update.

section4/Figures/figure-rlhf-vs-dpo.tex

-% !Mode:: "TeX:UTF-8"
 % !TEX encoding = UTF-8 Unicode
 
 \begin{center}

section5/section5.tex

@@ -127,3 +127,4 @@ An interesting issue arises with this design of iterative RL: why is RL aimed at
 
 Since the optimization objective of each phase is different, the design of iterative RL can also be analyzed and understood from the perspective of multi-objective optimization \citep{wang-etal:2024hybrid}. In the context of multi-objective optimization, iterative RL for LLMs can be likened to interactive methods where the solution process is iterative, and preferences are actively defined and refined by the decision-maker during the search for the most preferred solutions \citep{miettinen-etal:2008introduction,deb-etal:2016multi}. More specifically, in this scenario, RL can be seen as a decision-maker, iteratively refining and enhancing the different capabilities of the LLM across different phases.
 
+

section6/section6.tex

@@ -2,14 +2,26 @@
 
 \section{Reinforcement Learning for LLM-based Agents}
 
-What is the LLM-based agent?
 
-Agent Reinforcement Learning
 
-advanced Agent like openclaw
+\subsection{Why use Reinforcement Learning?}
+
+
+
+
+
+\subsection{Agentic Reinforcement Learning}
+
+
+
+
+\subsection{Advanced Agent Systems}
+
+
+
+
+
+
 
-Planning
 
 
-(1) use rl to gain better memory.
-(2) use rl to help agent to use skill.
\ No newline at end of file