List your company

Web Navigation on WebWalkerQA

35Internalized InferenceExperience Internalization
7.4414.59521.7528.905Jun 3, 2026

Evaluation results

MethodLinks
Experience InternalizationBase Model=Qwen3-4B-Instruct-2507, Experience Source=DeepSeek-generated, Injection Pattern=Step-wise injection, Distillation Regime=On-policy distillation, Iteration=iter 12026.0635—
Experience InternalizationBase Model=Qwen3-8B-Instruct, Experience Source=DeepSeek-generated, Injection Pattern=Step-wise injection, Distillation Regime=Off-policy distillation, Iteration=iter 32026.0634.6—
Experience InternalizationBase Model=Qwen3-8B-Instruct, Experience Source=DeepSeek-generated, Injection Pattern=Step-wise injection, Distillation Regime=On-policy distillation, Iteration=iter 12026.0633.9—
Experience InternalizationBase Model=Qwen3-4B-Instruct-2507, Experience Source=DeepSeek-generated, Injection Pattern=Step-wise injection, Distillation Regime=Off-policy distillation, Iteration=iter 32026.0633.1—
Experience InternalizationBase Model=Qwen3-8B-Instruct, Experience Source=DeepSeek-generated, Injection Pattern=Step-wise injection, Distillation Regime=Off-policy distillation, Iteration=iter 12026.0632.9—
Experience InternalizationBase Model=Qwen3-4B-Instruct-2507, Experience Source=DeepSeek-generated, Injection Pattern=Step-wise injection, Distillation Regime=On-policy distillation, Iteration=iter 22026.0632.4—
Experience InternalizationBase Model=Qwen3-8B-Instruct, Experience Source=DeepSeek-generated, Injection Pattern=Step-wise injection, Distillation Regime=On-policy distillation, Iteration=iter 32026.0632.2—
Experience InternalizationBase Model=Qwen3-8B-Instruct, Experience Source=DeepSeek-generated, Injection Pattern=Step-wise injection, Distillation Regime=Off-policy distillation, Iteration=iter 22026.0631.8—
Experience InternalizationBase Model=Qwen3-4B-Instruct-2507, Experience Source=DeepSeek-generated, Injection Pattern=Step-wise injection, Distillation Regime=On-policy distillation, Iteration=iter 32026.0631.5—
Experience InternalizationBase Model=Qwen3-8B-Instruct, Experience Source=DeepSeek-generated, Injection Pattern=Step-wise injection, Distillation Regime=On-policy distillation, Iteration=iter 22026.0631.5—
Experience InternalizationBase Model=Qwen3-4B-Instruct-2507, Experience Source=DeepSeek-generated, Injection Pattern=Global injection, Distillation Regime=Off-policy distillation, Iteration=iter 22026.063114.1
Experience InternalizationBase Model=Qwen3-4B-Instruct-2507, Experience Source=DeepSeek-generated, Injection Pattern=Step-wise injection, Distillation Regime=Off-policy distillation, Iteration=iter 22026.0630.734.6
Experience InternalizationBase Model=Qwen3-4B-Instruct-2507, Experience Source=DeepSeek-generated, Injection Pattern=Step-wise injection, Distillation Regime=Off-policy distillation, Iteration=iter 12026.0630.631.5
Experience InternalizationBase Model=Qwen3-4B-Instruct-2507, Experience Source=Qwen-generated, Injection Pattern=Step-wise injection, Distillation Regime=Off-policy distillation, Iteration=iter 32026.0630—
Experience InternalizationBase Model=Qwen3-4B-Instruct-2507, Experience Source=Qwen-generated, Injection Pattern=Step-wise injection, Distillation Regime=Off-policy distillation, Iteration=iter 12026.062932.1
Experience InternalizationBase Model=Qwen3-4B-Instruct-2507, Experience Source=DeepSeek-generated, Injection Pattern=Global injection, Distillation Regime=On-policy distillation, Iteration=iter 12026.0629—
Experience InternalizationBase Model=Qwen3-4B-Instruct-2507, Experience Source=Qwen-generated, Injection Pattern=Step-wise injection, Distillation Regime=Off-policy distillation, Iteration=iter 22026.0628.531.3
Experience InternalizationBase Model=Qwen3-4B-Instruct-2507, Experience Source=DeepSeek-generated, Injection Pattern=Global injection, Distillation Regime=Off-policy distillation, Iteration=iter 12026.0625.928.1
Experience InternalizationBase Model=Qwen3-4B-Instruct-2507, Experience Source=DeepSeek-generated, Injection Pattern=Global injection, Distillation Regime=On-policy distillation, Iteration=iter 22026.0622.5—
Qwen3-8B-InstructExperience Status=w/o experience2026.0621.8—
Experience InternalizationBase Model=Qwen3-4B-Instruct-2507, Experience Source=Qwen-generated, Injection Pattern=Global injection, Distillation Regime=Off-policy distillation, Iteration=iter 12026.062119.9
Experience InternalizationBase Model=Qwen3-4B-Instruct-2507, Experience Source=DeepSeek-generated, Injection Pattern=Global injection, Distillation Regime=On-policy distillation, Iteration=iter 32026.0619.9—
Experience InternalizationBase Model=Qwen3-4B-Instruct-2507, Experience Source=Qwen-generated, Injection Pattern=Global injection, Distillation Regime=Off-policy distillation, Iteration=iter 22026.0618.79
Qwen3-4B-Instruct-2507Experience Status=w/o experience2026.0616.6—
Experience InternalizationBase Model=Qwen3-4B-Instruct-2507, Experience Source=DeepSeek-generated, Injection Pattern=Global injection, Distillation Regime=Off-policy distillation, Iteration=iter 32026.0612.8—
Experience InternalizationBase Model=Qwen3-4B-Instruct-2507, Experience Source=Qwen-generated, Injection Pattern=Global injection, Distillation Regime=Off-policy distillation, Iteration=iter 32026.068.5—
Qwen3-4B-Instruct-2507Experience Source=Qwen-generated experience2026.06—18.5
Qwen3-4B-Instruct-2507Experience Source=DeepSeek-generated experience2026.06—25.9
Qwen3-8B-InstructExperience Source=DeepSeek-generated experience2026.06—27.79