AI Paper Atlas

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

OrchestrationBench: LLM-Driven Agentic Planning and Tool Use in Multi-Domain Scenarios

Aelim Ahn, Sooyeon Lee, Hyosun Wang, Chiwan Park, Daeryong Kim, Jihyeon Roh, Kichang Yang, Wonjun Jang, Hwang Woosung, Min Seok Kim, Jihoon kang

ICLR 2026 · Large language models › Agents, code and math · approach: Long-horizon LLM agents

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 Claude-sonnet-4 on English instead of Korean dataclaude-sonnet-4 · OrchestrationBenchcall/reject accuracy: 0.7586->0.8682Improved
Larger or stronger planner (Gemini-2.5-pro instead of GPT-4.1-nano)main LLM planning · OrchestrationBench Englishplanning score (1-GED): 0.462 -> 0.850Improved
Use GPT-5 with low reasoning effort for planning instead of GPT-4.1gpt-5 · OrchestrationBench Englishplanning score: 0.744 -> 0.583Hurt
Use dense Qwen3-235B-A22B instead of MoE variants for planningQwen3 · OrchestrationBench Englishplanning score: 0.768Mixed
Compare planning vs function calling spread across modelsLLM orchestration · OrchestrationBenchscore variation: 0.057 to 0.850Mixed
Correlate workflow score with function calling scoremodels · OrchestrationBench Englishcorrelation: 0.9215Improved
Correlate workflow score with call/reject accuracymodels · OrchestrationBench Koreancorrelation: 0.4480No clear effect
Use Claude-sonnet-4 for function calling instead of Gemini-2.5-proclaude-sonnet-4 · OrchestrationBench Englishfunction calling score: 0.836 -> 0.885Improved
Use Gemini-2.5-pro for Korean call/reject instead of Qwen3-30B-A3BGemini-2.5-pro · OrchestrationBench Koreancall/reject accuracy: 0.449 -> 0.813Improved

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