Trivium: Temporal Regret as a First-Class Objective for Causal-Memory Controllers

• URL: http://arxiv.org/abs/2606.04421v2
• Date: Sat, 06 Jun 2026 03:16:02 GMT
• Title: Trivium: Temporal Regret as a First-Class Objective for Causal-Memory Controllers
• Abstract summary: We argue that this is a structural problem, not merely a model-capacity one.<n>We propose long-horizon temporal regret as a first-class objective alongside outcome regret and epistemic regret over the working causal model.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Many current agentic systems and LLM pipelines correct mistakes by optimizing outcome reward. This addresses only the what of failure: when an outcome diverges from prediction, the why and when of the mismatch are not systematically logged, reviewed, or corrected, so the same error can recur episode after episode. We argue that this is a structural problem, not merely a model-capacity one. We propose long-horizon temporal regret as a first-class objective alongside outcome regret and epistemic regret over the working causal model. Temporal regret captures when failure persists: how long a miscalibrated causal model is tolerated before correction. Epistemic regret captures why failure persists: residual uncertainty or error in the working causal model. Together, the three regrets give a falsifiable account of what, why, and when a long-lived agent can fail. Modeling the agent as a stream of E episodes, we prove three conditional results under explicit causal-probing, persistence, and detectability assumptions. First, under observationally equivalent confounding, outcome-only learning cannot distinguish causal from spurious structure without an intervention channel, so temporal miscalibration can persist linearly even after outcome regret is driven to zero. Second, with a persistent causal log and budgeted probes, total probe complexity is logarithmic in the episode horizon, inducing O(log E) temporal regret. Third, under K detectable change-points, the rate extends to O(K log E). We instantiate Trivium and pre-register five falsifiable predictions. On CausalBench-Seq, Trivium follows the predicted logarithmic envelope while outcome-only baselines grow linearly. A pilot real-LLM stream provides preliminary external-validity evidence across one full E = 500 run and three E = 100 frontier-model pilots. Self-learning here means revising an external causal model, not retraining LLM weights.

