The evolution of Large Language Models (LLMs) towards autonomous agents has catalyzed progress in Deep Research. While retrieval capabilities are well-benchmarked, the post-retrieval synthesis stage--where agents must digest massive amounts of context and consolidate fragmented evidence into coherent, long-form reports--remains under-evaluated due to the subjectivity of open-ended writing. To bridge this gap, we introduce DeepSynth-Eval, a benchmark designed to objectively evaluate information consolidation capabilities. We leverage high-quality survey papers as gold standards, reverse-engineering research requests and constructing "Oracle Contexts" from their bibliographies to isolate synthesis from retrieval noise. We propose a fine-grained evaluation protocol using General Checklists (for factual coverage) and Constraint Checklists (for structural organization), transforming subjective judgment into verifiable metrics. Experiments across 96 tasks reveal that synthesizing information from hundreds of references remains a significant challenge. Our results demonstrate that agentic plan-and-write workflows significantly outperform single-turn generation, effectively reducing hallucinations and improving adherence to complex structural constraints.
@article{arxiv.2601.03540,
title = {DeepSynth-Eval: Objectively Evaluating Information Consolidation in Deep Survey Writing},
author = {Hongzhi Zhang and Yuanze Hu and Tinghai Zhang and Jia Fu and Tao Wang and Junwei Jing and Zhaoxin Fan and Qi Wang and Ruiming Tang and Han Li and Guorui Zhou and Kun Gai},
journal= {arXiv preprint arXiv:2601.03540},
year = {2026}
}