List your company

Question Answering on HotpotQA (EM, ASR)

76Exact Match (EM)Ignore
17.7632.884863.12Jul 1, 2026

Evaluation results

MethodLinks
IgnoreFramework=WebThinker, LLM Backbone=QwQ-32B2026.07760
TopicFramework=WebThinker, LLM Backbone=QwQ-32B2026.07760
Clean (No Attack)Framework=ReAct, LLM Backbone=Llama-3.3-70B-Inst2026.0775—
Fake CompletionFramework=WebThinker, LLM Backbone=QwQ-32B2026.07751
CombinedFramework=WebThinker, LLM Backbone=QwQ-32B2026.07750
Clean (No Attack)Framework=WebThinker, LLM Backbone=QwQ-32B2026.0771—
Fake CompletionFramework=ReAct, LLM Backbone=Llama-3.3-70B-Inst2026.07700
NaiveFramework=WebThinker, LLM Backbone=QwQ-32B2026.07701
PARADOXFramework=WebThinker, LLM Backbone=QwQ-32B2026.07701
IgnoreFramework=WebThinker, LLM Backbone=DeepSeek-32B2026.07690
CombinedFramework=WebThinker, LLM Backbone=DeepSeek-32B2026.07690
Clean (No Attack)Framework=ReAct, LLM Backbone=Qwen2.5-32B-Inst2026.0768—
Clean (No Attack)Framework=WebThinker, LLM Backbone=DeepSeek-32B2026.0768—
NaiveFramework=ReAct, LLM Backbone=Llama-3.3-70B-Inst2026.07675
TopicFramework=WebThinker, LLM Backbone=DeepSeek-32B2026.07670
NaiveFramework=WebThinker, LLM Backbone=DeepSeek-32B2026.07660
Fake CompletionFramework=WebThinker, LLM Backbone=DeepSeek-32B2026.07660
PARADOXFramework=ReAct, LLM Backbone=Llama-3.3-70B-Inst2026.07645
PoisonedRAGFramework=WebThinker, LLM Backbone=QwQ-32B2026.07644
CombinedFramework=ReAct, LLM Backbone=Llama-3.3-70B-Inst2026.07623
PARADOXFramework=ReAct, LLM Backbone=Qwen2.5-32B-Inst2026.07577
PoisonedRAGFramework=WebThinker, LLM Backbone=DeepSeek-32B2026.07579
NaiveFramework=ReAct, LLM Backbone=Qwen2.5-32B-Inst2026.075611
PoisonedRAGFramework=ReAct, LLM Backbone=Llama-3.3-70B-Inst2026.07568
PARADOXFramework=WebThinker, LLM Backbone=DeepSeek-32B2026.07507
IgnoreFramework=ReAct, LLM Backbone=Llama-3.3-70B-Inst2026.074816
IgnoreFramework=ReAct, LLM Backbone=Qwen2.5-32B-Inst2026.074718
KidnapRAGFramework=WebThinker, LLM Backbone=DeepSeek-32B2026.074623
PoisonedRAGFramework=ReAct, LLM Backbone=Qwen2.5-32B-Inst2026.07448
TopicFramework=ReAct, LLM Backbone=Llama-3.3-70B-Inst2026.07412
KidnapRAGFramework=WebThinker, LLM Backbone=QwQ-32B2026.073551
CombinedFramework=ReAct, LLM Backbone=Qwen2.5-32B-Inst2026.073430
Fake CompletionFramework=ReAct, LLM Backbone=Qwen2.5-32B-Inst2026.073335
TopicFramework=ReAct, LLM Backbone=Qwen2.5-32B-Inst2026.072221
KidnapRAGFramework=ReAct, LLM Backbone=Qwen2.5-32B-Inst2026.072039
KidnapRAGFramework=ReAct, LLM Backbone=Llama-3.3-70B-Inst2026.072064