Related papers

• Explanatory Engagement Under Rare Anomalous Failure: Asymptotic Rarity in Model Behavior (or: The Asymptotic AI) [0.0]
  We build a local, zero-cost harness on three open-weight models (qwen3:8b, llama3.1:8b, mistral:7b) running a repeated tool-call task.<n>We hypothesized a rise in engagement as failures grew rarer, then a collapse near a detectability threshold.<n>A companion guaranteed-failure run shows models differ in whether they recognize an anomaly, distinct from engagement once recognized.
  arXiv  Detail & Related papers  (2026-08-13T10:25:40Z)
• The Knowing-Saying Gap: When Probes See Errors that Confidence Misses [20.46211358172975]
  Linear probes detect corrupted context in language models with near-perfect accuracy, yet this does not translate into reliable failure prediction.<n>Across multi-hop arithmetic chains, probes that detect corruption turn out to be uninformative about final answer correctness.<n>As a real-time monitor, probe-based interventions are sharply model and error-type dependent.
  arXiv  Detail & Related papers  (2026-07-21T12:13:10Z)
• Why LLMs Fail at Causal Discovery and How Interventional Agents Escape [2.7976995580303305]
  Causal discovery is a cornerstone of scientific reasoning, yet whether large language models can perform it reliably remains an open question.<n>Recent benchmarks show that even fine-tuned models plateau on simple causal graphs and degrade as complexity grows, but why they fail has not been established.<n>We prove the failure is fundamental: supervised fine-tuning, direct preference optimization, and in-context learning all produce predictors that cannot distinguish between causal graphs generating similar observational data.
  arXiv  Detail & Related papers  (2026-05-26T18:37:03Z)
• Towards Counterfactual Explanation and Assertion Inference for CPS Debugging [0.0]
  We introduce DeCaF, a counterfactual-guided explanation and assertion-based characterization framework for cyber-physical systems.<n>Given a failing test input, DeCaF generates counterfactual changes to the input signals that transform the test from failing to passing.<n>Our approach combines three counterfactual generators with two causal models, and infers success assertions.
  arXiv  Detail & Related papers  (2026-04-09T00:53:00Z)
• Deep Doubly Debiased Longitudinal Effect Estimation with ICE G-Computation [13.1234934131475]
  Estimating longitudinal treatment effects is essential for sequential decision-making but is challenging due to treatment-confounder feedback.<n>We propose D3-Net, a framework that mitigates error propagation in ICE training and then applies a robust final correction.<n>Our model, D3-Net, robustly reduces bias and variance across different horizons, counterfactuals, and time-varying confoundings.
  arXiv  Detail & Related papers  (2026-02-12T20:16:27Z)
• Right for the Wrong Reasons: Epistemic Regret Minimization for Causal Rung Collapse in LLMs [0.0]
  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.
  arXiv  Detail & Related papers  (2026-02-12T07:48:21Z)
• "I May Not Have Articulated Myself Clearly": Diagnosing Dynamic Instability in LLM Reasoning at Inference Time [1.570719611178015]
  Reasoning failures in large language models (LLMs) are typically measured only at the end of a generation, yet many failures manifest as a process-level breakdown.<n>We define a simple instability signal that combines consecutive-step distributional shift (JSD) and uncertainty (entropy)<n>Across GSM8K and HotpotQA, instability strength predicts wrong answers with above-chance AUC and yields monotonic bucket-level accuracy decline.
  arXiv  Detail & Related papers  (2026-02-02T22:11:25Z)
• ResAD: Normalized Residual Trajectory Modeling for End-to-End Autonomous Driving [64.42138266293202]
  ResAD is a Normalized Residual Trajectory Modeling framework.<n>It reframes the learning task to predict the residual deviation from an inertial reference.<n>On the NAVSIM benchmark, ResAD achieves a state-of-the-art PDMS of 88.6 using a vanilla diffusion policy.
  arXiv  Detail & Related papers  (2025-10-09T17:59:36Z)
• Error-quantified Conformal Inference for Time Series [55.11926160774831]
  Uncertainty quantification in time series prediction is challenging due to the temporal dependence and distribution shift on sequential data.<n>We propose itError-quantified Conformal Inference (ECI) by smoothing the quantile loss function.<n>ECI can achieve valid miscoverage control and output tighter prediction sets than other baselines.
  arXiv  Detail & Related papers  (2025-02-02T15:02:36Z)
• LARA: A Light and Anti-overfitting Retraining Approach for Unsupervised Time Series Anomaly Detection [49.52429991848581]
  We propose a Light and Anti-overfitting Retraining Approach (LARA) for deep variational auto-encoder based time series anomaly detection methods (VAEs) This work aims to make three novel contributions: 1) the retraining process is formulated as a convex problem and can converge at a fast rate as well as prevent overfitting; 2) designing a ruminate block, which leverages the historical data without the need to store them; and 3) mathematically proving that when fine-tuning the latent vector and reconstructed data, the linear formations can achieve the least adjusting errors between the ground truths and the fine-tuned ones.
  arXiv  Detail & Related papers  (2023-10-09T12:36:16Z)
• Uncovering the Missing Pattern: Unified Framework Towards Trajectory Imputation and Prediction [60.60223171143206]
  Trajectory prediction is a crucial undertaking in understanding entity movement or human behavior from observed sequences. Current methods often assume that the observed sequences are complete while ignoring the potential for missing values. This paper presents a unified framework, the Graph-based Conditional Variational Recurrent Neural Network (GC-VRNN), which can perform trajectory imputation and prediction simultaneously.
  arXiv  Detail & Related papers  (2023-03-28T14:27:27Z)
• Are we certain it's anomalous? [57.729669157989235]
  Anomaly detection in time series is a complex task since anomalies are rare due to highly non-linear temporal correlations. Here we propose the novel use of Hyperbolic uncertainty for Anomaly Detection (HypAD) HypAD learns self-supervisedly to reconstruct the input signal.
  arXiv  Detail & Related papers  (2022-11-16T21:31:39Z)
• Optimization Variance: Exploring Generalization Properties of DNNs [83.78477167211315]
  The test error of a deep neural network (DNN) often demonstrates double descent. We propose a novel metric, optimization variance (OV), to measure the diversity of model updates.
  arXiv  Detail & Related papers  (2021-06-03T09:34:17Z)

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.