The Why Behind the Action: Unveiling Internal Drivers via Agentic Attribution

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Qian, Chen, Wang, Peng, Liu, Dongrui, Yang, Junyao, Guo, Dadi, Tang, Ling, Mei, Jilin, Ren, Qihan, Shao, Shuai, Liu, Yong, Fu, Jie, Shao, Jing, Hu, Xia
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915777462927360
author Qian, Chen
Wang, Peng
Liu, Dongrui
Yang, Junyao
Guo, Dadi
Tang, Ling
Mei, Jilin
Ren, Qihan
Shao, Shuai
Liu, Yong
Fu, Jie
Shao, Jing
Hu, Xia
author_facet Qian, Chen
Wang, Peng
Liu, Dongrui
Yang, Junyao
Guo, Dadi
Tang, Ling
Mei, Jilin
Ren, Qihan
Shao, Shuai
Liu, Yong
Fu, Jie
Shao, Jing
Hu, Xia
contents Large Language Model (LLM)-based agents are widely used in real-world applications such as customer service, web navigation, and software engineering. As these systems become more autonomous and are deployed at scale, understanding why an agent takes a particular action becomes increasingly important for accountability and governance. However, existing research predominantly focuses on \textit{failure attribution} to localize explicit errors in unsuccessful trajectories, which is insufficient for explaining \textbf{the reason behind agent behaviors}. To bridge this gap, we propose a novel framework for \textbf{general agentic attribution}, designed to identify the internal factors driving agent actions regardless of the task outcome. Our framework operates hierarchically to manage the complexity of agent interactions. Specifically, at the \textit{component level}, we employ temporal likelihood dynamics to identify critical interaction steps; then at the \textit{sentence level}, we refine this localization using perturbation-based analysis to isolate the specific textual evidence. We validate our framework across a diverse suite of agentic scenarios, including standard tool use and subtle reliability risks like memory-induced bias. Experimental results demonstrate that the proposed framework reliably pinpoints pivotal historical events and sentences behind the agent behavior, offering a critical step toward safer and more accountable agentic systems. Codes are available at https://github.com/AI45Lab/AgentDoG.
format Preprint
id arxiv_https___arxiv_org_abs_2601_15075
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle The Why Behind the Action: Unveiling Internal Drivers via Agentic Attribution
Qian, Chen
Wang, Peng
Liu, Dongrui
Yang, Junyao
Guo, Dadi
Tang, Ling
Mei, Jilin
Ren, Qihan
Shao, Shuai
Liu, Yong
Fu, Jie
Shao, Jing
Hu, Xia
Artificial Intelligence
Computation and Language
Large Language Model (LLM)-based agents are widely used in real-world applications such as customer service, web navigation, and software engineering. As these systems become more autonomous and are deployed at scale, understanding why an agent takes a particular action becomes increasingly important for accountability and governance. However, existing research predominantly focuses on \textit{failure attribution} to localize explicit errors in unsuccessful trajectories, which is insufficient for explaining \textbf{the reason behind agent behaviors}. To bridge this gap, we propose a novel framework for \textbf{general agentic attribution}, designed to identify the internal factors driving agent actions regardless of the task outcome. Our framework operates hierarchically to manage the complexity of agent interactions. Specifically, at the \textit{component level}, we employ temporal likelihood dynamics to identify critical interaction steps; then at the \textit{sentence level}, we refine this localization using perturbation-based analysis to isolate the specific textual evidence. We validate our framework across a diverse suite of agentic scenarios, including standard tool use and subtle reliability risks like memory-induced bias. Experimental results demonstrate that the proposed framework reliably pinpoints pivotal historical events and sentences behind the agent behavior, offering a critical step toward safer and more accountable agentic systems. Codes are available at https://github.com/AI45Lab/AgentDoG.
title The Why Behind the Action: Unveiling Internal Drivers via Agentic Attribution
topic Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2601.15075