List your company

Multi-Hop Question Answering on MuSiQue (EM, F1aware)

16.1EMSearch-R1
0.8124.7818.7512.719Dec 18, 2025

Evaluation results

MethodLinks
Search-R1Base Model=Qwen2.5-3B-Instruct, Category=Outcome RL Baselines2025.1216.10
Search-R1Base Model=Llama-3.2-3B-Instruct, Category=Outcome RL Baselines2025.1214.61.3
ADASEARCHBase Model=Qwen2.5-3B-Instruct, Category=Paper Method2025.1214.425.2
ADASEARCHBase Model=Llama-3.2-3B-Instruct, Category=Paper Method2025.1213.236.5
Awareness ShapingBase Model=Llama-3.2-3B-Instruct, Category=Reward-Shaping Baselines2025.121331.4
Awareness ShapingBase Model=Qwen2.5-3B-Instruct, Category=Reward-Shaping Baselines2025.1212.521.7
IKEABase Model=Qwen2.5-3B-Instruct, Category=Reward-Shaping Baselines2025.1211.514.2
Naive ShapingBase Model=Llama-3.2-3B-Instruct, Category=Reward-Shaping Baselines2025.1211.521.1
IKEABase Model=Llama-3.2-3B-Instruct, Category=Reward-Shaping Baselines2025.1211.231.9
Naive ShapingBase Model=Qwen2.5-3B-Instruct, Category=Reward-Shaping Baselines2025.129.915.8
RL w/o searchBase Model=Llama-3.2-3B-Instruct, Category=Outcome RL Baselines2025.126.76.7
RL w/o searchBase Model=Qwen2.5-3B-Instruct, Category=Outcome RL Baselines2025.125.95.9
CoTBase Model=Llama-3.2-3B-Instruct, Category=Prompting Baselines2025.124.54.5
RAGBase Model=Qwen2.5-3B-Instruct, Category=Prompting Baselines2025.124.40
RAGBase Model=Llama-3.2-3B-Instruct, Category=Prompting Baselines2025.124.10
CoTBase Model=Qwen2.5-3B-Instruct, Category=Prompting Baselines2025.123.93.9
Direct AnswerBase Model=Llama-3.2-3B-Instruct, Category=Prompting Baselines2025.1233
Direct AnswerBase Model=Qwen2.5-3B-Instruct, Category=Prompting Baselines2025.121.41.4