AI Paper Atlas

Research map / Large language models / Agents, code and math

DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents

Mingxuan Du, Benfeng Xu, Chiwei Zhu, Licheng Zhang, Xiaorui Wang, Zhendong Mao

ICLR 2026 · Large language models › Agents, code and math · approach: Agent instruction-following benchmarks · 234 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use reference-based scoring (add reference report) in RACE (ablation)RACE · Human consistency (50 Chinese tasks)pairwise agreement rate (%): 66.56 -> 71.33Improved
use RACE instead of vanilla direct-scoring prompt (ablation)Gemini-2.5-pro judge · Human consistency (50 Chinese tasks)pairwise agreement rate (%): 58.89 -> 71.33Improved
add adaptive task-specific criteria instead of static criteria (ablation)RACE · Human consistency (50 Chinese tasks)pairwise agreement rate (%): 68.33 -> 71.33Improved
add dynamic criteria weights (ablation)RACE · Human consistency (50 Chinese tasks)pairwise agreement rate (%): 70.67 -> 71.33Improved
add dynamic dimension weights (ablation)RACE · Human consistency (50 Chinese tasks)pairwise agreement rate (%): 70.89 -> 71.33Improved
keep reference as second position (vs swapping reference and target positions) (ablation)RACE · Human consistency (50 Chinese tasks)pairwise agreement rate (%): 69.56 -> 71.33Improved
use Gemini 2.5 Pro Preview as judge instead of o3 (ablation)RACE · Human consistency (50 Chinese tasks)pairwise agreement rate (%): 68.11 -> 71.33Improved
use cheaper o4-mini as judge instead of Gemini 2.5 Pro Preview (ablation)RACE · Human consistency (50 Chinese tasks)pairwise agreement rate (%) / cost: 71.33 -> 70.89; cost 0.13 -> 0.04Mixed
deep research agent design (vs LLM with search tools) for report qualityGemini-2.5-Pro · DeepResearch Bench (RACE)RACE overall score: 35.12 -> 48.88Improved
allow multi-turn web searches for Claude-3.7 vs single-turn search modelsClaude-3.7-Sonnet w/Search · DeepResearch Bench (RACE)RACE overall score: 28.48 -> 40.67Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy