Cover Image

Project Ariadne: A Structural Causal Framework for Auditing Faithfulness in LLM Agents

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Khanzadeh, Sourena
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

AgentMesh: A Cooperative Multi-Agent Generative AI Framework for Software Development Automation
by: Khanzadeh, Sourena
Published: (2025)

Breadth-First Search vs. Restarting Random Walks for Escaping Uninformed Heuristic Regions
by: Platnick, Daniel, et al.
Published: (2025)

GANsemble for Small and Imbalanced Data Sets: A Baseline for Synthetic Microplastics Data
by: Platnick, Daniel, et al.
Published: (2024)

Breaking the Chain: A Causal Analysis of LLM Faithfulness to Intermediate Structures
by: Somov, Oleg, et al.
Published: (2026)

Verify Before You Commit: Towards Faithful Reasoning in LLM Agents via Self-Auditing
by: Yuan, Wenhao, et al.
Published: (2026)

AriadneMem: Threading the Maze of Lifelong Memory for LLM Agents
by: Zhu, Wenhui, et al.
Published: (2026)

MemAudit: Post-hoc Auditing of Poisoned Agent Memory via Causal Attribution and Structural Anomaly Detection
by: Tan, Zhewen, et al.
Published: (2026)

C2-Faith: Benchmarking LLM Judges for Causal and Coverage Faithfulness in Chain-of-Thought Reasoning
by: Mittal, Avni, et al.
Published: (2026)

Counterfactual Trace Auditing of LLM Agent Skills
by: Zhou, Xiaolin, et al.
Published: (2026)

Ariadne and Theseus: Exploration and Rendezvous with Two Mobile Agents in an Unknown Graph
by: Cosson, Romain
Published: (2024)

MedSkillAudit: A Domain-Specific Audit Framework for Medical Research Agent Skills
by: Hou, Yingyong, et al.
Published: (2026)

TradeTrap: Are LLM-based Trading Agents Truly Reliable and Faithful?
by: Yan, Lewen, et al.
Published: (2025)

SOM: Structured Opponent Modeling for LLM-based Agents via Structural Causal Model
by: Cao, Shiyue, et al.
Published: (2026)

Towards Security-Auditable LLM Agents: A Unified Graph Representation
by: Li, Chaofan, et al.
Published: (2026)

Agent Audit: A Security Analysis System for LLM Agent Applications
by: Zhang, Haiyue, et al.
Published: (2026)

Auditable Agents
by: Nian, Yi, et al.
Published: (2026)

Doing What They Say, Not What They Reason: Locating the Faithfulness Gap in LLM Agents
by: Wang, Yufeng
Published: (2026)

Towards CausalGPT: A Multi-Agent Approach for Faithful Knowledge Reasoning via Promoting Causal Consistency in LLMs
by: Tang, Ziyi, et al.
Published: (2023)

Auditing Multi-Agent LLM Reasoning Trees Outperforms Majority Vote and LLM-as-Judge
by: Yang, Wei, et al.
Published: (2026)

IV Co-Scientist: Multi-Agent LLM Framework for Causal Instrumental Variable Discovery
by: Sheth, Ivaxi, et al.
Published: (2026)

Orientability of Causal Relations in Time Series using Summary Causal Graphs and Faithful Distributions
by: Loranchet, Timothée, et al.
Published: (2025)

IMMACULATE: A Practical LLM Auditing Framework via Verifiable Computation
by: Guo, Yanpei, et al.
Published: (2026)

AuditLLM: A Tool for Auditing Large Language Models Using Multiprobe Approach
by: Amirizaniani, Maryam, et al.
Published: (2024)

Beyond Jailbreaking: Auditing Contextual Privacy in LLM Agents
by: Das, Saswat, et al.
Published: (2025)

A Causal Lens for Evaluating Faithfulness Metrics
by: Zaman, Kerem, et al.
Published: (2025)

Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills
by: Lv, Lijia, et al.
Published: (2026)

An Analysis of Decoding Methods for LLM-based Agents for Faithful Multi-Hop Question Answering
by: Murphy, Alexander, et al.
Published: (2025)

Faithful Mobile GUI Agents with Guided Advantage Estimator
by: Hu, Haowen, et al.
Published: (2026)

Routine: A Structural Planning Framework for LLM Agent System in Enterprise
by: Zeng, Guancheng, et al.
Published: (2025)

Don't Start What You Can't Finish: A Counterfactual Audit of Support-State Triage in LLM Agents
by: Unlu, Eren
Published: (2026)

CausalPlan: Empowering Efficient LLM Multi-Agent Collaboration Through Causality-Driven Planning
by: Nguyen, Minh Hoang, et al.
Published: (2025)

CausalFlow: Causal Attribution and Counterfactual Repair for LLM Agent Failures
by: Bonagiri, Akash, et al.
Published: (2026)

FRIT: Using Causal Importance to Improve Chain-of-Thought Faithfulness
by: Swaroop, Anand, et al.
Published: (2025)

On the Need and Applicability of Causality for Fairness: A Unified Framework for AI Auditing and Legal Analysis
by: Binkyte, Ruta, et al.
Published: (2022)

Audit-LLM: Multi-Agent Collaboration for Log-based Insider Threat Detection
by: Song, Chengyu, et al.
Published: (2024)

A Concurrent Modular Agent: Framework for Autonomous LLM Agents
by: Maruyama, Norihiro, et al.
Published: (2025)

From Agent Loops to Structured Graphs:A Scheduler-Theoretic Framework for LLM Agent Execution
by: Wei, Hu
Published: (2026)

Separating Diagnosis from Control: Auditable Policy Adaptation in Agent-Based Simulations with LLM-Based Diagnostics
by: Zhong, Shaoxin, et al.
Published: (2026)

DeepFaith: A Domain-Free and Model-Agnostic Unified Framework for Highly Faithful Explanations
by: Guo, Yuhan, et al.
Published: (2025)

Faithfulness Serum: Mitigating the Faithfulness Gap in Textual Explanations of LLM Decisions via Attribution Guidance
by: Alon, Bar, et al.
Published: (2026)