List your company

Question Answering on TriviaQA (test) (Acc and F1)

80.6F1 ScoreIGPO
19.000834.992950.98566.9771Oct 16, 2025Nov 2, 2025Nov 19, 2025Dec 6, 2025Dec 23, 2025Jan 9, 2026Jan 27, 2026

Evaluation results

MethodLinks
IGPOMethod Category=Step-reward RL-based2025.1080.6—
DeepResearcherMethod Category=Outcome-reward RL-based2025.1078.4—
R1-searcherMethod Category=Outcome-reward RL-based2025.1073.1—
Search-r1-baseMethod Category=Outcome-reward RL-based2025.1071.9—
CoT+RAGMethod Category=Prompt-based2025.1068.9—
GiGPOMethod Category=Step-reward RL-based2025.1064.7—
Search-o1Method Category=Prompt-based2025.1058.9—
CoTMethod Category=Prompt-based2025.1045.6—
Search-r1-instructMethod Category=Outcome-reward RL-based2025.1044.7—
UR-RAGRank-By=Utility, LLM Backbone=Qwen-14B, Retrieval Method=BM252026.0142.3941.86
RePlugRank-By=Utility, LLM Backbone=Qwen-14B, Retrieval Method=BM252026.0141.2541.12
LURE-RAGRank-By=Utility, LLM Backbone=Qwen-14B, Retrieval Method=BM252026.0140.4740.57
LURE-RAG (w/o topics)Rank-By=Utility, LLM Backbone=Qwen-14B, Retrieval Method=BM252026.0140.0140.08
k-shotRank-By=Relevance, LLM Backbone=Qwen-14B, Retrieval Method=BM252026.0139.7839.76
0-shotRank-By=Relevance, LLM Backbone=Qwen-14B, Retrieval Method=BM252026.0135.8735.66
UR-RAGRank-By=Utility, LLM Backbone=phi-3.8B, Retrieval Method=BM252026.0134.7236.76
RePlugRank-By=Utility, LLM Backbone=phi-3.8B, Retrieval Method=BM252026.0133.2136.03
LURE-RAGRank-By=Utility, LLM Backbone=phi-3.8B, Retrieval Method=BM252026.0132.7235.69
LURE-RAG (w/o topics)Rank-By=Utility, LLM Backbone=phi-3.8B, Retrieval Method=BM252026.0132.6135.44
k-shotRank-By=Relevance, LLM Backbone=phi-3.8B, Retrieval Method=BM252026.0131.7734.86
UR-RAGRank-By=Utility, LLM Backbone=llama-1B, Retrieval Method=BM252026.0131.0431.11
RePlugRank-By=Utility, LLM Backbone=llama-1B, Retrieval Method=BM252026.0130.1730.27
LURE-RAGRank-By=Utility, LLM Backbone=llama-1B, Retrieval Method=BM252026.0130.129.68
LURE-RAG (w/o topics)Rank-By=Utility, LLM Backbone=llama-1B, Retrieval Method=BM252026.0129.7329.47
k-shotRank-By=Relevance, LLM Backbone=llama-1B, Retrieval Method=BM252026.012628.41
0-shotRank-By=Relevance, LLM Backbone=phi-3.8B, Retrieval Method=BM252026.0122.1427.79
0-shotRank-By=Relevance, LLM Backbone=llama-1B, Retrieval Method=BM252026.0121.3722.58