Update README.md

README.md

@@ -32,7 +32,7 @@ It introduces **Prospective Bounded Sequence Optimization (PBSO)** — a novel r
   A reinforcement learning algorithm with position-specific rewards for both task accuracy and critique quality, ensuring stable and interpretable optimization.
 
 - 📈 **State-of-the-art Semantic Consistency**  
-  ReForm achieves an **average +17.2pp improvement** over the strongest baseline across four formalization benchmarks (miniF2F, ProofNet, Putnam, and AIME 2025).
+  ReForm achieves an **average +22.6pp improvement** over the strongest baseline across four formalization benchmarks (miniF2F, ProofNet, Putnam, and AIME 2025).
 
 ---
 
@@ -53,11 +53,10 @@ model_name = "GuoxinChen/ReForm-8B"  # or "GuoxinChen/ReForm-32B"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="auto", device_map="auto")
 
-prompt = "Think step by step to translate the mathematical problem in natural language to Lean 4, and verify the consistency.
-Let $a_1, a_2,\\cdots, a_n$ be real constants, $x$ a real variable, and $f(x)=\\cos(a_1+x)+\\frac{1}{2}\\cos(a_2+x)+\\frac{1}{4}\\cos(a_3+x)+\\cdots+\\frac{1}{2^{n-1}}\\cos(a_n+x).$ Given that $f(x_1)=f(x_2)=0,$ prove that $x_2-x_1=m\\pi$ for some integer $m.$"
+prompt = "Think step by step to translate the mathematical problem in natural language to Lean 4, and verify the consistency.\nLet $a_1, a_2,\\cdots, a_n$ be real constants, $x$ a real variable, and $f(x)=\\cos(a_1+x)+\\frac{1}{2}\\cos(a_2+x)+\\frac{1}{4}\\cos(a_3+x)+\\cdots+\\frac{1}{2^{n-1}}\\cos(a_n+x).$ Given that $f(x_1)=f(x_2)=0,$ prove that $x_2-x_1=m\\pi$ for some integer $m.$"
 
 inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
-outputs = model.generate(**inputs, max_new_tokens=512)
+outputs = model.generate(**inputs, max_new_tokens=32768)
 print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 ```