List your company

Question Answering on FRAMES out-domain (test)

31.31LasJD2PLAN-7B
9.480415.147720.81526.4823Jan 13, 2026

Evaluation results

MethodLinks
D2PLAN-7BBase LLM=Qwen2.5-7B-Instruct2026.0131.3118.08
D2PLAN-3BBase LLM=Qwen2.5-3B-Instruct2026.0125.9714.68
R1-SearcherBase LLM=Qwen2.5-7B-Instruct2026.0125.6114.32
ReSearchBase LLM=Qwen2.5-7B-Instruct2026.0124.2714.32
AutoRefineBase LLM=Qwen2.5-3B-Instruct2026.0123.7911.17
StepSearchBase LLM=Qwen2.5-7B-Instruct2026.0123.1813.23
Search-R1Base LLM=Qwen2.5-7B-Instruct2026.0119.7810.19
ZeroSearchBase LLM=Qwen2.5-7B-Instruct2026.0118.3310.07
Search-R1Base LLM=Qwen2.5-3B-Instruct2026.0118.24.85
StepSearchBase LLM=Qwen2.5-3B-Instruct2026.0113.836.55
ZeroSearchBase LLM=Qwen2.5-3B-Instruct2026.0110.324