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

• URL: http://arxiv.org/abs/2601.02314v1
• Date: Mon, 05 Jan 2026 18:05:29 GMT
• Title: Project Ariadne: A Structural Causal Framework for Auditing Faithfulness in LLM Agents
• Authors: Sourena Khanzadeh,
• Abstract summary: We introduce textbfProject Ariadne, a novel XAI framework to audit the causal integrity of agentic reasoning.<n>Unlike existing interpretability methods that rely on surface-level textual similarity, Project Ariadne performs textbfhard interventions ($do$-calculus) on intermediate reasoning nodes.<n>Our empirical evaluation of state-of-the-art models reveals a persistent textitFaithfulness Gap.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As Large Language Model (LLM) agents are increasingly tasked with high-stakes autonomous decision-making, the transparency of their reasoning processes has become a critical safety concern. While \textit{Chain-of-Thought} (CoT) prompting allows agents to generate human-readable reasoning traces, it remains unclear whether these traces are \textbf{faithful} generative drivers of the model's output or merely \textbf{post-hoc rationalizations}. We introduce \textbf{Project Ariadne}, a novel XAI framework that utilizes Structural Causal Models (SCMs) and counterfactual logic to audit the causal integrity of agentic reasoning. Unlike existing interpretability methods that rely on surface-level textual similarity, Project Ariadne performs \textbf{hard interventions} ($do$-calculus) on intermediate reasoning nodes -- systematically inverting logic, negating premises, and reversing factual claims -- to measure the \textbf{Causal Sensitivity} ($φ$) of the terminal answer. Our empirical evaluation of state-of-the-art models reveals a persistent \textit{Faithfulness Gap}. We define and detect a widespread failure mode termed \textbf{Causal Decoupling}, where agents exhibit a violation density ($ρ$) of up to $0.77$ in factual and scientific domains. In these instances, agents arrive at identical conclusions despite contradictory internal logic, proving that their reasoning traces function as "Reasoning Theater" while decision-making is governed by latent parametric priors. Our findings suggest that current agentic architectures are inherently prone to unfaithful explanation, and we propose the Ariadne Score as a new benchmark for aligning stated logic with model action.

