AI Paper Atlas

Research map / Multi-agent systems and games / LLM agents

LiveResearchBench: Benchmarking Single- and Multi-Agent Systems for Citation-Grounded Deep Research

Jiayu Wang, Yifei Ming, Riya Dulepet, Qinglin Chen, Austin Xu, Zixuan Ke, Frederic Sala, Aws Albarghouthi, Caiming Xiong, Shafiq Joty

ICLR 2026 · Multi-agent systems and games › LLM agents · approach: Robust and efficient agent execution

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Introduces LiveResearchBench, a benchmark of user-centric, dynamic, unambiguous deep-research tasks for evaluating single- and multi-agent systems that produce citation-backed reports from live web search.

Problem

Evaluating deep research agents that produce comprehensive, citation-backed reports by searching hundreds of live websites lacks rigorous benchmarks satisfying user-centricity, dynamism, and unambiguity.

Approach

A benchmark whose tasks are built around realistic user information needs, require up-to-date live web information beyond parametric knowledge, and are phrased unambiguously so that outputs can be consistently judged; it is used to benchmark both single- and multi-agent deep research systems.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use multi-agent deep research systems instead of single-agent systemsdeep research systems · LiveResearchBenchaverage DeepEval score: 62.8 (single web) -> 69.5 (multi-agent)Improved
use multi-agent system for citation associationdeep research systems · LiveResearchBenchCitation Association: 61.9 avg multi-agent; Deerflow+ 77.0 vs o3 Deep Research 25.6Improved
use single-agent deep research (longer reasoning) rather than web-search agentdeep research systems · LiveResearchBenchCitation Association: GPT-5 67.6 -> o3 Deep Research 25.6Hurt
use multi-agent systems for coverageDeerflow+ / Open Deep Research · LiveResearchBenchCoverage & Comprehensiveness: GPT-5 83.4 vs Deerflow+ 61.6, ODR 65.3Hurt
longer reportsdeep research systems · LiveResearchBenchreport qualityNo clear effect
use multi-judge ensemble (Gemini 2.5 Pro + GPT-5) instead of direct 0-10 rating (ablation)DeepEval · human agreementagreement with humans: <60% (direct rating) -> 98.3% (checklist, ensemble)Improved
use checklist protocol for presentation (ablation)DeepEval · Presentation & Organizationhuman agreement (%): 98.3Improved

Experimental setup

Benchmarks: LiveResearchBench

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