Right for the Wrong Reasons: Epistemic Regret Minimization for Causal Rung Collapse in LLMs

• URL: http://arxiv.org/abs/2602.11675v1
• Date: Thu, 12 Feb 2026 07:48:21 GMT
• Title: Right for the Wrong Reasons: Epistemic Regret Minimization for Causal Rung Collapse in LLMs
• Abstract summary: We show that machine learning systems that are "right for the wrong reasons" achieve high performance through shortcuts that collapse under distributional shift.<n>When outcome-based learning reinforces correct answers, the agent becomes entrenched in flawed reasoning.<n>We propose Epistemic Regret Minimization (ERM), a belief revision objective that penalizes errors in causal reasoning independently of task success.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Machine learning systems that are "right for the wrong reasons" achieve high performance through shortcuts that collapse under distributional shift. We show this pathology has a precise causal origin: autoregressive training provides no gradient signal to distinguish association P(Y|X) from intervention P(Y|do(X)), a failure we formalize as Rung Collapse. When outcome-based learning reinforces correct answers obtained through incorrect causal models, the agent becomes entrenched in flawed reasoning, a phenomenon we term Aleatoric Entrenchment. We propose Epistemic Regret Minimization (ERM), a belief revision objective that penalizes errors in causal reasoning independently of task success, and embed it within a three-layer architecture with three contributions grounded in knowledge representation: (1) a Physical Grounding Theorem proving that actions satisfying actuator independence implement valid do-operations, bridging action languages and do-calculus; (2) ERM as a causal belief revision operator satisfying AGM postulates, preventing entrenchment even when the agent succeeds for the wrong reasons; and (3) a failure mode taxonomy that classifies recurring reasoning errors and injects domain-independent guards, enabling cross-domain transfer. We prove asymptotic recovery of the true interventional distribution with finite-sample bounds. Experiments on 1,360 causal trap scenarios across six frontier LLMs reveal that Rung Collapse persists even in reasoning-enhanced models (3.7% for GPT-5.2), that steerability exhibits inverse scaling where advanced models resist generic correction, and that targeted ERM feedback recovers 53-59% of entrenched errors where outcome-level feedback fails.

Related papers

• Interventional Causal Circuits for Safe Robot Action Testing and Failure Recovery [4.492262382019958]
  Formal testing of motion parameters is computationally expensive, and the cost scales poorly with the dimensionality of the action space.<n>We propose a closed-loop framework that couples a Joint Probability Tree (JPT) with a Causal Circuit derived from a Marginal-Deterministic Variable Tree.<n>The framework validates tractability of all interventional queries before the robot begins operating, and out-of-support candidates are detected and excluded from correction automatically.
  arXiv  Detail & Related papers  (2026-07-16T10:41:20Z)
• Purified OPSD: On-Policy Self-Distillation Without Losing How to Think [52.879387744920415]
  We find that on-policy self-distillation (OPSD) consistently fails on long chain-of-thought (long-CoT) reasoning models.<n>We propose a two-step solution: first, we construct a reference-only teacher to isolate the non-transferable component of the supervision signal.<n>Second, we use pointwise mutual information (PMI) as the mechanism to transform this residual into a well-formed PMI target distribution.
  arXiv  Detail & Related papers  (2026-07-02T14:33:07Z)
• One Reflection Is Not Enough: Self-Correcting Autonomous Research via Multi-Hypothesis Failure Attribution [85.65263343588026]
  We propose SAGE, a Self-correcting, Autonomous, Grounded Experimenter.<n>Its core mechanism, Multi-Hypothesis Failure Attribution (MHFA), treats recovery as a structured causal diagnosis.<n>On a 12-topic, 5-domain benchmark, SAGE increases metrics-bearing outputs from 42% to 92% over a baseline reflection.
  arXiv  Detail & Related papers  (2026-06-30T10:54:16Z)
• R-APS: Compositional Reasoning and In-Context Meta-Learning for Constrained Design via Reflective Adversarial Pareto Search [18.8323743697237]
  Large language models (LLMs) are fluent on open-ended tasks, yet in agentic settings, fluency does not ensure reliable delivery.<n>We trace this gap to three coupled structural failures: errors propagate without localization, worst-case perturbations go unevaluated, and accumulated knowledge is never invalidated.<n>We argue these share a root cause: abductive, counterfactual, meta-inductive, corrective, and inductive reasoning pull a shared context in incompatible directions.