Related papers

• TraceGuard: Process-Guided Firewall against Reasoning Backdoors in Large Language Models [19.148124494194317]
  We propose TraceGuard, a process-guided security framework that transforms small-scale models into robust reasoning firewalls.<n>Our approach treats the reasoning trace as an untrusted payload and establishes a defense-in-depth strategy.<n>We demonstrate robustness against adaptive adversaries in a grey-box setting, establishing TraceGuard as a viable, low-latency security primitive.
  arXiv  Detail & Related papers  (2026-03-02T22:19:13Z)
• CausalFlip: A Benchmark for LLM Causal Judgment Beyond Semantic Matching [50.65932158912512]
  We propose a new causal reasoning benchmark, CausalFlip, to encourage the development of new large language models.<n>CaulFlip consists of causal judgment questions built over event triples that could form different confounder, chain, and collider relations.<n>We evaluate LLMs under multiple training paradigms, including answer-only training, explicit Chain-of-Thought supervision, and a proposed internalized causal reasoning approach.
  arXiv  Detail & Related papers  (2026-02-23T18:06:15Z)
• Pushing the Boundaries of Natural Reasoning: Interleaved Bonus from Formal-Logic Verification [49.506412445511934]
  Large Language Models (LLMs) show remarkable capabilities, yet their next-token prediction creates logical inconsistencies and reward hacking.<n>We introduce a formal logic verification-guided framework that dynamically interleaves formal symbolic verification with the natural language generation process.<n>We operationalize this framework via a novel two-stage training pipeline that synergizes formal logic verification-guided supervised fine-tuning and policy optimization.
  arXiv  Detail & Related papers  (2026-01-30T07:01:25Z)
• Think Locally, Explain Globally: Graph-Guided LLM Investigations via Local Reasoning and Belief Propagation [5.191980417814362]
  LLM agents excel when environments are mostly static and the needed information fits in a model's context window.<n>ReAct-style agents are especially brittle in this regime.<n>We propose EoG, a framework in which an LLM performs bounded local evidence mining and labeling (cause vs symptom) while a deterministic controller manages, state, and belief propagation to compute a minimal explanatory frontier.
  arXiv  Detail & Related papers  (2026-01-25T17:27:19Z)
• ReasonAny: Incorporating Reasoning Capability to Any Model via Simple and Effective Model Merging [46.06799235021118]
  We propose a novel merging framework that resolves the reasoning-domain performance collapse through Contrastive Gradient Identification.<n>Experiments across safety, biomedicine, and finance domains show that ReasonAny effectively synthesizes "Reasoning + X" capabilities.
  arXiv  Detail & Related papers  (2026-01-09T06:19:00Z)
• Adversarial Yet Cooperative: Multi-Perspective Reasoning in Retrieved-Augmented Language Models [72.4149653187766]
  We propose a Reasoner-Verifier framework named Adrialversa Reasoning RAG (ARR)<n>The Reasoner and Verifier engage in reasoning on retrieved evidence and critiquing each other's logic while being guided by process-aware advantage.<n> Experiments on multiple benchmarks demonstrate the effectiveness of our method.
  arXiv  Detail & Related papers  (2026-01-08T06:57:03Z)
• The Seeds of Scheming: Weakness of Will in the Building Blocks of Agentic Systems [0.0]
  Large language models display a peculiar form of inconsistency: they "know" the correct answer but fail to act on it.<n>In human philosophy, this tension between global judgment and local impulse is called akrasia, or weakness of will.<n>We propose akrasia as a foundational concept for analyzing inconsistency and goal drift in agentic AI systems.
  arXiv  Detail & Related papers  (2025-12-05T05:57:40Z)
• ARCHE: A Novel Task to Evaluate LLMs on Latent Reasoning Chain Extraction [70.53044880892196]
  We introduce a novel task named Latent Reasoning Chain Extraction (ARCHE), in which models must decompose complex reasoning arguments into combinations of standard reasoning paradigms in the form of a Reasoning Logic Tree (RLT)<n>To facilitate this task, we release ARCHE Bench, a new benchmark derived from 70 Nature Communications articles, including more than 1,900 references and 38,000 viewpoints.<n> Evaluations on 10 leading LLMs on ARCHE Bench reveal that models exhibit a trade-off between REA and EC, and none are yet able to extract a complete and standard reasoning chain.
  arXiv  Detail & Related papers  (2025-11-16T07:37:09Z)
• Hallucination Detection via Internal States and Structured Reasoning Consistency in Large Language Models [7.18947815679122]
  Internal State Probing and Chain-of-Thought Verification are used to detect hallucinations in large language models.<n>We develop a unified framework that bridges the gap between the two methods.<n>Our framework consistently and significantly outperforms strong baselines.
  arXiv  Detail & Related papers  (2025-10-13T15:31:21Z)
• Implicit Reasoning in Large Language Models: A Comprehensive Survey [67.53966514728383]
  Large Language Models (LLMs) have demonstrated strong generalization across a wide range of tasks.<n>Recent studies have shifted attention from explicit chain-of-thought prompting toward implicit reasoning.<n>This survey introduces a taxonomy centered on execution paradigms, shifting the focus from representational forms to computational strategies.
  arXiv  Detail & Related papers  (2025-09-02T14:16:02Z)
• Is Reasoning All You Need? Probing Bias in the Age of Reasoning Language Models [0.0]
  Reasoning Language Models (RLMs) have gained traction for their ability to perform complex, multi-step reasoning tasks.<n>While these capabilities promise improved reliability, their impact on robustness to social biases remains unclear.<n>We leverage the CLEAR-Bias benchmark to investigate the adversarial robustness of RLMs to bias elicitation.
  arXiv  Detail & Related papers  (2025-07-03T17:01:53Z)
• A Comment On "The Illusion of Thinking": Reframing the Reasoning Cliff as an Agentic Gap [0.39073867995073247]
  We argue that the observed failure is not evidence of a fundamental cognitive boundary, but rather a predictable outcome of system-level constraints.<n>A model, initially declaring a puzzle impossible when confined to text-only generation, now employs agentic tools to not only solve it but also master variations of complexity far beyond the reasoning cliff it previously failed to surmount.
  arXiv  Detail & Related papers  (2025-06-23T17:14:21Z)
• Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimization [58.390885294401066]
  Retrieval-augmented generation (RAG) has become a widely adopted paradigm for enabling knowledge-grounded large language models (LLMs)<n>RAG pipelines often fail to ensure that model reasoning remains consistent with the evidence retrieved, leading to factual inconsistencies or unsupported conclusions.<n>We propose AlignRAG, a novel iterative framework grounded in Critique-Driven Alignment (CDA)<n>We introduce AlignRAG-auto, an autonomous variant that dynamically terminates refinement, removing the need to pre-specify the number of critique iterations.
  arXiv  Detail & Related papers  (2025-04-21T04:56:47Z)
• Logical Satisfiability of Counterfactuals for Faithful Explanations in NLI [60.142926537264714]
  We introduce the methodology of Faithfulness-through-Counterfactuals. It generates a counterfactual hypothesis based on the logical predicates expressed in the explanation. It then evaluates if the model's prediction on the counterfactual is consistent with that expressed logic.
  arXiv  Detail & Related papers  (2022-05-25T03:40:59Z)
• Logically Consistent Adversarial Attacks for Soft Theorem Provers [110.17147570572939]
  We propose a generative adversarial framework for probing and improving language models' reasoning capabilities. Our framework successfully generates adversarial attacks and identifies global weaknesses. In addition to effective probing, we show that training on the generated samples improves the target model's performance.
  arXiv  Detail & Related papers  (2022-04-29T19:10:12Z)
• Measuring Association Between Labels and Free-Text Rationales [60.58672852655487]
  In interpretable NLP, we require faithful rationales that reflect the model's decision-making process for an explained instance. We demonstrate that pipelines, existing models for faithful extractive rationalization on information-extraction style tasks, do not extend as reliably to "reasoning" tasks requiring free-text rationales. We turn to models that jointly predict and rationalize, a class of widely used high-performance models for free-text rationalization whose faithfulness is not yet established.
  arXiv  Detail & Related papers  (2020-10-24T03:40:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.