update.

section6/section6.tex

@@ -449,6 +449,7 @@ The above way of generating skills often suffers from quality issues. First, a g
 \begin{figure*}[!t]
 \begin{figure*}[!t]
     \centering
     \centering
     \input{section6/Figures/skillrl_illustration.tex}
     \input{section6/Figures/skillrl_illustration.tex}
+    \vspace{-4mm}
     \caption{
     \caption{
         Illustration of SkillRL \citep{xia-etal:skillrl}. SkillRL maintains a pool of agentic trajectories and initially abstracts reusable skills from these trajectories. The extracted skills are then used to guide RL training. As the agent improves through RL training, it generates higher-quality trajectories, which are further used to refine the skill bank.
         Illustration of SkillRL \citep{xia-etal:skillrl}. SkillRL maintains a pool of agentic trajectories and initially abstracts reusable skills from these trajectories. The extracted skills are then used to guide RL training. As the agent improves through RL training, it generates higher-quality trajectories, which are further used to refine the skill bank.
     }
     }
@@ -472,9 +473,9 @@ Here we consider \textbf{SkillRL} as an example to illustrate how to optimize sk
 
 
 By repeating the above process, the agent can improve its skill library through accumulated experiences. Specifically, newly collected trajectories provide additional evidence for discovering new skills or refining existing ones, while the updated skill library further guides future RL training. This creates an iterative learning process in which the agent and its skills co-evolve over time. From this perspective, skill optimization provides a practical way to transform low-level interaction experiences into reusable capabilities, and has become an important approach for enabling agents to continuously learn from their own experiences \citep{wang-etal:reinforcement,fu-etal:self}. 
 By repeating the above process, the agent can improve its skill library through accumulated experiences. Specifically, newly collected trajectories provide additional evidence for discovering new skills or refining existing ones, while the updated skill library further guides future RL training. This creates an iterative learning process in which the agent and its skills co-evolve over time. From this perspective, skill optimization provides a practical way to transform low-level interaction experiences into reusable capabilities, and has become an important approach for enabling agents to continuously learn from their own experiences \citep{wang-etal:reinforcement,fu-etal:self}. 
 
 
-
+\vspace{-2mm}
 \subsubsection{Trajectory Refinement}
 \subsubsection{Trajectory Refinement}
-\vspace{-4mm}
+% \vspace{-1mm}
 
 
 Different from memory management and skill optimization, which focus on storing and abstracting experiences, trajectory refinement directly improves agent behaviors by revising generated trajectories. This idea is motivated by the self-refinement capability of LLMs. As discussed in Section~\ref{sec:tts}, reasoning-enhanced RL training enables LLMs to evaluate their intermediate reasoning processes and revise incorrect solutions. For example, when solving mathematical problems, an LLM can verify intermediate results after each reasoning step and adjust its solution trajectory based on the verification outcomes. 
 Different from memory management and skill optimization, which focus on storing and abstracting experiences, trajectory refinement directly improves agent behaviors by revising generated trajectories. This idea is motivated by the self-refinement capability of LLMs. As discussed in Section~\ref{sec:tts}, reasoning-enhanced RL training enables LLMs to evaluate their intermediate reasoning processes and revise incorrect solutions. For example, when solving mathematical problems, an LLM can verify intermediate results after each reasoning step and adjust its solution trajectory based on the verification outcomes.