  arXiv  Detail & Related papers  (2026-06-03T12:45:39Z)
• The Paradox of Outcome Optimization: A Causal Information-Theoretic Bound on Reasoning Shortcuts in LLMs [5.802098323678549]
  Large Language Models (LLMs) aligned via outcome-based Reinforcement Learning (RL) frequently exhibit a critical failure mode.<n>We establish a theoretical framework bridging Structural Causal Models (SCM) and the Information Bottleneck (IB) principle to explain this paradox.
  arXiv  Detail & Related papers  (2026-05-30T11:06:13Z)
• LC-ERD: Mining Latent Logic for Self-Evolving Reasoning via Consistency-Regulated Reward Decomposition [55.572260012037084]
  We introduce LC-ERD (Logic-Consistent Endogenous Reward Decomposition), a framework framing self-alignment as latent structure mining.<n>We derive a Variational Logic Potential by aggregating consensus from the model's Latent Logic Expertise.<n>Experiments show LC-ERD delivers a robust self-evolution path, uncovering trade-offs between logic consistency and accuracy.
  arXiv  Detail & Related papers  (2026-05-19T07:27:50Z)
• Perception Without Engagement: Dissecting the Causal Discovery Deficit in LMMs [68.58207076756237]
  We introduce ProCauEval, a perturbation-based evaluation protocol that shifts from outcome assessment to mechanism diagnosis.<n>We find that models faithfully perceive video content yet systematically underexploit it during causal reasoning.<n>We propose Anti-Distillation Policy Optimization (ADPO), a reinforcement learning framework built on negative teacher alignment.
  arXiv  Detail & Related papers  (2026-05-10T08:48:58Z)
• CausalDisenSeg: A Causality-Guided Disentanglement Framework with Counterfactual Reasoning for Robust Brain Tumor Segmentation Under Missing Modalities [14.27898790157402]
  In clinical practice, the robustness of deep learning models for multimodal brain tumor segmentation is severely compromised by incomplete MRI data.<n>This vulnerability stems primarily from modality bias, where models exploit spurious correlations as shortcuts rather than learning true anatomical structures.<n>We propose CausalDisenSeg, a novel Structural Causal Model (SCM)-grounded framework that achieves robust segmentation via causality-guided disentanglement and counterfactual reasoning.
  arXiv  Detail & Related papers  (2026-04-15T02:20:09Z)
• MAS-FIRE: Fault Injection and Reliability Evaluation for LLM-Based Multi-Agent Systems [38.44649280816596]
  We propose MAS-FIRE, a systematic framework for fault injection and reliability evaluation of Multi-Agent Systems.<n>We define a taxonomy of 15 fault types covering intra-agent cognitive errors and inter-agent coordination failures.<n>Applying MAS-FIRE to three representative MAS architectures, we uncover a rich set of fault-tolerant behaviors.
  arXiv  Detail & Related papers  (2026-02-23T13:47:43Z)
• ReBeCA: Unveiling Interpretable Behavior Hierarchy behind the Iterative Self-Reflection of Language Models with Causal Analysis [35.12196884025294]
  We introduce textbftextttReBeCA (self-textbftexttReflection textbftextttBehavior explained through textbftextttBehavior), a framework that unveils the interpretable behavioral hierarchy governing the self-reflection outcome.<n>By modeling self-reflection trajectories as causal graphs, ReBeCA isolates genuine determinants of performance.
  arXiv  Detail & Related papers  (2026-02-06T04:00:57Z)
• Generation Order and Parallel Decoding in Masked Diffusion Models: An Information-Theoretic Perspective [16.942478643768144]
  Masked Diffusion Models (MDMs) significantly accelerate inference by trading off sequential determinism.<n>We provide a unified information-theoretic framework to decouple and analyze two fundamental sources of failure: order sensitivity and parallelization bias.
