Papers
arxiv:2601.03540

DeepSynth-Eval: Objectively Evaluating Information Consolidation in Deep Survey Writing

Published on Jan 7
Authors:
,
,
,
,
,
,
,
,
,
,
,

Abstract

DeepSynth-Eval benchmark evaluates LLMs' information consolidation capabilities through objective metrics derived from survey papers, demonstrating superior performance of plan-and-write workflows over single-turn generation.

AI-generated summary

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.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2601.03540 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2601.03540 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2601.03540 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.