velocitatem/PHANTOM
1
0
Fork 0
mirror of https://github.com/velocitatem/PHANTOM.git synced 2026-05-31 16:43:36 +00:00
Code Issues Packages Projects Releases Wiki Activity

details on formulation and defintion of agent and its loop

Browse Source
This commit is contained in:
Daniel Rosel
2025-12-12 15:43:45 +01:00
parent 2ccf9bd444
commit 10d472353f
2 changed files with 35 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
paper/src/chapters/01-intro.tex
View File

@@ -21,9 +21,37 @@ The key stakeholders of the threat presented by the shift towards a growing shar
The industry has already seen legal action coming from large cases like Amazon against Perplexity \cite{AmazonvsPerplexity} which comes from the nature of the difficulty of identifying traffic coming from hybrid systems like the Commet browser, which is a system that this paper does explore in order to better understand the nature of how the interaction data looks like and what it means for dynamic pricing or recommendation systems down the line. This observed impact indicates a need for prevention of seconddary negative effects on the ``legacy'' systems which power modern revenue sources for many companies. Dynamic pricing algorithms rely on directly trnslating demand features $q$ to new price assignments $\hat{p}$ across a catalogue of products of size $N$. The industry has already seen legal action coming from large cases like Amazon against Perplexity \cite{AmazonvsPerplexity} which comes from the nature of the difficulty of identifying traffic coming from hybrid systems like the Commet browser, which is a system that this paper does explore in order to better understand the nature of how the interaction data looks like and what it means for dynamic pricing or recommendation systems down the line. This observed impact indicates a need for prevention of seconddary negative effects on the ``legacy'' systems which power modern revenue sources for many companies. Dynamic pricing algorithms rely on directly trnslating demand features $q$ to new price assignments $\hat{p}$ across a catalogue of products of size $N$.
\subsection{Solution Space Overview} \subsection{Solution Space Overview}
The dynamic pricing systems, as presented in \cite{Mueller2019} often deal with sparse low-rank data of demand signals, which in combination with contamination from agents makes for a very complex set of interactions which have an impact on the pricing. To further complicate the problem in certain comercial settings, such as the one presented in \cite{Amjad2017} must addreses the true demand of products under censored observations. This sets us up with a good formulation for handling demand in our case of multiple kinds of comercial mediators $\hat{q} \gets q_A + q_H$ where $A$ represents the distribution of demand generated by agentic mediators and $H$ represents that of true human demand. The dynamic pricing systems, as presented in \cite{Mueller2019} often deal with sparse low-rank data of demand signals, which in combination with contamination from agents makes for a very complex set of interactions which have an impact on the pricing. To further complicate the problem in certain comercial settings, such as the one presented in \cite{Amjad2017} must addreses the true demand of products under censored observations. This sets us up with a good formulation for handling demand in our case of multiple kinds of comercial mediators $\hat{q} \gets q_A + q_H$ where $q_A$ represents the distribution of demand generated by agentic mediators and $q_H$ represents that of true human demand.
The previously described goal of We formally define interaction data as coming from some actor which either either be an agent ($A$) or human ($H$). An agent for pruposes of our research, is an algorithmic loop with the ability to access a web platform, perform actions on that platform such as (click, scroll and fill input field), the loop finishes in the moment when the judgement of provided definition of done by the internal large language model is satisfied. A detailed breakdown can be found in \cref{algagent-loop}.
Different approaches and perspectives, here also add a preview of what will be developed and explored in the lit review. \begin{algorithm}[t]
\DontPrintSemicolon
\SetKwInOut{Input}{Input}
\SetKwInOut{Output}{Output}
\Input{Goal $G$, Platform URL $u$, LLM $\mathcal{M}$}
\Output{Task completion result $r$}
Initialize browser instance $\mathcal{B}$ with connection to $u$\;
Construct prompt $\pi \gets \textsc{BuildPrompt}(G, u)$\;
$\text{done} \gets \text{False}$\;
\While{$\neg \text{done}$}{
Observe current page state $s_t$ from $\mathcal{B}$\;
Query $\mathcal{M}$ with $(\pi, s_t)$ to determine next action $a_t \in \{\text{click}, \text{scroll}, \text{fill}, \text{navigate}\}$\;
Execute $a_t$ on $\mathcal{B}$ to transition to state $s_{t+1}$\;
$\text{done} \gets \mathcal{M}.\textsc{JudgeCompletion}(G, s_{t+1})$\;
}
Extract final result $r$ from terminal state\;
\Return{$r$}\;
\caption{AI Agent's Interaction Loop}
\label{algagent-loop}
\end{algorithm}
The previously described goal of separability allows us to formulate a task which entails taking raw interaction data for either actor and creating a composite demand estimtate $\hat{q}$.

4
paper/src/preamble.tex
View File

@@ -8,6 +8,10 @@
\usepackage{listings} \usepackage{listings}
\usepackage{xcolor} \usepackage{xcolor}
\usepackage[ruled,vlined]{algorithm2e} \usepackage[ruled,vlined]{algorithm2e}
\usepackage{cleveref}
% Configure cleveref for algorithm2e
\crefname{algocf}{Algorithm}{Algorithms}
\usetikzlibrary{positioning, shapes, arrows.meta, fit, backgrounds} \usetikzlibrary{positioning, shapes, arrows.meta, fit, backgrounds}
\lstset{ \lstset{