  arXiv  Detail & Related papers  (2026-01-30T20:15:18Z)
• RAudit: A Blind Auditing Protocol for Large Language Model Reasoning [0.8594140167290097]
  Inference-time scaling can amplify reasoning pathologies: sycophancy, rung collapse, and premature certainty.<n>We present RAudit, a diagnostic protocol for auditing LLM reasoning without ground truth access.
  arXiv  Detail & Related papers  (2026-01-30T16:22:45Z)
• Recoverability Has a Law: The ERR Measure for Tool-Augmented Agents [0.0]
  We show that recoverability follows a measurable law in language model agents.<n>We empirically validate the law across five tool-use benchmarks spanning controlled perturbations, diagnostic reasoning, and real-world APIs.<n>Our results reveal that recoverability is not an artifact of model scale or architecture, but a governed property of interaction dynamics.
  arXiv  Detail & Related papers  (2026-01-29T21:55:50Z)
• Consistency Is Not Always Correct: Towards Understanding the Role of Exploration in Post-Training Reasoning [75.79451512757844]
  Foundation models exhibit broad knowledge but limited task-specific reasoning.<n> RLVR and inference scaling motivate post-training strategies such as RLVR and inference scaling.<n>We show that RLVR induces a squeezing effect, reducing reasoning entropy and forgetting some correct paths.
  arXiv  Detail & Related papers  (2025-11-10T18:25:26Z)
• Alignment Tipping Process: How Self-Evolution Pushes LLM Agents Off the Rails [103.05296856071931]
  We identify the Alignment Tipping Process (ATP), a critical post-deployment risk unique to self-evolving Large Language Model (LLM) agents.<n>ATP arises when continual interaction drives agents to abandon alignment constraints established during training in favor of reinforced, self-interested strategies.<n>Our experiments show that alignment benefits erode rapidly under self-evolution, with initially aligned models converging toward unaligned states.
  arXiv  Detail & Related papers  (2025-10-06T14:48:39Z)
• ReaLM: Reflection-Enhanced Autonomous Reasoning with Small Language Models [76.28894983518164]
  Small Language Models (SLMs) are a cost-effective alternative to Large Language Models (LLMs)<n>They often struggle with complex reasoning due to their limited capacity and a tendency to produce mistakes or inconsistent answers.<n>We introduce ReaLM, a reinforcement learning framework for robust and self-sufficient reasoning in vertical domains.
  arXiv  Detail & Related papers  (2025-08-17T14:50:23Z)
• Lost at the Beginning of Reasoning [85.17612793300238]
  We show that the first reasoning step exerts a disproportionately large influence on the final prediction.<n>We propose an efficient sampling strategy that leverages a reward model to identify and retain high-quality first reasoning steps.
  arXiv  Detail & Related papers  (2025-06-27T09:53:57Z)
• Bridging Internal Probability and Self-Consistency for Effective and Efficient LLM Reasoning [53.25336975467293]
  We present the first theoretical error decomposition analysis of methods such as perplexity and self-consistency.<n>Our analysis reveals a fundamental trade-off: perplexity methods suffer from substantial model error due to the absence of a proper consistency function.<n>We propose Reasoning-Pruning Perplexity Consistency (RPC), which integrates perplexity with self-consistency, and Reasoning Pruning, which eliminates low-probability reasoning paths.
  arXiv  Detail & Related papers  (2025-02-01T18:09:49Z)
• Self-Healing Machine Learning: A Framework for Autonomous Adaptation in Real-World Environments [50.310636905746975]
  Real-world machine learning systems often encounter model performance degradation due to distributional shifts in the underlying data generating process. Existing approaches to addressing shifts, such as concept drift adaptation, are limited by their reason-agnostic nature. We propose self-healing machine learning (SHML) to overcome these limitations.
  arXiv  Detail & Related papers  (2024-10-31T20:05:51Z)
• Nonparametric Identifiability of Causal Representations from Unknown Interventions [63.1354734978244]
  We study causal representation learning, the task of inferring latent causal variables and their causal relations from mixtures of the variables. Our goal is to identify both the ground truth latents and their causal graph up to a set of ambiguities which we show to be irresolvable from interventional data.
  arXiv  Detail & Related papers  (2023-06-01T10:51:58Z)

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.