BrowseComp benchmark for web browsing agent evaluation
| Name | Categories | Topics | References | Credibility | CreateDate | UpdateDate | Title | RelatedNotes | NavigationOrder | Eleventy | TemplateEngineOverride | Created |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 20260610_searchswarm_delegation_intelligence_agentic_llm_long_horizon_research | paper_analysis | agent_architecture, multi_agent_systems, reasoning, workflow_optimization, reasoning_memory | tsinghua_university, pku, ant_group, browsecomp, searchswarm | 100 | SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Research | lintree_explicitly_structured_search_histories, aip_graph_representation_for_learning_and_governing_agent_skills, aflow_automating_agentic_workflow_generation, apwa_parallelizable_agentic_workflows, scaling_large_language_model_multi_agent_collaboration | [object Object] | [object Object] | md |