List your company

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

38.2EMSearch-R1
11.47218.41125.3532.289Dec 18, 2025

Evaluation results

MethodLinks
Search-R1Base Model=Llama-3.2-3B-Instruct, Category=Outcome RL Baselines2025.1238.26.6
Search-R1Base Model=Qwen2.5-3B-Instruct, Category=Outcome RL Baselines2025.1236.90.1
ADASEARCHBase Model=Llama-3.2-3B-Instruct, Category=Paper Method2025.1234.459.2
Awareness ShapingBase Model=Llama-3.2-3B-Instruct, Category=Reward-Shaping Baselines2025.1233.757.5
ADASEARCHBase Model=Qwen2.5-3B-Instruct, Category=Paper Method2025.1233.457.5
IKEABase Model=Llama-3.2-3B-Instruct, Category=Reward-Shaping Baselines2025.1232.358.2
Awareness ShapingBase Model=Qwen2.5-3B-Instruct, Category=Reward-Shaping Baselines2025.1232.157.5
IKEABase Model=Qwen2.5-3B-Instruct, Category=Reward-Shaping Baselines2025.123258.1
Naive ShapingBase Model=Llama-3.2-3B-Instruct, Category=Reward-Shaping Baselines2025.1231.252.6
Naive ShapingBase Model=Qwen2.5-3B-Instruct, Category=Reward-Shaping Baselines2025.1229.849.3
RAGBase Model=Qwen2.5-3B-Instruct, Category=Prompting Baselines2025.1224.60
RL w/o searchBase Model=Llama-3.2-3B-Instruct, Category=Outcome RL Baselines2025.1223.723.7
RAGBase Model=Llama-3.2-3B-Instruct, Category=Prompting Baselines2025.1220.60
RL w/o searchBase Model=Qwen2.5-3B-Instruct, Category=Outcome RL Baselines2025.1220.520.5
CoTBase Model=Qwen2.5-3B-Instruct, Category=Prompting Baselines2025.1217.317.3
CoTBase Model=Llama-3.2-3B-Instruct, Category=Prompting Baselines2025.1216.316.3
Direct AnswerBase Model=Qwen2.5-3B-Instruct, Category=Prompting Baselines2025.1213.213.2
Direct AnswerBase Model=Llama-3.2-3B-Instruct, Category=Prompting Baselines2025.1212.512.5