraction (MIMDE) tasks.<n>This task is fundamental to many practical applications, from analyzing survey responses to processing medical records.<n>We introduce a novel set of complementary human and synthetic datasets to examine the potential of synthetic data for evaluation.
  arXiv  Detail & Related papers  (2024-11-29T13:24:10Z)
• DSBench: How Far Are Data Science Agents from Becoming Data Science Experts? [58.330879414174476]
  We introduce DSBench, a benchmark designed to evaluate data science agents with realistic tasks.<n>This benchmark includes 466 data analysis tasks and 74 data modeling tasks, sourced from Eloquence and Kaggle competitions.<n>Our evaluation of state-of-the-art LLMs, LVLMs, and agents shows that they struggle with most tasks, with the best agent solving only 34.12% of data analysis tasks and achieving a 34.74% Relative Performance Gap (RPG)
  arXiv  Detail & Related papers  (2024-09-12T02:08:00Z)
• DiscoveryBench: Towards Data-Driven Discovery with Large Language Models [50.36636396660163]
  We present DiscoveryBench, the first comprehensive benchmark that formalizes the multi-step process of data-driven discovery. Our benchmark contains 264 tasks collected across 6 diverse domains, such as sociology and engineering. Our benchmark, thus, illustrates the challenges in autonomous data-driven discovery and serves as a valuable resource for the community to make progress.
  arXiv  Detail & Related papers  (2024-07-01T18:58:22Z)

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.