Update index.html

docs/index.html

@@ -194,7 +194,7 @@ <h1 class="title is-2 publication-title">🪄 Lumos: Learning Agents with Unifie
     <div class="columns is-centered has-text-centered">
         <div class="content has-text-justified">
           We introduce 🪄 <strong>Lumos</strong>, Language Agents with Unified Data Formats, Modular Design, and Open-Source LLMs. <strong>Lumos</strong> unifies a suite of complex interactive tasks and achieves competitive performance with GPT-4/3.5-based and larger open-source agents. 
-          <br><br><span class="dnerf">Lumos</span> has following features: 
+          <br><br><strong>Lumos</strong> has following features: 
           <ul>
             <li><strong>🧩 A General Agent Modular Framework</strong>
               <ul>
@@ -210,7 +210,7 @@ <h1 class="title is-2 publication-title">🪄 Lumos: Learning Agents with Unifie
             </li>
             <li><strong>🚀 Competitive Performance</strong>
               <ul>
-              <li>🚀 <strong>Lumos</strong> is comparable or even beats GPT-4/3.5-based agents on web/complex QA tasks such as Mind2Web and HotpotQA, and larger open agents on math tasks.</li>
+              <li>🚀 <strong>Lumos</strong> is comparable or even beats GPT-series agents on web/complex QA tasks Mind2Web and HotpotQA, and larger open agents on math tasks.</li>
               <li>🚀 <strong>Lumos</strong> exceeds contemporaneous agents that have been fine-tuned with in-domain HotpotQA and Mind2Web annotations, such as FiReAct and AgentLM.</li>
               <li>🚀 <strong>Lumos</strong> outperforms open agent baseline formulations like chain-of-thoughts and integrated training.</li>
               <li>🚀 <strong>Lumos</strong> surpasses larger open LLM agents and domain-specific agents by a large margin on an unseen task, WebShop.</li>